Fix ft_title_rag_fine (#11555)

### What problem does this PR solve?

Fix ft_title_rag_fine

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

.github/workflows/release.yml

@@ -16,10 +16,10 @@ concurrency:
 
 jobs:
   release:
-    runs-on: [ "self-hosted", "overseas" ]
+    runs-on: [ "self-hosted", "ragflow-test" ]
     steps:
       - name: Ensure workspace ownership
-        run: echo "chown -R $USER $GITHUB_WORKSPACE" && sudo chown -R $USER $GITHUB_WORKSPACE
+        run: echo "chown -R ${USER} ${GITHUB_WORKSPACE}" && sudo chown -R ${USER} ${GITHUB_WORKSPACE}
 
       # https://github.com/actions/checkout/blob/v3/README.md
       - name: Check out code
@@ -31,37 +31,37 @@ jobs:
 
       - name: Prepare release body
         run: |
-          if [[ $GITHUB_EVENT_NAME == 'create' ]]; then
+          if [[ ${GITHUB_EVENT_NAME} == "create" ]]; then
             RELEASE_TAG=${GITHUB_REF#refs/tags/}
-            if [[ $RELEASE_TAG == 'nightly' ]]; then
+            if [[ ${RELEASE_TAG} == "nightly" ]]; then
               PRERELEASE=true
             else
               PRERELEASE=false
             fi
-            echo "Workflow triggered by create tag: $RELEASE_TAG"
+            echo "Workflow triggered by create tag: ${RELEASE_TAG}"
           else
             RELEASE_TAG=nightly
             PRERELEASE=true
             echo "Workflow triggered by schedule"
           fi
-          echo "RELEASE_TAG=$RELEASE_TAG" >> $GITHUB_ENV
+          echo "RELEASE_TAG=${RELEASE_TAG}" >> ${GITHUB_ENV}
-          echo "PRERELEASE=$PRERELEASE" >> $GITHUB_ENV
+          echo "PRERELEASE=${PRERELEASE}" >> ${GITHUB_ENV}
           RELEASE_DATETIME=$(date --rfc-3339=seconds)
-          echo Release $RELEASE_TAG created from $GITHUB_SHA at $RELEASE_DATETIME > release_body.md
+          echo Release ${RELEASE_TAG} created from ${GITHUB_SHA} at ${RELEASE_DATETIME} > release_body.md
 
       - name: Move the existing mutable tag
         # https://github.com/softprops/action-gh-release/issues/171
         run: |
           git fetch --tags
-          if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then
+          if [[ ${GITHUB_EVENT_NAME} == "schedule" ]]; then
             # Determine if a given tag exists and matches a specific Git commit.
             # actions/checkout@v4 fetch-tags doesn't work when triggered by schedule
-            if [ "$(git rev-parse -q --verify "refs/tags/$RELEASE_TAG")" = "$GITHUB_SHA" ]; then
+            if [ "$(git rev-parse -q --verify "refs/tags/${RELEASE_TAG}")" = "${GITHUB_SHA}" ]; then
-              echo "mutable tag $RELEASE_TAG exists and matches $GITHUB_SHA"
+              echo "mutable tag ${RELEASE_TAG} exists and matches ${GITHUB_SHA}"
             else
-              git tag -f $RELEASE_TAG $GITHUB_SHA
+              git tag -f ${RELEASE_TAG} ${GITHUB_SHA}
-              git push -f origin $RELEASE_TAG:refs/tags/$RELEASE_TAG
+              git push -f origin ${RELEASE_TAG}:refs/tags/${RELEASE_TAG}
-              echo "created/moved mutable tag $RELEASE_TAG to $GITHUB_SHA"
+              echo "created/moved mutable tag ${RELEASE_TAG} to ${GITHUB_SHA}"
             fi
           fi
 
@@ -75,62 +75,20 @@ jobs:
           # The body field does not support environment variable substitution directly.
           body_path: release_body.md
 
-      # https://github.com/marketplace/actions/docker-login
+      - name: Build and push ragflow-sdk
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: infiniflow
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      # https://github.com/marketplace/actions/build-and-push-docker-images
-      - name: Build and push full image
-        uses: docker/build-push-action@v6
-        with:
-          context: .
-          push: true
-          tags: |
-            infiniflow/ragflow:${{ env.RELEASE_TAG }}
-            infiniflow/ragflow:latest-full
-          file: Dockerfile
-          platforms: linux/amd64
-
-      # https://github.com/marketplace/actions/build-and-push-docker-images
-      - name: Build and push slim image
-        uses: docker/build-push-action@v6
-        with:
-          context: .
-          push: true
-          tags: |
-            infiniflow/ragflow:${{ env.RELEASE_TAG }}-slim
-            infiniflow/ragflow:latest-slim
-          file: Dockerfile
-          build-args: LIGHTEN=1
-          platforms: linux/amd64
-
-      - name: Build ragflow-sdk
         if: startsWith(github.ref, 'refs/tags/v')
         run: |
-          cd sdk/python && \
+          cd sdk/python && uv build && uv publish --token ${{ secrets.PYPI_API_TOKEN }}
-          uv build
 
-      - name: Publish package distributions to PyPI
+      - name: Build and push ragflow-cli
-        if: startsWith(github.ref, 'refs/tags/v')
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          packages-dir: sdk/python/dist/
-          password: ${{ secrets.PYPI_API_TOKEN }}
-          verbose: true
-
-      - name: Build ragflow-cli
         if: startsWith(github.ref, 'refs/tags/v')
         run: |
-          cd admin/client && \
+          cd admin/client && uv build && uv publish --token ${{ secrets.PYPI_API_TOKEN }}
-          uv build
 
-      - name: Publish client package distributions to PyPI
+      - name: Build and push image
-        if: startsWith(github.ref, 'refs/tags/v')
+        run: |
-        uses: pypa/gh-action-pypi-publish@release/v1
+          sudo docker login --username infiniflow --password-stdin <<< ${{ secrets.DOCKERHUB_TOKEN }}
-        with:
+          sudo docker build --build-arg NEED_MIRROR=1 -t infiniflow/ragflow:${RELEASE_TAG} -f Dockerfile .
-          packages-dir: admin/client/dist/
+          sudo docker tag infiniflow/ragflow:${RELEASE_TAG} infiniflow/ragflow:latest
-          password: ${{ secrets.PYPI_API_TOKEN }}
+          sudo docker push infiniflow/ragflow:${RELEASE_TAG}
-          verbose: true
+          sudo docker push infiniflow/ragflow:latest

.github/workflows/tests.yml

@@ -9,8 +9,11 @@ on:
       - 'docs/**'
       - '*.md'
       - '*.mdx'
-  pull_request:
+  # The only difference between pull_request and pull_request_target is the context in which the workflow runs:
-    types: [ opened, synchronize, reopened, labeled ]
+  # — pull_request_target workflows use the workflow files from the default branch, and secrets are available.
+  # — pull_request workflows use the workflow files from the pull request branch, and secrets are unavailable.
+  pull_request_target:
+    types: [ synchronize, ready_for_review ]
     paths-ignore:
       - 'docs/**'
       - '*.md'
@@ -28,8 +31,8 @@ jobs:
     name: ragflow_tests
     # https://docs.github.com/en/actions/using-jobs/using-conditions-to-control-job-execution
     # https://github.com/orgs/community/discussions/26261
-    if: ${{ github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'ci') }}
+    if: ${{ github.event_name != 'pull_request_target' || (contains(github.event.pull_request.labels.*.name, 'ci') && github.event.pull_request.mergeable == true) }}
-    runs-on: [ "self-hosted", "debug" ]
+    runs-on: [ "self-hosted", "ragflow-test" ]
     steps:
       # https://github.com/hmarr/debug-action
       #- uses: hmarr/debug-action@v2
@@ -37,44 +40,45 @@ jobs:
       - name: Ensure workspace ownership
         run: |
           echo "Workflow triggered by ${{ github.event_name }}"
-          echo "chown -R $USER $GITHUB_WORKSPACE" && sudo chown -R $USER $GITHUB_WORKSPACE
+          echo "chown -R ${USER} ${GITHUB_WORKSPACE}" && sudo chown -R ${USER} ${GITHUB_WORKSPACE}
 
       # https://github.com/actions/checkout/issues/1781
       - name: Check out code
         uses: actions/checkout@v4
         with:
+          ref: ${{ (github.event_name == 'pull_request' || github.event_name == 'pull_request_target') && format('refs/pull/{0}/merge', github.event.pull_request.number) || github.sha }}
           fetch-depth: 0
           fetch-tags: true
 
       - name: Check workflow duplication
-        if: ${{ !cancelled() && !failure() && (github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'ci')) }}
+        if: ${{ !cancelled() && !failure() }}
         run: |
-          if [[ ${{ github.event_name }} != 'pull_request' ]]; then
+          if [[ ${GITHUB_EVENT_NAME} != "pull_request_target" && ${GITHUB_EVENT_NAME} != "schedule" ]]; then
             HEAD=$(git rev-parse HEAD)
             # Find a PR that introduced a given commit
             gh auth login --with-token <<< "${{ secrets.GITHUB_TOKEN }}"
             PR_NUMBER=$(gh pr list --search ${HEAD} --state merged --json number --jq .[0].number)
             echo "HEAD=${HEAD}"
             echo "PR_NUMBER=${PR_NUMBER}"
-            if [[ -n ${PR_NUMBER} ]]; then
+            if [[ -n "${PR_NUMBER}" ]]; then
               PR_SHA_FP=${RUNNER_WORKSPACE_PREFIX}/artifacts/${GITHUB_REPOSITORY}/PR_${PR_NUMBER}
-              if [[ -f ${PR_SHA_FP} ]]; then
+              if [[ -f "${PR_SHA_FP}" ]]; then
                 read -r PR_SHA PR_RUN_ID < "${PR_SHA_FP}"
                 # Calculate the hash of the current workspace content
                 HEAD_SHA=$(git rev-parse HEAD^{tree})
-                if [[ ${HEAD_SHA} == ${PR_SHA} ]]; then
+                if [[ "${HEAD_SHA}" == "${PR_SHA}" ]]; then
                   echo "Cancel myself since the workspace content hash is the same with PR #${PR_NUMBER} merged. See ${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${PR_RUN_ID} for details."
                   gh run cancel ${GITHUB_RUN_ID}
                   while true; do
                     status=$(gh run view ${GITHUB_RUN_ID} --json status -q .status)
-                    [ "$status" = "completed" ] && break
+                    [ "${status}" = "completed" ] && break
                     sleep 5
                   done
                   exit 1
                 fi
               fi
             fi
-          else
+          elif [[ ${GITHUB_EVENT_NAME} == "pull_request_target" ]]; then
             PR_NUMBER=${{ github.event.pull_request.number }}
             PR_SHA_FP=${RUNNER_WORKSPACE_PREFIX}/artifacts/${GITHUB_REPOSITORY}/PR_${PR_NUMBER}
             # Calculate the hash of the current workspace content
@@ -91,122 +95,177 @@ jobs:
           version: ">=0.11.x"
           args: "check"
 
-      - name: Build ragflow:nightly-slim
+      - name: Check comments of changed Python files
+        if: ${{ false }}
         run: |
-          RUNNER_WORKSPACE_PREFIX=${RUNNER_WORKSPACE_PREFIX:-$HOME}
+          if [[ ${{ github.event_name }} == 'pull_request_target' ]]; then
-          sudo docker pull ubuntu:22.04
+            CHANGED_FILES=$(git diff --name-only ${{ github.event.pull_request.base.sha }}...${{ github.event.pull_request.head.sha }} \
-          sudo DOCKER_BUILDKIT=1 docker build --build-arg LIGHTEN=1 --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
+              | grep -E '\.(py)$' || true)
+
+            if [ -n "$CHANGED_FILES" ]; then
+              echo "Check comments of changed Python files with check_comment_ascii.py"
+
+              readarray -t files <<< "$CHANGED_FILES"
+              HAS_ERROR=0
+
+              for file in "${files[@]}"; do
+                if [ -f "$file" ]; then
+                  if python3 check_comment_ascii.py "$file"; then
+                    echo "✅ $file"
+                  else
+                    echo "❌ $file"
+                    HAS_ERROR=1
+                  fi
+                fi
+              done
+
+              if [ $HAS_ERROR -ne 0 ]; then
+                exit 1
+              fi
+            else
+              echo "No Python files changed"
+            fi
+          fi
 
       - name: Build ragflow:nightly
         run: |
-          sudo DOCKER_BUILDKIT=1 docker build --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly .
+          RUNNER_WORKSPACE_PREFIX=${RUNNER_WORKSPACE_PREFIX:-${HOME}}
-
+          RAGFLOW_IMAGE=infiniflow/ragflow:${GITHUB_RUN_ID}
-      - name: Start ragflow:nightly-slim
+          echo "RAGFLOW_IMAGE=${RAGFLOW_IMAGE}" >> ${GITHUB_ENV}
-        run: |
+          sudo docker pull ubuntu:22.04
-          sudo docker compose -f docker/docker-compose.yml down --volumes --remove-orphans
+          sudo DOCKER_BUILDKIT=1 docker build --build-arg NEED_MIRROR=1 -f Dockerfile -t ${RAGFLOW_IMAGE} .
-          echo -e "\nRAGFLOW_IMAGE=infiniflow/ragflow:nightly-slim" >> docker/.env
+          if [[ ${GITHUB_EVENT_NAME} == "schedule" ]]; then
-          sudo docker compose -f docker/docker-compose.yml up -d
+            export HTTP_API_TEST_LEVEL=p3
-
+          else
-      - name: Stop ragflow:nightly-slim
+            export HTTP_API_TEST_LEVEL=p2
-        if: always()  # always run this step even if previous steps failed
+          fi
-        run: |
+          echo "HTTP_API_TEST_LEVEL=${HTTP_API_TEST_LEVEL}" >> ${GITHUB_ENV}
-          sudo docker compose -f docker/docker-compose.yml down -v
+          echo "RAGFLOW_CONTAINER=${GITHUB_RUN_ID}-ragflow-cpu-1" >> ${GITHUB_ENV}
 
       - name: Start ragflow:nightly
         run: |
-          echo -e "\nRAGFLOW_IMAGE=infiniflow/ragflow:nightly" >> docker/.env
+          # Determine runner number (default to 1 if not found)
-          sudo docker compose -f docker/docker-compose.yml up -d
+          RUNNER_NUM=$(sudo docker inspect $(hostname) --format '{{index .Config.Labels "com.docker.compose.container-number"}}' 2>/dev/null || true)
+          RUNNER_NUM=${RUNNER_NUM:-1}
+
+          # Compute port numbers using bash arithmetic
+          ES_PORT=$((1200 + RUNNER_NUM * 10))
+          OS_PORT=$((1201 + RUNNER_NUM * 10))
+          INFINITY_THRIFT_PORT=$((23817 + RUNNER_NUM * 10))
+          INFINITY_HTTP_PORT=$((23820 + RUNNER_NUM * 10))
+          INFINITY_PSQL_PORT=$((5432 + RUNNER_NUM * 10))
+          MYSQL_PORT=$((5455 + RUNNER_NUM * 10))
+          MINIO_PORT=$((9000 + RUNNER_NUM * 10))
+          MINIO_CONSOLE_PORT=$((9001 + RUNNER_NUM * 10))
+          REDIS_PORT=$((6379 + RUNNER_NUM * 10))
+          TEI_PORT=$((6380 + RUNNER_NUM * 10))
+          KIBANA_PORT=$((6601 + RUNNER_NUM * 10))
+          SVR_HTTP_PORT=$((9380 + RUNNER_NUM * 10))
+          ADMIN_SVR_HTTP_PORT=$((9381 + RUNNER_NUM * 10))
+          SVR_MCP_PORT=$((9382 + RUNNER_NUM * 10))
+          SANDBOX_EXECUTOR_MANAGER_PORT=$((9385 + RUNNER_NUM * 10))
+          SVR_WEB_HTTP_PORT=$((80 + RUNNER_NUM * 10))
+          SVR_WEB_HTTPS_PORT=$((443 + RUNNER_NUM * 10))
+
+          # Persist computed ports into docker/.env so docker-compose uses the correct host bindings
+          echo "" >> docker/.env
+          echo -e "ES_PORT=${ES_PORT}" >> docker/.env
+          echo -e "OS_PORT=${OS_PORT}" >> docker/.env
+          echo -e "INFINITY_THRIFT_PORT=${INFINITY_THRIFT_PORT}" >> docker/.env
+          echo -e "INFINITY_HTTP_PORT=${INFINITY_HTTP_PORT}" >> docker/.env
+          echo -e "INFINITY_PSQL_PORT=${INFINITY_PSQL_PORT}" >> docker/.env
+          echo -e "MYSQL_PORT=${MYSQL_PORT}" >> docker/.env
+          echo -e "MINIO_PORT=${MINIO_PORT}" >> docker/.env
+          echo -e "MINIO_CONSOLE_PORT=${MINIO_CONSOLE_PORT}" >> docker/.env
+          echo -e "REDIS_PORT=${REDIS_PORT}" >> docker/.env
+          echo -e "TEI_PORT=${TEI_PORT}" >> docker/.env
+          echo -e "KIBANA_PORT=${KIBANA_PORT}" >> docker/.env
+          echo -e "SVR_HTTP_PORT=${SVR_HTTP_PORT}" >> docker/.env
+          echo -e "ADMIN_SVR_HTTP_PORT=${ADMIN_SVR_HTTP_PORT}" >> docker/.env
+          echo -e "SVR_MCP_PORT=${SVR_MCP_PORT}" >> docker/.env
+          echo -e "SANDBOX_EXECUTOR_MANAGER_PORT=${SANDBOX_EXECUTOR_MANAGER_PORT}" >> docker/.env
+          echo -e "SVR_WEB_HTTP_PORT=${SVR_WEB_HTTP_PORT}" >> docker/.env
+          echo -e "SVR_WEB_HTTPS_PORT=${SVR_WEB_HTTPS_PORT}" >> docker/.env
+
+          echo -e "COMPOSE_PROFILES=\${COMPOSE_PROFILES},tei-cpu" >> docker/.env
+          echo -e "TEI_MODEL=BAAI/bge-small-en-v1.5" >> docker/.env
+          echo -e "RAGFLOW_IMAGE=${RAGFLOW_IMAGE}" >> docker/.env
+          echo "HOST_ADDRESS=http://host.docker.internal:${SVR_HTTP_PORT}" >> ${GITHUB_ENV}
+
+          sudo docker compose -f docker/docker-compose.yml -p ${GITHUB_RUN_ID} up -d
+          uv sync --python 3.10 --only-group test --no-default-groups --frozen && uv pip install sdk/python --group test
 
       - name: Run sdk tests against Elasticsearch
         run: |
           export http_proxy=""; export https_proxy=""; export no_proxy=""; export HTTP_PROXY=""; export HTTPS_PROXY=""; export NO_PROXY=""
-          export HOST_ADDRESS=http://host.docker.internal:9380
+          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
-          until sudo docker exec ragflow-server curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
             echo "Waiting for service to be available..."
             sleep 5
           done
-          if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then
+          source .venv/bin/activate && pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_sdk_api
-            export HTTP_API_TEST_LEVEL=p3
-          else
-            export HTTP_API_TEST_LEVEL=p2
-          fi
-          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && uv pip install sdk/python && uv run --only-group test --no-default-groups pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_sdk_api
 
       - name: Run frontend api tests against Elasticsearch
         run: |
           export http_proxy=""; export https_proxy=""; export no_proxy=""; export HTTP_PROXY=""; export HTTPS_PROXY=""; export NO_PROXY=""
-          export HOST_ADDRESS=http://host.docker.internal:9380
+          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
-          until sudo docker exec ragflow-server curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
             echo "Waiting for service to be available..."
             sleep 5
           done
-          cd sdk/python && UV_LINK_MODE=copy uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_frontend_api && pytest -s --tb=short get_email.py test_dataset.py
+          source .venv/bin/activate && pytest -s --tb=short sdk/python/test/test_frontend_api/get_email.py sdk/python/test/test_frontend_api/test_dataset.py
           
       - name: Run http api tests against Elasticsearch
         run: |
           export http_proxy=""; export https_proxy=""; export no_proxy=""; export HTTP_PROXY=""; export HTTPS_PROXY=""; export NO_PROXY=""
-          export HOST_ADDRESS=http://host.docker.internal:9380
+          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
-          until sudo docker exec ragflow-server curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
             echo "Waiting for service to be available..."
             sleep 5
           done
-          if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then
+          source .venv/bin/activate && pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_http_api
-            export HTTP_API_TEST_LEVEL=p3
-          else
-            export HTTP_API_TEST_LEVEL=p2
-          fi
-          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && uv run --only-group test --no-default-groups pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_http_api
 
       - name: Stop ragflow:nightly
         if: always()  # always run this step even if previous steps failed
         run: |
-          sudo docker compose -f docker/docker-compose.yml down -v
+          sudo docker compose -f docker/docker-compose.yml -p ${GITHUB_RUN_ID} down -v || true
+          sudo docker ps -a --filter "label=com.docker.compose.project=${GITHUB_RUN_ID}" -q | xargs -r sudo docker rm -f
 
       - name: Start ragflow:nightly
         run: |
-          sudo DOC_ENGINE=infinity docker compose -f docker/docker-compose.yml up -d
+          sed -i '1i DOC_ENGINE=infinity' docker/.env
+          sudo docker compose -f docker/docker-compose.yml -p ${GITHUB_RUN_ID} up -d
 
       - name: Run sdk tests against Infinity
         run: |
           export http_proxy=""; export https_proxy=""; export no_proxy=""; export HTTP_PROXY=""; export HTTPS_PROXY=""; export NO_PROXY=""
-          export HOST_ADDRESS=http://host.docker.internal:9380
+          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
-          until sudo docker exec ragflow-server curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
             echo "Waiting for service to be available..."
             sleep 5
           done
-          if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then
+          source .venv/bin/activate && DOC_ENGINE=infinity pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_sdk_api
-            export HTTP_API_TEST_LEVEL=p3
-          else
-            export HTTP_API_TEST_LEVEL=p2
-          fi
-          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && uv pip install sdk/python && DOC_ENGINE=infinity uv run --only-group test --no-default-groups pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_sdk_api
 
       - name: Run frontend api tests against Infinity
         run: |
           export http_proxy=""; export https_proxy=""; export no_proxy=""; export HTTP_PROXY=""; export HTTPS_PROXY=""; export NO_PROXY=""
-          export HOST_ADDRESS=http://host.docker.internal:9380
+          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
-          until sudo docker exec ragflow-server curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
             echo "Waiting for service to be available..."
             sleep 5
           done
-          cd sdk/python && UV_LINK_MODE=copy uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_frontend_api && pytest -s --tb=short get_email.py test_dataset.py
+          source .venv/bin/activate && DOC_ENGINE=infinity pytest -s --tb=short sdk/python/test/test_frontend_api/get_email.py sdk/python/test/test_frontend_api/test_dataset.py
 
       - name: Run http api tests against Infinity
         run: |
           export http_proxy=""; export https_proxy=""; export no_proxy=""; export HTTP_PROXY=""; export HTTPS_PROXY=""; export NO_PROXY=""
-          export HOST_ADDRESS=http://host.docker.internal:9380
+          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
-          until sudo docker exec ragflow-server curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
             echo "Waiting for service to be available..."
             sleep 5
           done
-          if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then
+          source .venv/bin/activate && DOC_ENGINE=infinity pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_http_api
-            export HTTP_API_TEST_LEVEL=p3
-          else
-            export HTTP_API_TEST_LEVEL=p2
-          fi
-          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && DOC_ENGINE=infinity uv run --only-group test --no-default-groups pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_http_api
 
       - name: Stop ragflow:nightly
         if: always()  # always run this step even if previous steps failed
         run: |
-          sudo DOC_ENGINE=infinity docker compose -f docker/docker-compose.yml down -v
+          # Sometimes `docker compose down` fail due to hang container, heavy load etc. Need to remove such containers to release resources(for example, listen ports).
+          sudo docker compose -f docker/docker-compose.yml -p ${GITHUB_RUN_ID} down -v || true
+          sudo docker ps -a --filter "label=com.docker.compose.project=${GITHUB_RUN_ID}" -q | xargs -r sudo docker rm -f
+          if [[ -n ${RAGFLOW_IMAGE} ]]; then
+            sudo docker rmi -f ${RAGFLOW_IMAGE}
+          fi

CLAUDE.md

@@ -0,0 +1,116 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Project Overview
+
+RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It's a full-stack application with:
+- Python backend (Flask-based API server)
+- React/TypeScript frontend (built with UmiJS)
+- Microservices architecture with Docker deployment
+- Multiple data stores (MySQL, Elasticsearch/Infinity, Redis, MinIO)
+
+## Architecture
+
+### Backend (`/api/`)
+- **Main Server**: `api/ragflow_server.py` - Flask application entry point
+- **Apps**: Modular Flask blueprints in `api/apps/` for different functionalities:
+  - `kb_app.py` - Knowledge base management
+  - `dialog_app.py` - Chat/conversation handling
+  - `document_app.py` - Document processing
+  - `canvas_app.py` - Agent workflow canvas
+  - `file_app.py` - File upload/management
+- **Services**: Business logic in `api/db/services/`
+- **Models**: Database models in `api/db/db_models.py`
+
+### Core Processing (`/rag/`)
+- **Document Processing**: `deepdoc/` - PDF parsing, OCR, layout analysis
+- **LLM Integration**: `rag/llm/` - Model abstractions for chat, embedding, reranking
+- **RAG Pipeline**: `rag/flow/` - Chunking, parsing, tokenization
+- **Graph RAG**: `graphrag/` - Knowledge graph construction and querying
+
+### Agent System (`/agent/`)
+- **Components**: Modular workflow components (LLM, retrieval, categorize, etc.)
+- **Templates**: Pre-built agent workflows in `agent/templates/`
+- **Tools**: External API integrations (Tavily, Wikipedia, SQL execution, etc.)
+
+### Frontend (`/web/`)
+- React/TypeScript with UmiJS framework
+- Ant Design + shadcn/ui components
+- State management with Zustand
+- Tailwind CSS for styling
+
+## Common Development Commands
+
+### Backend Development
+```bash
+# Install Python dependencies
+uv sync --python 3.10 --all-extras
+uv run download_deps.py
+pre-commit install
+
+# Start dependent services
+docker compose -f docker/docker-compose-base.yml up -d
+
+# Run backend (requires services to be running)
+source .venv/bin/activate
+export PYTHONPATH=$(pwd)
+bash docker/launch_backend_service.sh
+
+# Run tests
+uv run pytest
+
+# Linting
+ruff check
+ruff format
+```
+
+### Frontend Development
+```bash
+cd web
+npm install
+npm run dev        # Development server
+npm run build      # Production build
+npm run lint       # ESLint
+npm run test       # Jest tests
+```
+
+### Docker Development
+```bash
+# Full stack with Docker
+cd docker
+docker compose -f docker-compose.yml up -d
+
+# Check server status
+docker logs -f ragflow-server
+
+# Rebuild images
+docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly .
+```
+
+## Key Configuration Files
+
+- `docker/.env` - Environment variables for Docker deployment
+- `docker/service_conf.yaml.template` - Backend service configuration
+- `pyproject.toml` - Python dependencies and project configuration
+- `web/package.json` - Frontend dependencies and scripts
+
+## Testing
+
+- **Python**: pytest with markers (p1/p2/p3 priority levels)
+- **Frontend**: Jest with React Testing Library
+- **API Tests**: HTTP API and SDK tests in `test/` and `sdk/python/test/`
+
+## Database Engines
+
+RAGFlow supports switching between Elasticsearch (default) and Infinity:
+- Set `DOC_ENGINE=infinity` in `docker/.env` to use Infinity
+- Requires container restart: `docker compose down -v && docker compose up -d`
+
+## Development Environment Requirements
+
+- Python 3.10-3.12
+- Node.js >=18.20.4
+- Docker & Docker Compose
+- uv package manager
+- 16GB+ RAM, 50GB+ disk space

Dockerfile

@@ -4,8 +4,6 @@ USER root
 SHELL ["/bin/bash", "-c"]
 
 ARG NEED_MIRROR=0
-ARG LIGHTEN=0
-ENV LIGHTEN=${LIGHTEN}
 
 WORKDIR /ragflow
 
@@ -17,13 +15,6 @@ RUN --mount=type=bind,from=infiniflow/ragflow_deps:latest,source=/huggingface.co
         /huggingface.co/InfiniFlow/text_concat_xgb_v1.0 \
         /huggingface.co/InfiniFlow/deepdoc \
         | tar -xf - --strip-components=3 -C /ragflow/rag/res/deepdoc 
-RUN --mount=type=bind,from=infiniflow/ragflow_deps:latest,source=/huggingface.co,target=/huggingface.co \
-    if [ "$LIGHTEN" != "1" ]; then \
-        (tar -cf - \
-            /huggingface.co/BAAI/bge-large-zh-v1.5 \
-            /huggingface.co/maidalun1020/bce-embedding-base_v1 \
-            | tar -xf - --strip-components=2 -C /root/.ragflow) \
-    fi
 
 # https://github.com/chrismattmann/tika-python
 # This is the only way to run python-tika without internet access. Without this set, the default is to check the tika version and pull latest every time from Apache.
@@ -60,14 +51,16 @@ RUN --mount=type=cache,id=ragflow_apt,target=/var/cache/apt,sharing=locked \
     apt install -y libpython3-dev libgtk-4-1 libnss3 xdg-utils libgbm-dev && \
     apt install -y libjemalloc-dev && \
     apt install -y python3-pip pipx nginx unzip curl wget git vim less && \
-    apt install -y ghostscript
+    apt install -y ghostscript && \
+    apt install -y pandoc && \
+    apt install -y texlive
 
 RUN if [ "$NEED_MIRROR" == "1" ]; then \
-        pip3 config set global.index-url https://mirrors.aliyun.com/pypi/simple && \
+        pip3 config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple && \
-        pip3 config set global.trusted-host mirrors.aliyun.com; \
+        pip3 config set global.trusted-host pypi.tuna.tsinghua.edu.cn; \
         mkdir -p /etc/uv && \
         echo "[[index]]" > /etc/uv/uv.toml && \
-        echo 'url = "https://mirrors.aliyun.com/pypi/simple"' >> /etc/uv/uv.toml && \
+        echo 'url = "https://pypi.tuna.tsinghua.edu.cn/simple"' >> /etc/uv/uv.toml && \
         echo "default = true" >> /etc/uv/uv.toml; \
     fi; \
     pipx install uv
@@ -151,15 +144,11 @@ COPY pyproject.toml uv.lock ./
 # uv records index url into uv.lock but doesn't failover among multiple indexes
 RUN --mount=type=cache,id=ragflow_uv,target=/root/.cache/uv,sharing=locked \
     if [ "$NEED_MIRROR" == "1" ]; then \
-        sed -i 's|pypi.org|mirrors.aliyun.com/pypi|g' uv.lock; \
+        sed -i 's|pypi.org|pypi.tuna.tsinghua.edu.cn|g' uv.lock; \
     else \
-        sed -i 's|mirrors.aliyun.com/pypi|pypi.org|g' uv.lock; \
+        sed -i 's|pypi.tuna.tsinghua.edu.cn|pypi.org|g' uv.lock; \
     fi; \
-    if [ "$LIGHTEN" == "1" ]; then \
+    uv sync --python 3.10 --frozen
-        uv sync --python 3.10 --frozen; \
-    else \
-        uv sync --python 3.10 --frozen --all-extras; \
-    fi
 
 COPY web web
 COPY docs docs
@@ -169,11 +158,7 @@ RUN --mount=type=cache,id=ragflow_npm,target=/root/.npm,sharing=locked \
 COPY .git /ragflow/.git
 
 RUN version_info=$(git describe --tags --match=v* --first-parent --always); \
-    if [ "$LIGHTEN" == "1" ]; then \
+    version_info="$version_info"; \
-        version_info="$version_info slim"; \
-    else \
-        version_info="$version_info full"; \
-    fi; \
     echo "RAGFlow version: $version_info"; \
     echo $version_info > /ragflow/VERSION
 
@@ -202,6 +187,7 @@ COPY agentic_reasoning agentic_reasoning
 COPY pyproject.toml uv.lock ./
 COPY mcp mcp
 COPY plugin plugin
+COPY common common
 
 COPY docker/service_conf.yaml.template ./conf/service_conf.yaml.template
 COPY docker/entrypoint.sh ./

Dockerfile_tei

@@ -0,0 +1,14 @@
+FROM ghcr.io/huggingface/text-embeddings-inference:cpu-1.8
+
+# uv tool install huggingface_hub
+# hf download --local-dir tei_data/BAAI/bge-small-en-v1.5 BAAI/bge-small-en-v1.5
+# hf download --local-dir tei_data/BAAI/bge-m3 BAAI/bge-m3
+# hf download --local-dir tei_data/Qwen/Qwen3-Embedding-0.6B Qwen/Qwen3-Embedding-0.6B
+COPY tei_data /data
+
+# curl -X POST http://localhost:6380/embed -H "Content-Type: application/json" -d '{"inputs": "Hello, world! This is a test sentence."}'
+# curl -X POST http://tei:80/embed -H "Content-Type: application/json" -d '{"inputs": "Hello, world! This is a test sentence."}'
+# [[-0.058816575,0.019564206,0.026697718,...]]
+
+# curl -X POST http://localhost:6380/v1/embeddings -H "Content-Type: application/json" -d '{"input": "Hello, world! This is a test sentence."}'
+# {"object":"list","data":[{"object":"embedding","embedding":[-0.058816575,0.019564206,...],"index":0}],"model":"BAAI/bge-small-en-v1.5","usage":{"prompt_tokens":12,"total_tokens":12}}

README.md

@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.22.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@@ -43,7 +43,9 @@
   <a href="https://demo.ragflow.io">Demo</a>
 </h4>
 
-#
+<div align="center" style="margin-top:20px;margin-bottom:20px;">
+<img src="https://raw.githubusercontent.com/infiniflow/ragflow-docs/refs/heads/image/image/ragflow-octoverse.png" width="1200"/>
+</div>
 
 <div align="center">
 <a href="https://trendshift.io/repositories/9064" target="_blank"><img src="https://trendshift.io/api/badge/repositories/9064" alt="infiniflow%2Fragflow | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
@@ -59,8 +61,7 @@
 - 🔎 [System Architecture](#-system-architecture)
 - 🎬 [Get Started](#-get-started)
 - 🔧 [Configurations](#-configurations)
-- 🔧 [Build a docker image without embedding models](#-build-a-docker-image-without-embedding-models)
+- 🔧 [Build a Docker image](#-build-a-docker-image)
-- 🔧 [Build a docker image including embedding models](#-build-a-docker-image-including-embedding-models)
 - 🔨 [Launch service from source for development](#-launch-service-from-source-for-development)
 - 📚 [Documentation](#-documentation)
 - 📜 [Roadmap](#-roadmap)
@@ -84,15 +85,15 @@ Try our demo at [https://demo.ragflow.io](https://demo.ragflow.io).
 
 ## 🔥 Latest Updates
 
+- 2025-11-19 Supports Gemini 3 Pro.
+- 2025-11-12 Supports data synchronization from Confluence, S3, Notion, Discord, Google Drive.
+- 2025-10-23 Supports MinerU & Docling as document parsing methods.
 - 2025-10-15 Supports orchestrable ingestion pipeline.
 - 2025-08-08 Supports OpenAI's latest GPT-5 series models.
 - 2025-08-01 Supports agentic workflow and MCP.
 - 2025-05-23 Adds a Python/JavaScript code executor component to Agent.
 - 2025-05-05 Supports cross-language query.
 - 2025-03-19 Supports using a multi-modal model to make sense of images within PDF or DOCX files.
-- 2025-02-28 Combined with Internet search (Tavily), supports reasoning like Deep Research for any LLMs.
-- 2024-12-18 Upgrades Document Layout Analysis model in DeepDoc.
-- 2024-08-22 Support text to SQL statements through RAG.
 
 ## 🎉 Stay Tuned
 
@@ -135,7 +136,7 @@ releases! 🌟
 ## 🔎 System Architecture
 
 <div align="center" style="margin-top:20px;margin-bottom:20px;">
-<img src="https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485" width="1000"/>
+<img src="https://github.com/user-attachments/assets/31b0dd6f-ca4f-445a-9457-70cb44a381b2" width="1000"/>
 </div>
 
 ## 🎬 Get Started
@@ -174,41 +175,48 @@ releases! 🌟
    > ```bash
    > vm.max_map_count=262144
    > ```
-
+   >
 2. Clone the repo:
 
    ```bash
    $ git clone https://github.com/infiniflow/ragflow.git
    ```
-
 3. Start up the server using the pre-built Docker images:
 
 > [!CAUTION]
 > All Docker images are built for x86 platforms. We don't currently offer Docker images for ARM64.
 > If you are on an ARM64 platform, follow [this guide](https://ragflow.io/docs/dev/build_docker_image) to build a Docker image compatible with your system.
 
-   > The command below downloads the `v0.21.0-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.21.0-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0` for the full edition `v0.21.0`.
+> The command below downloads the `v0.22.1` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.22.1`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server.
 
-   ```bash
+```bash
    $ cd ragflow/docker
-   # Use CPU for embedding and DeepDoc tasks:
+  
+   # git checkout v0.22.1
+   # Optional: use a stable tag (see releases: https://github.com/infiniflow/ragflow/releases)
+   # This steps ensures the **entrypoint.sh** file in the code matches the Docker image version.
+   
+   # Use CPU for DeepDoc tasks:
    $ docker compose -f docker-compose.yml up -d
 
-   # To use GPU to accelerate embedding and DeepDoc tasks:
+   # To use GPU to accelerate DeepDoc tasks:
-   # docker compose -f docker-compose-gpu.yml up -d
+   # sed -i '1i DEVICE=gpu' .env
-   ```
+   # docker compose -f docker-compose.yml up -d
+```
 
-   | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
+> Note: Prior to `v0.22.0`, we provided both images with embedding models and slim images without embedding models. Details as follows:
-   |-------------------|-----------------|-----------------------|--------------------------|
+
-   | v0.21.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
+| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
-   | v0.21.0-slim      | &approx;2       | ❌                   | Stable release            |
+| ----------------- | --------------- | --------------------- | ------------------------ |
-   | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
+| v0.21.1           | &approx;9       | ✔️                    | Stable release           |
-   | nightly-slim      | &approx;2       | ❌                   | _Unstable_ nightly build  |
+| v0.21.1-slim      | &approx;2       | ❌                    | Stable release           |
+
+> Starting with `v0.22.0`, we ship only the slim edition and no longer append the **-slim** suffix to the image tag.
 
 4. Check the server status after having the server up and running:
 
    ```bash
-   $ docker logs -f ragflow-server
+   $ docker logs -f docker-ragflow-cpu-1
    ```
 
    _The following output confirms a successful launch of the system:_
@@ -226,14 +234,17 @@ releases! 🌟
 
    > If you skip this confirmation step and directly log in to RAGFlow, your browser may prompt a `network anormal`
    > error because, at that moment, your RAGFlow may not be fully initialized.
-
+   >
 5. In your web browser, enter the IP address of your server and log in to RAGFlow.
+
    > With the default settings, you only need to enter `http://IP_OF_YOUR_MACHINE` (**sans** port number) as the default
    > HTTP serving port `80` can be omitted when using the default configurations.
+   >
 6. In [service_conf.yaml.template](./docker/service_conf.yaml.template), select the desired LLM factory in `user_default_llm` and update
    the `API_KEY` field with the corresponding API key.
 
    > See [llm_api_key_setup](https://ragflow.io/docs/dev/llm_api_key_setup) for more information.
+   >
 
    _The show is on!_
 
@@ -272,7 +283,6 @@ RAGFlow uses Elasticsearch by default for storing full text and vectors. To swit
 > `-v` will delete the docker container volumes, and the existing data will be cleared.
 
 2. Set `DOC_ENGINE` in **docker/.env** to `infinity`.
-
 3. Start the containers:
 
    ```bash
@@ -282,20 +292,10 @@ RAGFlow uses Elasticsearch by default for storing full text and vectors. To swit
 > [!WARNING]
 > Switching to Infinity on a Linux/arm64 machine is not yet officially supported.
 
-## 🔧 Build a Docker image without embedding models
+## 🔧 Build a Docker image
 
 This image is approximately 2 GB in size and relies on external LLM and embedding services.
 
-```bash
-git clone https://github.com/infiniflow/ragflow.git
-cd ragflow/
-docker build --platform linux/amd64 --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
-```
-
-## 🔧 Build a Docker image including embedding models
-
-This image is approximately 9 GB in size. As it includes embedding models, it relies on external LLM services only.
-
 ```bash
 git clone https://github.com/infiniflow/ragflow.git
 cd ragflow/
@@ -309,17 +309,15 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    ```bash
    pipx install uv pre-commit
    ```
-
 2. Clone the source code and install Python dependencies:
 
    ```bash
    git clone https://github.com/infiniflow/ragflow.git
    cd ragflow/
-   uv sync --python 3.10 --all-extras # install RAGFlow dependent python modules
+   uv sync --python 3.10 # install RAGFlow dependent python modules
    uv run download_deps.py
    pre-commit install
    ```
-
 3. Launch the dependent services (MinIO, Elasticsearch, Redis, and MySQL) using Docker Compose:
 
    ```bash
@@ -331,13 +329,11 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    ```
    127.0.0.1       es01 infinity mysql minio redis sandbox-executor-manager
    ```
-
 4. If you cannot access HuggingFace, set the `HF_ENDPOINT` environment variable to use a mirror site:
 
    ```bash
    export HF_ENDPOINT=https://hf-mirror.com
    ```
-
 5. If your operating system does not have jemalloc, please install it as follows:
 
    ```bash
@@ -350,7 +346,6 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    # macOS
    sudo brew install jemalloc
    ```
-
 6. Launch backend service:
 
    ```bash
@@ -358,14 +353,12 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    export PYTHONPATH=$(pwd)
    bash docker/launch_backend_service.sh
    ```
-
 7. Install frontend dependencies:
 
    ```bash
    cd web
    npm install
    ```
-
 8. Launch frontend service:
 
    ```bash
@@ -375,14 +368,12 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    _The following output confirms a successful launch of the system:_
 
    ![](https://github.com/user-attachments/assets/0daf462c-a24d-4496-a66f-92533534e187)
-
 9. Stop RAGFlow front-end and back-end service after development is complete:
 
    ```bash
    pkill -f "ragflow_server.py|task_executor.py"
    ```
 
-
 ## 📚 Documentation
 
 - [Quickstart](https://ragflow.io/docs/dev/)

README_id.md

@@ -22,7 +22,7 @@
         <img alt="Lencana Daring" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.22.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Rilis%20Terbaru" alt="Rilis Terbaru">
@@ -43,7 +43,13 @@
   <a href="https://demo.ragflow.io">Demo</a>
 </h4>
 
-#
+<div align="center" style="margin-top:20px;margin-bottom:20px;">
+<img src="https://raw.githubusercontent.com/infiniflow/ragflow-docs/refs/heads/image/image/ragflow-octoverse.png" width="1200"/>
+</div>
+
+<div align="center">
+<a href="https://trendshift.io/repositories/9064" target="_blank"><img src="https://trendshift.io/api/badge/repositories/9064" alt="infiniflow%2Fragflow | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</div>
 
 <details open>
 <summary><b>📕 Daftar Isi </b> </summary>
@@ -55,8 +61,7 @@
 - 🔎 [Arsitektur Sistem](#-arsitektur-sistem)
 - 🎬 [Mulai](#-mulai)
 - 🔧 [Konfigurasi](#-konfigurasi)
-- 🔧 [Membangun Image Docker tanpa Model Embedding](#-membangun-image-docker-tanpa-model-embedding)
+- 🔧 [Membangun Image Docker](#-membangun-docker-image)
-- 🔧 [Membangun Image Docker dengan Model Embedding](#-membangun-image-docker-dengan-model-embedding)
 - 🔨 [Meluncurkan aplikasi dari Sumber untuk Pengembangan](#-meluncurkan-aplikasi-dari-sumber-untuk-pengembangan)
 - 📚 [Dokumentasi](#-dokumentasi)
 - 📜 [Peta Jalan](#-peta-jalan)
@@ -80,13 +85,15 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
 
 ## 🔥 Pembaruan Terbaru
 
+- 2025-11-19 Mendukung Gemini 3 Pro.
+- 2025-11-12 Mendukung sinkronisasi data dari Confluence, S3, Notion, Discord, Google Drive.
+- 2025-10-23 Mendukung MinerU & Docling sebagai metode penguraian dokumen.
 - 2025-10-15 Dukungan untuk jalur data yang terorkestrasi.
 - 2025-08-08 Mendukung model seri GPT-5 terbaru dari OpenAI.
 - 2025-08-01 Mendukung alur kerja agen dan MCP.
 - 2025-05-23 Menambahkan komponen pelaksana kode Python/JS ke Agen.
 - 2025-05-05 Mendukung kueri lintas bahasa.
 - 2025-03-19 Mendukung penggunaan model multi-modal untuk memahami gambar di dalam file PDF atau DOCX.
-- 2025-02-28 dikombinasikan dengan pencarian Internet (TAVILY), mendukung penelitian mendalam untuk LLM apa pun.
 - 2024-12-18 Meningkatkan model Analisis Tata Letak Dokumen di DeepDoc.
 - 2024-08-22 Dukungan untuk teks ke pernyataan SQL melalui RAG.
 
@@ -129,7 +136,7 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
 ## 🔎 Arsitektur Sistem
 
 <div align="center" style="margin-top:20px;margin-bottom:20px;">
-<img src="https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485" width="1000"/>
+<img src="https://github.com/user-attachments/assets/31b0dd6f-ca4f-445a-9457-70cb44a381b2" width="1000"/>
 </div>
 
 ## 🎬 Mulai
@@ -168,41 +175,48 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
    > ```bash
    > vm.max_map_count=262144
    > ```
-
+   >
 2. Clone repositori:
 
    ```bash
    $ git clone https://github.com/infiniflow/ragflow.git
    ```
-
 3. Bangun image Docker pre-built dan jalankan server:
 
 > [!CAUTION]
 > Semua gambar Docker dibangun untuk platform x86. Saat ini, kami tidak menawarkan gambar Docker untuk ARM64.
 > Jika Anda menggunakan platform ARM64, [silakan gunakan panduan ini untuk membangun gambar Docker yang kompatibel dengan sistem Anda](https://ragflow.io/docs/dev/build_docker_image).
 
-> Perintah di bawah ini mengunduh edisi v0.21.0-slim dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.21.0-slim, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server. Misalnya, atur RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0 untuk edisi lengkap v0.21.0.
+> Perintah di bawah ini mengunduh edisi v0.22.1 dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.22.1, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server.
 
 ```bash
-$ cd ragflow/docker
+   $ cd ragflow/docker
-# Use CPU for embedding and DeepDoc tasks:
-$ docker compose -f docker-compose.yml up -d
    
-# To use GPU to accelerate embedding and DeepDoc tasks:
+   # git checkout v0.22.1
-# docker compose -f docker-compose-gpu.yml up -d
+   # Opsional: gunakan tag stabil (lihat releases: https://github.com/infiniflow/ragflow/releases)
+   # This steps ensures the **entrypoint.sh** file in the code matches the Docker image version.
+
+   # Use CPU for DeepDoc tasks:
+   $ docker compose -f docker-compose.yml up -d
+
+   # To use GPU to accelerate DeepDoc tasks:
+   # sed -i '1i DEVICE=gpu' .env
+   # docker compose -f docker-compose.yml up -d
 ```
 
+> Catatan: Sebelum `v0.22.0`, kami menyediakan image dengan model embedding dan image slim tanpa model embedding. Detailnya sebagai berikut:
+
 | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
 | ----------------- | --------------- | --------------------- | ------------------------ |
-| v0.21.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
+| v0.21.1           | &approx;9       | ✔️                    | Stable release           |
-| v0.21.0-slim      | &approx;2       | ❌                    | Stable release           |
+| v0.21.1-slim      | &approx;2       | ❌                    | Stable release           |
-| nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
+
-| nightly-slim      | &approx;2       | ❌                    | _Unstable_ nightly build |
+> Mulai dari `v0.22.0`, kami hanya menyediakan edisi slim dan tidak lagi menambahkan akhiran **-slim** pada tag image.
 
 1. Periksa status server setelah server aktif dan berjalan:
 
    ```bash
-   $ docker logs -f ragflow-server
+   $ docker logs -f docker-ragflow-cpu-1
    ```
 
    _Output berikut menandakan bahwa sistem berhasil diluncurkan:_
@@ -220,14 +234,17 @@ $ docker compose -f docker-compose.yml up -d
 
    > Jika Anda melewatkan langkah ini dan langsung login ke RAGFlow, browser Anda mungkin menampilkan error `network anormal`
    > karena RAGFlow mungkin belum sepenuhnya siap.
-
+   >
 2. Buka browser web Anda, masukkan alamat IP server Anda, dan login ke RAGFlow.
+
    > Dengan pengaturan default, Anda hanya perlu memasukkan `http://IP_DEVICE_ANDA` (**tanpa** nomor port) karena
    > port HTTP default `80` bisa dihilangkan saat menggunakan konfigurasi default.
+   >
 3. Dalam [service_conf.yaml.template](./docker/service_conf.yaml.template), pilih LLM factory yang diinginkan di `user_default_llm` dan perbarui
    bidang `API_KEY` dengan kunci API yang sesuai.
 
    > Lihat [llm_api_key_setup](https://ragflow.io/docs/dev/llm_api_key_setup) untuk informasi lebih lanjut.
+   >
 
    _Sistem telah siap digunakan!_
 
@@ -249,20 +266,10 @@ Pembaruan konfigurasi ini memerlukan reboot semua kontainer agar efektif:
 > $ docker compose -f docker-compose.yml up -d
 > ```
 
-## 🔧 Membangun Docker Image tanpa Model Embedding
+## 🔧 Membangun Docker Image
 
 Image ini berukuran sekitar 2 GB dan bergantung pada aplikasi LLM eksternal dan embedding.
 
-```bash
-git clone https://github.com/infiniflow/ragflow.git
-cd ragflow/
-docker build --platform linux/amd64 --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
-```
-
-## 🔧 Membangun Docker Image Termasuk Model Embedding
-
-Image ini berukuran sekitar 9 GB. Karena sudah termasuk model embedding, ia hanya bergantung pada aplikasi LLM eksternal.
-
 ```bash
 git clone https://github.com/infiniflow/ragflow.git
 cd ragflow/
@@ -276,17 +283,15 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    ```bash
    pipx install uv pre-commit
    ```
-
 2. Clone kode sumber dan instal dependensi Python:
 
    ```bash
    git clone https://github.com/infiniflow/ragflow.git
    cd ragflow/
-   uv sync --python 3.10 --all-extras # install RAGFlow dependent python modules
+   uv sync --python 3.10 # install RAGFlow dependent python modules
    uv run download_deps.py
    pre-commit install
    ```
-
 3. Jalankan aplikasi yang diperlukan (MinIO, Elasticsearch, Redis, dan MySQL) menggunakan Docker Compose:
 
    ```bash
@@ -298,13 +303,11 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    ```
    127.0.0.1       es01 infinity mysql minio redis sandbox-executor-manager
    ```
-
 4. Jika Anda tidak dapat mengakses HuggingFace, atur variabel lingkungan `HF_ENDPOINT` untuk menggunakan situs mirror:
 
    ```bash
    export HF_ENDPOINT=https://hf-mirror.com
    ```
-
 5. Jika sistem operasi Anda tidak memiliki jemalloc, instal sebagai berikut:
 
    ```bash
@@ -315,7 +318,6 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    # mac
    sudo brew install jemalloc
    ```
-
 6. Jalankan aplikasi backend:
 
    ```bash
@@ -323,14 +325,12 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    export PYTHONPATH=$(pwd)
    bash docker/launch_backend_service.sh
    ```
-
 7. Instal dependensi frontend:
 
    ```bash
    cd web
    npm install
    ```
-
 8. Jalankan aplikasi frontend:
 
    ```bash
@@ -340,15 +340,12 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    _Output berikut menandakan bahwa sistem berhasil diluncurkan:_
 
    ![](https://github.com/user-attachments/assets/0daf462c-a24d-4496-a66f-92533534e187)
-
-
 9. Hentikan layanan front-end dan back-end RAGFlow setelah pengembangan selesai:
 
    ```bash
    pkill -f "ragflow_server.py|task_executor.py"
    ```
 
-
 ## 📚 Dokumentasi
 
 - [Quickstart](https://ragflow.io/docs/dev/)

README_ja.md

@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.22.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@@ -43,7 +43,13 @@
   <a href="https://demo.ragflow.io">Demo</a>
 </h4>
 
-#
+<div align="center" style="margin-top:20px;margin-bottom:20px;">
+<img src="https://raw.githubusercontent.com/infiniflow/ragflow-docs/refs/heads/image/image/ragflow-octoverse.png" width="1200"/>
+</div>
+
+<div align="center">
+<a href="https://trendshift.io/repositories/9064" target="_blank"><img src="https://trendshift.io/api/badge/repositories/9064" alt="infiniflow%2Fragflow | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</div>
 
 ## 💡 RAGFlow とは？
 
@@ -60,13 +66,15 @@
 
 ## 🔥 最新情報
 
+- 2025-11-19 Gemini 3 Proをサポートしています
+- 2025-11-12 Confluence、S3、Notion、Discord、Google Drive からのデータ同期をサポートします。
+- 2025-10-23 ドキュメント解析方法として MinerU と Docling をサポートします。
 - 2025-10-15 オーケストレーションされたデータパイプラインのサポート。
 - 2025-08-08 OpenAI の最新 GPT-5 シリーズモデルをサポートします。
 - 2025-08-01 エージェントワークフローとMCPをサポート。
 - 2025-05-23 エージェントに Python/JS コードエグゼキュータコンポーネントを追加しました。
 - 2025-05-05 言語間クエリをサポートしました。
 - 2025-03-19 PDFまたはDOCXファイル内の画像を理解するために、多モーダルモデルを使用することをサポートします。
-- 2025-02-28 インターネット検索 (TAVILY) と組み合わせて、あらゆる LLM の詳細な調査をサポートします。
 - 2024-12-18 DeepDoc のドキュメント レイアウト分析モデルをアップグレードします。
 - 2024-08-22 RAG を介して SQL ステートメントへのテキストをサポートします。
 
@@ -109,7 +117,7 @@
 ## 🔎 システム構成
 
 <div align="center" style="margin-top:20px;margin-bottom:20px;">
-<img src="https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485" width="1000"/>
+<img src="https://github.com/user-attachments/assets/31b0dd6f-ca4f-445a-9457-70cb44a381b2" width="1000"/>
 </div>
 
 ## 🎬 初期設定
@@ -147,41 +155,48 @@
    > ```bash
    > vm.max_map_count=262144
    > ```
-
+   >
 2. リポジトリをクローンする:
 
    ```bash
    $ git clone https://github.com/infiniflow/ragflow.git
    ```
-
 3. ビルド済みの Docker イメージをビルドし、サーバーを起動する:
 
 > [!CAUTION]
 > 現在、公式に提供されているすべての Docker イメージは x86 アーキテクチャ向けにビルドされており、ARM64 用の Docker イメージは提供されていません。
 > ARM64 アーキテクチャのオペレーティングシステムを使用している場合は、[このドキュメント](https://ragflow.io/docs/dev/build_docker_image)を参照して Docker イメージを自分でビルドしてください。
 
-   > 以下のコマンドは、RAGFlow Docker イメージの v0.21.0-slim エディションをダウンロードします。異なる RAGFlow エディションの説明については、以下の表を参照してください。v0.21.0-slim とは異なるエディションをダウンロードするには、docker/.env ファイルの RAGFLOW_IMAGE 変数を適宜更新し、docker compose を使用してサーバーを起動してください。例えば、完全版 v0.21.0 をダウンロードするには、RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0 と設定します。
+> 以下のコマンドは、RAGFlow Docker イメージの v0.22.1 エディションをダウンロードします。異なる RAGFlow エディションの説明については、以下の表を参照してください。v0.22.1 とは異なるエディションをダウンロードするには、docker/.env ファイルの RAGFLOW_IMAGE 変数を適宜更新し、docker compose を使用してサーバーを起動してください。
 
-   ```bash
+```bash
    $ cd ragflow/docker
-   # Use CPU for embedding and DeepDoc tasks:
+
+   # git checkout v0.22.1
+   # 任意: 安定版タグを利用 (一覧: https://github.com/infiniflow/ragflow/releases)
+   # この手順は、コード内の entrypoint.sh ファイルが Docker イメージのバージョンと一致していることを確認します。
+
+   # Use CPU for DeepDoc tasks:
    $ docker compose -f docker-compose.yml up -d
 
-   # To use GPU to accelerate embedding and DeepDoc tasks:
+   # To use GPU to accelerate DeepDoc tasks:
-   # docker compose -f docker-compose-gpu.yml up -d
+   # sed -i '1i DEVICE=gpu' .env
-   ```
+   # docker compose -f docker-compose.yml up -d
+```
 
-   | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
+> 注意：`v0.22.0` より前のバージョンでは、embedding モデルを含むイメージと、embedding モデルを含まない slim イメージの両方を提供していました。詳細は以下の通りです：
-   | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.21.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.21.0-slim      | &approx;2       | ❌                    | Stable release           |
-   | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
-   | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
 
-1. サーバーを立ち上げた後、サーバーの状態を確認する:
+| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
+| ----------------- | --------------- | --------------------- | ------------------------ |
+| v0.21.1           | &approx;9       | ✔️                    | Stable release           |
+| v0.21.1-slim      | &approx;2       | ❌                    | Stable release           |
+
+> `v0.22.0` 以降、当プロジェクトでは slim エディションのみを提供し、イメージタグに **-slim** サフィックスを付けなくなりました。
+
+   1. サーバーを立ち上げた後、サーバーの状態を確認する:   
    
    ```bash
-   $ docker logs -f ragflow-server
+   $ docker logs -f docker-ragflow-cpu-1
    ```
 
    _以下の出力は、システムが正常に起動したことを確認するものです:_
@@ -197,12 +212,15 @@
    ```
 
    > もし確認ステップをスキップして直接 RAGFlow にログインした場合、その時点で RAGFlow が完全に初期化されていない可能性があるため、ブラウザーがネットワーク異常エラーを表示するかもしれません。
-
+   >
 2. ウェブブラウザで、プロンプトに従ってサーバーの IP アドレスを入力し、RAGFlow にログインします。
+
    > デフォルトの設定を使用する場合、デフォルトの HTTP サービングポート `80` は省略できるので、与えられたシナリオでは、`http://IP_OF_YOUR_MACHINE`（ポート番号は省略）だけを入力すればよい。
+   >
 3. [service_conf.yaml.template](./docker/service_conf.yaml.template) で、`user_default_llm` で希望の LLM ファクトリを選択し、`API_KEY` フィールドを対応する API キーで更新する。
 
    > 詳しくは [llm_api_key_setup](https://ragflow.io/docs/dev/llm_api_key_setup) を参照してください。
+   >
 
    _これで初期設定完了！ショーの開幕です！_
 
@@ -231,33 +249,27 @@
 RAGFlow はデフォルトで Elasticsearch を使用して全文とベクトルを保存します。［Infinity］に切り替え（https://github.com/infiniflow/infinity/)、次の手順に従います。
 
 1. 実行中のすべてのコンテナを停止するには：
+
    ```bash
    $ docker compose -f docker/docker-compose.yml down -v
    ```
+
    Note: `-v` は docker コンテナのボリュームを削除し、既存のデータをクリアします。
 2. **docker/.env** の「DOC \_ ENGINE」を「infinity」に設定します。
-
 3. 起動コンテナ：
+
    ```bash
    $ docker compose -f docker-compose.yml up -d
    ```
+
    > [!WARNING]
    > Linux/arm64 マシンでの Infinity への切り替えは正式にサポートされていません。
+   >
 
-## 🔧 ソースコードで Docker イメージを作成（埋め込みモデルなし）
+## 🔧 ソースコードで Docker イメージを作成
 
 この Docker イメージのサイズは約 1GB で、外部の大モデルと埋め込みサービスに依存しています。
 
-```bash
-git clone https://github.com/infiniflow/ragflow.git
-cd ragflow/
-docker build --platform linux/amd64 --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
-```
-
-## 🔧 ソースコードをコンパイルした Docker イメージ（埋め込みモデルを含む）
-
-この Docker のサイズは約 9GB で、埋め込みモデルを含むため、外部の大モデルサービスのみが必要です。
-
 ```bash
 git clone https://github.com/infiniflow/ragflow.git
 cd ragflow/
@@ -271,17 +283,15 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    ```bash
    pipx install uv pre-commit
    ```
-
 2. ソースコードをクローンし、Python の依存関係をインストールする:
 
    ```bash
    git clone https://github.com/infiniflow/ragflow.git
    cd ragflow/
-   uv sync --python 3.10 --all-extras # install RAGFlow dependent python modules
+   uv sync --python 3.10 # install RAGFlow dependent python modules
    uv run download_deps.py
    pre-commit install
    ```
-
 3. Docker Compose を使用して依存サービス（MinIO、Elasticsearch、Redis、MySQL）を起動する:
 
    ```bash
@@ -293,13 +303,11 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    ```
    127.0.0.1       es01 infinity mysql minio redis sandbox-executor-manager
    ```
-
 4. HuggingFace にアクセスできない場合は、`HF_ENDPOINT` 環境変数を設定してミラーサイトを使用してください:
 
    ```bash
    export HF_ENDPOINT=https://hf-mirror.com
    ```
-
 5. オペレーティングシステムにjemallocがない場合は、次のようにインストールします:
 
    ```bash
@@ -310,7 +318,6 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    # mac
    sudo brew install jemalloc
    ```
-
 6. バックエンドサービスを起動する:
 
    ```bash
@@ -318,14 +325,12 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    export PYTHONPATH=$(pwd)
    bash docker/launch_backend_service.sh
    ```
-
 7. フロントエンドの依存関係をインストールする:
 
    ```bash
    cd web
    npm install
    ```
-
 8. フロントエンドサービスを起動する:
 
    ```bash
@@ -335,14 +340,12 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    _以下の画面で、システムが正常に起動したことを示します:_
 
    ![](https://github.com/user-attachments/assets/0daf462c-a24d-4496-a66f-92533534e187)
-
 9. 開発が完了したら、RAGFlow のフロントエンド サービスとバックエンド サービスを停止します:
 
    ```bash
    pkill -f "ragflow_server.py|task_executor.py"
    ```
 
-
 ## 📚 ドキュメンテーション
 
 - [Quickstart](https://ragflow.io/docs/dev/)

README_ko.md

@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.22.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@@ -43,7 +43,14 @@
   <a href="https://demo.ragflow.io">Demo</a>
 </h4>
 
-#
+<div align="center" style="margin-top:20px;margin-bottom:20px;">
+<img src="https://raw.githubusercontent.com/infiniflow/ragflow-docs/refs/heads/image/image/ragflow-octoverse.png" width="1200"/>
+</div>
+
+<div align="center">
+<a href="https://trendshift.io/repositories/9064" target="_blank"><img src="https://trendshift.io/api/badge/repositories/9064" alt="infiniflow%2Fragflow | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</div>
+
 
 ## 💡 RAGFlow란?
 
@@ -60,13 +67,15 @@
 
 ## 🔥 업데이트
 
+- 2025-11-19 Gemini 3 Pro를 지원합니다.
+- 2025-11-12 Confluence, S3, Notion, Discord, Google Drive에서 데이터 동기화를 지원합니다.
+- 2025-10-23 문서 파싱 방법으로 MinerU 및 Docling을 지원합니다.
 - 2025-10-15 조정된 데이터 파이프라인 지원.
 - 2025-08-08 OpenAI의 최신 GPT-5 시리즈 모델을 지원합니다.
 - 2025-08-01 에이전트 워크플로우와 MCP를 지원합니다.
 - 2025-05-23 Agent에 Python/JS 코드 실행기 구성 요소를 추가합니다.
 - 2025-05-05 언어 간 쿼리를 지원합니다.
 - 2025-03-19 PDF 또는 DOCX 파일 내의 이미지를 이해하기 위해 다중 모드 모델을 사용하는 것을 지원합니다.
-- 2025-02-28 인터넷 검색(TAVILY)과 결합되어 모든 LLM에 대한 심층 연구를 지원합니다.
 - 2024-12-18 DeepDoc의 문서 레이아웃 분석 모델 업그레이드.
 - 2024-08-22 RAG를 통해 SQL 문에 텍스트를 지원합니다.
 
@@ -109,7 +118,7 @@
 ## 🔎 시스템 아키텍처
 
 <div align="center" style="margin-top:20px;margin-bottom:20px;">
-<img src="https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485" width="1000"/>
+<img src="https://github.com/user-attachments/assets/31b0dd6f-ca4f-445a-9457-70cb44a381b2" width="1000"/>
 </div>
 
 ## 🎬 시작하기
@@ -160,28 +169,36 @@
 > 모든 Docker 이미지는 x86 플랫폼을 위해 빌드되었습니다. 우리는 현재 ARM64 플랫폼을 위한 Docker 이미지를 제공하지 않습니다.
 > ARM64 플랫폼을 사용 중이라면, [시스템과 호환되는 Docker 이미지를 빌드하려면 이 가이드를 사용해 주세요](https://ragflow.io/docs/dev/build_docker_image).
 
-   > 아래 명령어는 RAGFlow Docker 이미지의 v0.21.0-slim 버전을 다운로드합니다. 다양한 RAGFlow 버전에 대한 설명은 다음 표를 참조하십시오. v0.21.0-slim과 다른 RAGFlow 버전을 다운로드하려면, docker/.env 파일에서 RAGFLOW_IMAGE 변수를 적절히 업데이트한 후 docker compose를 사용하여 서버를 시작하십시오. 예를 들어, 전체 버전인 v0.21.0을 다운로드하려면 RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0로 설정합니다.
+   > 아래 명령어는 RAGFlow Docker 이미지의 v0.22.1 버전을 다운로드합니다. 다양한 RAGFlow 버전에 대한 설명은 다음 표를 참조하십시오. v0.22.1과 다른 RAGFlow 버전을 다운로드하려면, docker/.env 파일에서 RAGFLOW_IMAGE 변수를 적절히 업데이트한 후 docker compose를 사용하여 서버를 시작하십시오.
 
    ```bash
    $ cd ragflow/docker
-   # Use CPU for embedding and DeepDoc tasks:
+   
+   # git checkout v0.22.1
+   # Optional: use a stable tag (see releases: https://github.com/infiniflow/ragflow/releases)
+   # 이 단계는 코드의 entrypoint.sh 파일이 Docker 이미지 버전과 일치하도록 보장합니다.
+
+   # Use CPU for DeepDoc tasks:
    $ docker compose -f docker-compose.yml up -d
 
-   # To use GPU to accelerate embedding and DeepDoc tasks:
+   # To use GPU to accelerate DeepDoc tasks:
-   # docker compose -f docker-compose-gpu.yml up -d
+   # sed -i '1i DEVICE=gpu' .env
-   ```
+   # docker compose -f docker-compose.yml up -d
+```
 
-   | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
+> 참고: `v0.22.0` 이전 버전에서는 embedding 모델이 포함된 이미지와 embedding 모델이 포함되지 않은 slim 이미지를 모두 제공했습니다. 자세한 내용은 다음과 같습니다:
-   | ----------------- | --------------- | --------------------- | ------------------------ |
+
-   | v0.21.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
+| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
-   | v0.21.0-slim      | &approx;2       | ❌                    | Stable release           |
+| ----------------- | --------------- | --------------------- | ------------------------ |
-   | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
+| v0.21.1           | &approx;9       | ✔️                    | Stable release           |
-   | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
+| v0.21.1-slim      | &approx;2       | ❌                    | Stable release           |
+
+> `v0.22.0`부터는 slim 에디션만 배포하며 이미지 태그에 **-slim** 접미사를 더 이상 붙이지 않습니다.
 
 1. 서버가 시작된 후 서버 상태를 확인하세요:
 
    ```bash
-   $ docker logs -f ragflow-server
+   $ docker logs -f docker-ragflow-cpu-1
    ```
 
    _다음 출력 결과로 시스템이 성공적으로 시작되었음을 확인합니다:_
@@ -243,20 +260,10 @@ RAGFlow 는 기본적으로 Elasticsearch 를 사용하여 전체 텍스트 및
    > [!WARNING]
    > Linux/arm64 시스템에서 Infinity로 전환하는 것은 공식적으로 지원되지 않습니다.
 
-## 🔧 소스 코드로 Docker 이미지를 컴파일합니다(임베딩 모델 포함하지 않음)
+## 🔧 소스 코드로 Docker 이미지를 컴파일합니다
 
 이 Docker 이미지의 크기는 약 1GB이며, 외부 대형 모델과 임베딩 서비스에 의존합니다.
 
-```bash
-git clone https://github.com/infiniflow/ragflow.git
-cd ragflow/
-docker build --platform linux/amd64 --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
-```
-
-## 🔧 소스 코드로 Docker 이미지를 컴파일합니다(임베딩 모델 포함)
-
-이 Docker의 크기는 약 9GB이며, 이미 임베딩 모델을 포함하고 있으므로 외부 대형 모델 서비스에만 의존하면 됩니다.
-
 ```bash
 git clone https://github.com/infiniflow/ragflow.git
 cd ragflow/
@@ -276,7 +283,7 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    ```bash
    git clone https://github.com/infiniflow/ragflow.git
    cd ragflow/
-   uv sync --python 3.10 --all-extras # install RAGFlow dependent python modules
+   uv sync --python 3.10 # install RAGFlow dependent python modules
    uv run download_deps.py
    pre-commit install
    ```

README_pt_br.md

@@ -22,7 +22,7 @@
         <img alt="Badge Estático" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.22.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Última%20Relese" alt="Última Versão">
@@ -43,7 +43,13 @@
   <a href="https://demo.ragflow.io">Demo</a>
 </h4>
 
-#
+<div align="center" style="margin-top:20px;margin-bottom:20px;">
+<img src="https://raw.githubusercontent.com/infiniflow/ragflow-docs/refs/heads/image/image/ragflow-octoverse.png" width="1200"/>
+</div>
+
+<div align="center">
+<a href="https://trendshift.io/repositories/9064" target="_blank"><img src="https://trendshift.io/api/badge/repositories/9064" alt="infiniflow%2Fragflow | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</div>
 
 <details open>
 <summary><b>📕 Índice</b></summary>
@@ -80,13 +86,15 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).
 
 ## 🔥 Últimas Atualizações
 
-- 10-15-2025 Suporte para pipelines de dados orquestrados.
+- 19-11-2025 Suporta Gemini 3 Pro.
+- 12-11-2025 Suporta a sincronização de dados do Confluence, S3, Notion, Discord e Google Drive.
+- 23-10-2025 Suporta MinerU e Docling como métodos de análise de documentos.
+- 15-10-2025 Suporte para pipelines de dados orquestrados.
 - 08-08-2025 Suporta a mais recente série GPT-5 da OpenAI.
 - 01-08-2025 Suporta fluxo de trabalho agente e MCP.
 - 23-05-2025 Adicione o componente executor de código Python/JS ao Agente.
 - 05-05-2025 Suporte a consultas entre idiomas.
 - 19-03-2025 Suporta o uso de um modelo multi-modal para entender imagens dentro de arquivos PDF ou DOCX.
-- 28-02-2025 combinado com a pesquisa na Internet (T AVI LY), suporta pesquisas profundas para qualquer LLM.
 - 18-12-2024 Atualiza o modelo de Análise de Layout de Documentos no DeepDoc.
 - 22-08-2024 Suporta conversão de texto para comandos SQL via RAG.
 
@@ -129,7 +137,7 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).
 ## 🔎 Arquitetura do Sistema
 
 <div align="center" style="margin-top:20px;margin-bottom:20px;">
-<img src="https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485" width="1000"/>
+<img src="https://github.com/user-attachments/assets/31b0dd6f-ca4f-445a-9457-70cb44a381b2" width="1000"/>
 </div>
 
 ## 🎬 Primeiros Passos
@@ -147,84 +155,92 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).
 
 ### 🚀 Iniciar o servidor
 
-1.  Certifique-se de que `vm.max_map_count` >= 262144:
+1. Certifique-se de que `vm.max_map_count` >= 262144:
 
-    > Para verificar o valor de `vm.max_map_count`:
+   > Para verificar o valor de `vm.max_map_count`:
-    >
+   >
-    > ```bash
+   > ```bash
-    > $ sysctl vm.max_map_count
+   > $ sysctl vm.max_map_count
-    > ```
+   > ```
-    >
+   >
-    > Se necessário, redefina `vm.max_map_count` para um valor de pelo menos 262144:
+   > Se necessário, redefina `vm.max_map_count` para um valor de pelo menos 262144:
-    >
+   >
-    > ```bash
+   > ```bash
-    > # Neste caso, defina para 262144:
+   > # Neste caso, defina para 262144:
-    > $ sudo sysctl -w vm.max_map_count=262144
+   > $ sudo sysctl -w vm.max_map_count=262144
-    > ```
+   > ```
-    >
+   >
-    > Essa mudança será resetada após a reinicialização do sistema. Para garantir que a alteração permaneça permanente, adicione ou atualize o valor de `vm.max_map_count` em **/etc/sysctl.conf**:
+   > Essa mudança será resetada após a reinicialização do sistema. Para garantir que a alteração permaneça permanente, adicione ou atualize o valor de `vm.max_map_count` em **/etc/sysctl.conf**:
-    >
+   >
-    > ```bash
+   > ```bash
-    > vm.max_map_count=262144
+   > vm.max_map_count=262144
-    > ```
+   > ```
+   >
+2. Clone o repositório:
 
-2.  Clone o repositório:
+   ```bash
-
+   $ git clone https://github.com/infiniflow/ragflow.git
-    ```bash
+   ```
-    $ git clone https://github.com/infiniflow/ragflow.git
+3. Inicie o servidor usando as imagens Docker pré-compiladas:
-    ```
-
-3.  Inicie o servidor usando as imagens Docker pré-compiladas:
 
 > [!CAUTION]
 > Todas as imagens Docker são construídas para plataformas x86. Atualmente, não oferecemos imagens Docker para ARM64.
 > Se você estiver usando uma plataforma ARM64, por favor, utilize [este guia](https://ragflow.io/docs/dev/build_docker_image) para construir uma imagem Docker compatível com o seu sistema.
 
-    > O comando abaixo baixa a edição `v0.21.0-slim` da imagem Docker do RAGFlow. Consulte a tabela a seguir para descrições de diferentes edições do RAGFlow. Para baixar uma edição do RAGFlow diferente da `v0.21.0-slim`, atualize a variável `RAGFLOW_IMAGE` conforme necessário no **docker/.env** antes de usar `docker compose` para iniciar o servidor. Por exemplo: defina `RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0` para a edição completa `v0.21.0`.
+    > O comando abaixo baixa a edição`v0.22.1` da imagem Docker do RAGFlow. Consulte a tabela a seguir para descrições de diferentes edições do RAGFlow. Para baixar uma edição do RAGFlow diferente da `v0.22.1`, atualize a variável `RAGFLOW_IMAGE` conforme necessário no **docker/.env** antes de usar `docker compose` para iniciar o servidor.
 
-    ```bash
+```bash
-    $ cd ragflow/docker
+   $ cd ragflow/docker
-    # Use CPU for embedding and DeepDoc tasks:
-    $ docker compose -f docker-compose.yml up -d
    
-    # To use GPU to accelerate embedding and DeepDoc tasks:
+   # git checkout v0.22.1
-    # docker compose -f docker-compose-gpu.yml up -d
+   # Opcional: use uma tag estável (veja releases: https://github.com/infiniflow/ragflow/releases)
-    ```
+   # Esta etapa garante que o arquivo entrypoint.sh no código corresponda à versão da imagem do Docker.
 
-    | Tag da imagem RAGFlow | Tamanho da imagem (GB) | Possui modelos de incorporação? | Estável?                 |
+   # Use CPU for DeepDoc tasks:
-    | --------------------- | ---------------------- | ------------------------------- | ------------------------ |
+   $ docker compose -f docker-compose.yml up -d
-    | v0.21.0               | ~9                     | :heavy_check_mark:              | Lançamento estável       |
-    | v0.21.0-slim          | ~2                     | ❌                              | Lançamento estável       |
-    | nightly               | ~9                     | :heavy_check_mark:              | _Instável_ build noturno |
-    | nightly-slim          | ~2                     | ❌                               | _Instável_ build noturno |
 
-4.  Verifique o status do servidor após tê-lo iniciado:
+   # To use GPU to accelerate DeepDoc tasks:
+   # sed -i '1i DEVICE=gpu' .env
+   # docker compose -f docker-compose.yml up -d
+```
 
-    ```bash
+> Nota: Antes da `v0.22.0`, fornecíamos imagens com modelos de embedding e imagens slim sem modelos de embedding. Detalhes a seguir:
-    $ docker logs -f ragflow-server
-    ```
 
-    _O seguinte resultado confirma o lançamento bem-sucedido do sistema:_
+| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
+| ----------------- | --------------- | --------------------- | ------------------------ |
+| v0.21.1           | &approx;9       | ✔️                    | Stable release           |
+| v0.21.1-slim      | &approx;2       | ❌                    | Stable release           |
 
-    ```bash
+> A partir da `v0.22.0`, distribuímos apenas a edição slim e não adicionamos mais o sufixo **-slim** às tags das imagens.
-         ____   ___    ______ ______ __
-        / __ \ /   |  / ____// ____// /____  _      __
-       / /_/ // /| | / / __ / /_   / // __ \| | /| / /
-      / _, _// ___ |/ /_/ // __/  / // /_/ /| |/ |/ /
-     /_/ |_|/_/  |_|\____//_/    /_/ \____/ |__/|__/
 
-     * Rodando em todos os endereços (0.0.0.0)
+4. Verifique o status do servidor após tê-lo iniciado:
-    ```
 
-    > Se você pular essa etapa de confirmação e acessar diretamente o RAGFlow, seu navegador pode exibir um erro `network anormal`, pois, nesse momento, seu RAGFlow pode não estar totalmente inicializado.
+   ```bash
+   $ docker logs -f docker-ragflow-cpu-1
+   ```
 
-5.  No seu navegador, insira o endereço IP do seu servidor e faça login no RAGFlow.
+   _O seguinte resultado confirma o lançamento bem-sucedido do sistema:_
 
-    > Com as configurações padrão, você só precisa digitar `http://IP_DO_SEU_MÁQUINA` (**sem** o número da porta), pois a porta HTTP padrão `80` pode ser omitida ao usar as configurações padrão.
+   ```bash
+        ____   ___    ______ ______ __
+       / __ \ /   |  / ____// ____// /____  _      __
+      / /_/ // /| | / / __ / /_   / // __ \| | /| / /
+     / _, _// ___ |/ /_/ // __/  / // /_/ /| |/ |/ /
+    /_/ |_|/_/  |_|\____//_/    /_/ \____/ |__/|__/
 
-6.  Em [service_conf.yaml.template](./docker/service_conf.yaml.template), selecione a fábrica LLM desejada em `user_default_llm` e atualize o campo `API_KEY` com a chave de API correspondente.
+    * Rodando em todos os endereços (0.0.0.0)
+   ```
 
-    > Consulte [llm_api_key_setup](https://ragflow.io/docs/dev/llm_api_key_setup) para mais informações.
+   > Se você pular essa etapa de confirmação e acessar diretamente o RAGFlow, seu navegador pode exibir um erro `network anormal`, pois, nesse momento, seu RAGFlow pode não estar totalmente inicializado.
+   >
+5. No seu navegador, insira o endereço IP do seu servidor e faça login no RAGFlow.
+
+   > Com as configurações padrão, você só precisa digitar `http://IP_DO_SEU_MÁQUINA` (**sem** o número da porta), pois a porta HTTP padrão `80` pode ser omitida ao usar as configurações padrão.
+   >
+6. Em [service_conf.yaml.template](./docker/service_conf.yaml.template), selecione a fábrica LLM desejada em `user_default_llm` e atualize o campo `API_KEY` com a chave de API correspondente.
+
+   > Consulte [llm_api_key_setup](https://ragflow.io/docs/dev/llm_api_key_setup) para mais informações.
+   >
 
 _O show está no ar!_
 
@@ -255,9 +271,9 @@ O RAGFlow usa o Elasticsearch por padrão para armazenar texto completo e vetore
    ```bash
    $ docker compose -f docker/docker-compose.yml down -v
    ```
+
    Note: `-v` irá deletar os volumes do contêiner, e os dados existentes serão apagados.
 2. Defina `DOC_ENGINE` no **docker/.env** para `infinity`.
-
 3. Inicie os contêineres:
 
    ```bash
@@ -265,22 +281,12 @@ O RAGFlow usa o Elasticsearch por padrão para armazenar texto completo e vetore
    ```
 
 > [!ATENÇÃO]
-> A mudança para o Infinity em uma máquina Linux/arm64 ainda não é oficialmente suportada.
+ > A mudança para o Infinity em uma máquina Linux/arm64 ainda não é oficialmente suportada.
 
-## 🔧 Criar uma imagem Docker sem modelos de incorporação
+## 🔧 Criar uma imagem Docker
 
 Esta imagem tem cerca de 2 GB de tamanho e depende de serviços externos de LLM e incorporação.
 
-```bash
-git clone https://github.com/infiniflow/ragflow.git
-cd ragflow/
-docker build --platform linux/amd64 --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
-```
-
-## 🔧 Criar uma imagem Docker incluindo modelos de incorporação
-
-Esta imagem tem cerca de 9 GB de tamanho. Como inclui modelos de incorporação, depende apenas de serviços externos de LLM.
-
 ```bash
 git clone https://github.com/infiniflow/ragflow.git
 cd ragflow/
@@ -294,17 +300,15 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    ```bash
    pipx install uv pre-commit
    ```
-
 2. Clone o código-fonte e instale as dependências Python:
 
    ```bash
    git clone https://github.com/infiniflow/ragflow.git
    cd ragflow/
-   uv sync --python 3.10 --all-extras # instala os módulos Python dependentes do RAGFlow
+   uv sync --python 3.10 # instala os módulos Python dependentes do RAGFlow
    uv run download_deps.py
    pre-commit install
    ```
-
 3. Inicie os serviços dependentes (MinIO, Elasticsearch, Redis e MySQL) usando Docker Compose:
 
    ```bash
@@ -316,24 +320,21 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    ```
    127.0.0.1       es01 infinity mysql minio redis sandbox-executor-manager
    ```
-
 4. Se não conseguir acessar o HuggingFace, defina a variável de ambiente `HF_ENDPOINT` para usar um site espelho:
 
    ```bash
    export HF_ENDPOINT=https://hf-mirror.com
    ```
-
 5. Se o seu sistema operacional não tiver jemalloc, instale-o da seguinte maneira:
 
-    ```bash
+   ```bash
-    # ubuntu
+   # ubuntu
-    sudo apt-get install libjemalloc-dev
+   sudo apt-get install libjemalloc-dev
-    # centos
+   # centos
-    sudo yum instalar jemalloc
+   sudo yum instalar jemalloc
-    # mac
+   # mac
-    sudo brew install jemalloc
+   sudo brew install jemalloc
-    ```
+   ```
-
 6. Lance o serviço de back-end:
 
    ```bash
@@ -341,14 +342,12 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    export PYTHONPATH=$(pwd)
    bash docker/launch_backend_service.sh
    ```
-
 7. Instale as dependências do front-end:
 
    ```bash
    cd web
    npm install
    ```
-
 8. Lance o serviço de front-end:
 
    ```bash
@@ -358,13 +357,11 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    _O seguinte resultado confirma o lançamento bem-sucedido do sistema:_
 
    ![](https://github.com/user-attachments/assets/0daf462c-a24d-4496-a66f-92533534e187)
-
 9. Pare os serviços de front-end e back-end do RAGFlow após a conclusão do desenvolvimento:
 
-    ```bash
+   ```bash
-    pkill -f "ragflow_server.py|task_executor.py"
+   pkill -f "ragflow_server.py|task_executor.py"
-    ```
+   ```
-
 
 ## 📚 Documentação
 

README_tzh.md

@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.22.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@@ -43,7 +43,9 @@
   <a href="https://demo.ragflow.io">Demo</a>
 </h4>
 
-#
+<div align="center" style="margin-top:20px;margin-bottom:20px;">
+<img src="https://raw.githubusercontent.com/infiniflow/ragflow-docs/refs/heads/image/image/ragflow-octoverse.png" width="1200"/>
+</div>
 
 <div align="center">
 <a href="https://trendshift.io/repositories/9064" target="_blank"><img src="https://trendshift.io/api/badge/repositories/9064" alt="infiniflow%2Fragflow | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
@@ -83,13 +85,15 @@
 
 ## 🔥 近期更新
 
+- 2025-11-19 支援 Gemini 3 Pro.
+- 2025-11-12 支援從 Confluence、S3、Notion、Discord、Google Drive 進行資料同步。
+- 2025-10-23 支援 MinerU 和 Docling 作為文件解析方法。
 - 2025-10-15 支援可編排的資料管道。
 - 2025-08-08 支援 OpenAI 最新的 GPT-5 系列模型。
 - 2025-08-01 支援 agentic workflow 和 MCP
 - 2025-05-23 為 Agent 新增 Python/JS 程式碼執行器元件。
 - 2025-05-05 支援跨語言查詢。
 - 2025-03-19 PDF和DOCX中的圖支持用多模態大模型去解析得到描述.
-- 2025-02-28 結合網路搜尋（Tavily），對於任意大模型實現類似 Deep Research 的推理功能.
 - 2024-12-18 升級了 DeepDoc 的文檔佈局分析模型。
 - 2024-08-22 支援用 RAG 技術實現從自然語言到 SQL 語句的轉換。
 
@@ -132,7 +136,7 @@
 ## 🔎 系統架構
 
 <div align="center" style="margin-top:20px;margin-bottom:20px;">
-<img src="https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485" width="1000"/>
+<img src="https://github.com/user-attachments/assets/31b0dd6f-ca4f-445a-9457-70cb44a381b2" width="1000"/>
 </div>
 
 ## 🎬 快速開始
@@ -170,47 +174,54 @@
    > ```bash
    > vm.max_map_count=262144
    > ```
-
+   >
 2. 克隆倉庫：
 
    ```bash
    $ git clone https://github.com/infiniflow/ragflow.git
    ```
-
 3. 進入 **docker** 資料夾，利用事先編譯好的 Docker 映像啟動伺服器：
 
 > [!CAUTION]
 > 所有 Docker 映像檔都是為 x86 平台建置的。目前，我們不提供 ARM64 平台的 Docker 映像檔。
 > 如果您使用的是 ARM64 平台，請使用 [這份指南](https://ragflow.io/docs/dev/build_docker_image) 來建置適合您系統的 Docker 映像檔。
 
-   > 執行以下指令會自動下載 RAGFlow slim Docker 映像 `v0.21.0-slim`。請參考下表查看不同 Docker 發行版的說明。如需下載不同於 `v0.21.0-slim` 的 Docker 映像，請在執行 `docker compose` 啟動服務之前先更新 **docker/.env** 檔案內的 `RAGFLOW_IMAGE` 變數。例如，你可以透過設定 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0` 來下載 RAGFlow 鏡像的 `v0.21.0` 完整發行版。
+> 執行以下指令會自動下載 RAGFlow Docker 映像 `v0.22.1`。請參考下表查看不同 Docker 發行版的說明。如需下載不同於 `v0.22.1` 的 Docker 映像，請在執行 `docker compose` 啟動服務之前先更新 **docker/.env** 檔案內的 `RAGFLOW_IMAGE` 變數。
 
-   ```bash
+```bash
    $ cd ragflow/docker
-   # Use CPU for embedding and DeepDoc tasks:
+   
+   # git checkout v0.22.1
+   # 可選：使用穩定版標籤（查看發佈：https://github.com/infiniflow/ragflow/releases）
+   # 此步驟確保程式碼中的 entrypoint.sh 檔案與 Docker 映像版本一致。
+
+   # Use CPU for DeepDoc tasks:
    $ docker compose -f docker-compose.yml up -d
 
-   # To use GPU to accelerate embedding and DeepDoc tasks:
+   # To use GPU to accelerate DeepDoc tasks:
-   # docker compose -f docker-compose-gpu.yml up -d
+   # sed -i '1i DEVICE=gpu' .env
-   ```
+   # docker compose -f docker-compose.yml up -d
+```
 
-   | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
+> 注意：在 `v0.22.0` 之前的版本，我們會同時提供包含 embedding 模型的映像和不含 embedding 模型的 slim 映像。具體如下：
-   | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.21.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.21.0-slim      | &approx;2       | ❌                    | Stable release           |
-   | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
-   | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
 
-   > [!TIP]
+| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
-   > 如果你遇到 Docker 映像檔拉不下來的問題，可以在 **docker/.env** 檔案內根據變數 `RAGFLOW_IMAGE` 的註解提示選擇華為雲或阿里雲的對應映像。
+| ----------------- | --------------- | --------------------- | ------------------------ |
-   >
+| v0.21.1           | &approx;9       | ✔️                    | Stable release           |
-   > - 華為雲鏡像名：`swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow`
+| v0.21.1-slim      | &approx;2       | ❌                    | Stable release           |
-   > - 阿里雲鏡像名：`registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow`
+
+> 從 `v0.22.0` 開始，我們只發佈 slim 版本，並且不再在映像標籤後附加 **-slim** 後綴。
+
+> [!TIP]
+> 如果你遇到 Docker 映像檔拉不下來的問題，可以在 **docker/.env** 檔案內根據變數 `RAGFLOW_IMAGE` 的註解提示選擇華為雲或阿里雲的對應映像。
+>
+> - 華為雲鏡像名：`swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow`
+> - 阿里雲鏡像名：`registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow`
 
 4. 伺服器啟動成功後再次確認伺服器狀態：
 
    ```bash
-   $ docker logs -f ragflow-server
+   $ docker logs -f docker-ragflow-cpu-1
    ```
 
    _出現以下介面提示說明伺服器啟動成功：_
@@ -226,12 +237,15 @@
    ```
 
    > 如果您跳過這一步驟系統確認步驟就登入 RAGFlow，你的瀏覽器有可能會提示 `network anormal` 或 `網路異常`，因為 RAGFlow 可能並未完全啟動成功。
-
+   >
 5. 在你的瀏覽器中輸入你的伺服器對應的 IP 位址並登入 RAGFlow。
+
    > 上面這個範例中，您只需輸入 http://IP_OF_YOUR_MACHINE 即可：未改動過設定則無需輸入連接埠（預設的 HTTP 服務連接埠 80）。
+   >
 6. 在 [service_conf.yaml.template](./docker/service_conf.yaml.template) 檔案的 `user_default_llm` 欄位設定 LLM factory，並在 `API_KEY` 欄填入和你選擇的大模型相對應的 API key。
 
    > 詳見 [llm_api_key_setup](https://ragflow.io/docs/dev/llm_api_key_setup)。
+   >
 
    _好戲開始，接著奏樂接著舞！ _
 
@@ -249,7 +263,7 @@
 
 > [./docker/README](./docker/README.md) 解釋了 [service_conf.yaml.template](./docker/service_conf.yaml.template) 用到的環境變數設定和服務配置。
 
-如需更新預設的 HTTP 服務連接埠(80), 可以在[docker-compose.yml](./docker/docker-compose.yml) 檔案中將配置`80:80` 改為`<YOUR_SERVING_PORT>:80` 。
+如需更新預設的 HTTP 服務連接埠(80), 可以在[docker-compose.yml](./docker/docker-compose.yml) 檔案中將配置 `80:80` 改為 `<YOUR_SERVING_PORT>:80` 。
 
 > 所有系統配置都需要透過系統重新啟動生效：
 >
@@ -266,10 +280,9 @@ RAGFlow 預設使用 Elasticsearch 儲存文字和向量資料. 如果要切換
    ```bash
    $ docker compose -f docker/docker-compose.yml down -v
    ```
+
    Note: `-v` 將會刪除 docker 容器的 volumes，已有的資料會被清空。
-
 2. 設定 **docker/.env** 目錄中的 `DOC_ENGINE` 為 `infinity`.
-
 3. 啟動容器:
 
    ```bash
@@ -279,24 +292,14 @@ RAGFlow 預設使用 Elasticsearch 儲存文字和向量資料. 如果要切換
 > [!WARNING]
 > Infinity 目前官方並未正式支援在 Linux/arm64 架構下的機器上運行.
 
-## 🔧 原始碼編譯 Docker 映像（不含 embedding 模型）
+## 🔧 原始碼編譯 Docker 映像
 
 本 Docker 映像大小約 2 GB 左右並且依賴外部的大模型和 embedding 服務。
 
 ```bash
 git clone https://github.com/infiniflow/ragflow.git
 cd ragflow/
-docker build --platform linux/amd64 --build-arg LIGHTEN=1 --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
+docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly .
-```
-
-## 🔧 原始碼編譯 Docker 映像（包含 embedding 模型）
-
-本 Docker 大小約 9 GB 左右。由於已包含 embedding 模型，所以只需依賴外部的大模型服務即可。
-
-```bash
-git clone https://github.com/infiniflow/ragflow.git
-cd ragflow/
-docker build --platform linux/amd64 --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly .
 ```
 
 ## 🔨 以原始碼啟動服務
@@ -307,17 +310,15 @@ docker build --platform linux/amd64 --build-arg NEED_MIRROR=1 -f Dockerfile -t i
    pipx install uv pre-commit
    export UV_INDEX=https://mirrors.aliyun.com/pypi/simple
    ```
-
 2. 下載原始碼並安裝 Python 依賴：
 
    ```bash
    git clone https://github.com/infiniflow/ragflow.git
    cd ragflow/
-   uv sync --python 3.10 --all-extras # install RAGFlow dependent python modules
+   uv sync --python 3.10 # install RAGFlow dependent python modules
    uv run download_deps.py
    pre-commit install
    ```
-
 3. 透過 Docker Compose 啟動依賴的服務（MinIO, Elasticsearch, Redis, and MySQL）：
 
    ```bash
@@ -329,13 +330,11 @@ docker build --platform linux/amd64 --build-arg NEED_MIRROR=1 -f Dockerfile -t i
    ```
    127.0.0.1       es01 infinity mysql minio redis sandbox-executor-manager
    ```
-
 4. 如果無法存取 HuggingFace，可以把環境變數 `HF_ENDPOINT` 設為對應的鏡像網站：
 
    ```bash
    export HF_ENDPOINT=https://hf-mirror.com
    ```
-
 5. 如果你的操作系统没有 jemalloc，请按照如下方式安装：
 
    ```bash
@@ -346,7 +345,6 @@ docker build --platform linux/amd64 --build-arg NEED_MIRROR=1 -f Dockerfile -t i
    # mac
    sudo brew install jemalloc
    ```
-
 6. 啟動後端服務：
 
    ```bash
@@ -354,14 +352,12 @@ docker build --platform linux/amd64 --build-arg NEED_MIRROR=1 -f Dockerfile -t i
    export PYTHONPATH=$(pwd)
    bash docker/launch_backend_service.sh
    ```
-
 7. 安裝前端依賴：
 
    ```bash
    cd web
    npm install
    ```
-
 8. 啟動前端服務：
 
    ```bash
@@ -371,15 +367,16 @@ docker build --platform linux/amd64 --build-arg NEED_MIRROR=1 -f Dockerfile -t i
    以下界面說明系統已成功啟動：_
 
    ![](https://github.com/user-attachments/assets/0daf462c-a24d-4496-a66f-92533534e187)
+
    ```
 
+   ```
 9. 開發完成後停止 RAGFlow 前端和後端服務：
 
    ```bash
    pkill -f "ragflow_server.py|task_executor.py"
    ```
 
-
 ## 📚 技術文檔
 
 - [Quickstart](https://ragflow.io/docs/dev/)

README_zh.md

@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.22.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@@ -43,7 +43,9 @@
   <a href="https://demo.ragflow.io">Demo</a>
 </h4>
 
-#
+<div align="center" style="margin-top:20px;margin-bottom:20px;">
+<img src="https://raw.githubusercontent.com/infiniflow/ragflow-docs/refs/heads/image/image/ragflow-octoverse.png" width="1200"/>
+</div>
 
 <div align="center">
 <a href="https://trendshift.io/repositories/9064" target="_blank"><img src="https://trendshift.io/api/badge/repositories/9064" alt="infiniflow%2Fragflow | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
@@ -83,13 +85,15 @@
 
 ## 🔥 近期更新
 
+- 2025-11-19 支持 Gemini 3 Pro.
+- 2025-11-12 支持从 Confluence、S3、Notion、Discord、Google Drive 进行数据同步。
+- 2025-10-23 支持 MinerU 和 Docling 作为文档解析方法。
 - 2025-10-15 支持可编排的数据管道。
 - 2025-08-08 支持 OpenAI 最新的 GPT-5 系列模型。
 - 2025-08-01 支持 agentic workflow 和 MCP。
 - 2025-05-23 Agent 新增 Python/JS 代码执行器组件。
 - 2025-05-05 支持跨语言查询。
 - 2025-03-19 PDF 和 DOCX 中的图支持用多模态大模型去解析得到描述.
-- 2025-02-28 结合互联网搜索（Tavily），对于任意大模型实现类似 Deep Research 的推理功能.
 - 2024-12-18 升级了 DeepDoc 的文档布局分析模型。
 - 2024-08-22 支持用 RAG 技术实现从自然语言到 SQL 语句的转换。
 
@@ -132,7 +136,7 @@
 ## 🔎 系统架构
 
 <div align="center" style="margin-top:20px;margin-bottom:20px;">
-<img src="https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485" width="1000"/>
+<img src="https://github.com/user-attachments/assets/31b0dd6f-ca4f-445a-9457-70cb44a381b2" width="1000"/>
 </div>
 
 ## 🎬 快速开始
@@ -183,23 +187,31 @@
 > 请注意，目前官方提供的所有 Docker 镜像均基于 x86 架构构建，并不提供基于 ARM64 的 Docker 镜像。
 > 如果你的操作系统是 ARM64 架构，请参考[这篇文档](https://ragflow.io/docs/dev/build_docker_image)自行构建 Docker 镜像。
 
-   > 运行以下命令会自动下载 RAGFlow slim Docker 镜像 `v0.21.0-slim`。请参考下表查看不同 Docker 发行版的描述。如需下载不同于 `v0.21.0-slim` 的 Docker 镜像，请在运行 `docker compose` 启动服务之前先更新 **docker/.env** 文件内的 `RAGFLOW_IMAGE` 变量。比如，你可以通过设置 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0` 来下载 RAGFlow 镜像的 `v0.21.0` 完整发行版。
+   > 运行以下命令会自动下载 RAGFlow Docker 镜像 `v0.22.1`。请参考下表查看不同 Docker 发行版的描述。如需下载不同于 `v0.22.1` 的 Docker 镜像，请在运行 `docker compose` 启动服务之前先更新 **docker/.env** 文件内的 `RAGFLOW_IMAGE` 变量。
 
    ```bash
    $ cd ragflow/docker
-   # Use CPU for embedding and DeepDoc tasks:
+   
+   # git checkout v0.22.1
+   # 可选：使用稳定版本标签（查看发布：https://github.com/infiniflow/ragflow/releases）
+   # 这一步确保代码中的 entrypoint.sh 文件与 Docker 镜像的版本保持一致。
+
+   # Use CPU for DeepDoc tasks:
    $ docker compose -f docker-compose.yml up -d
 
-   # To use GPU to accelerate embedding and DeepDoc tasks:
+   # To use GPU to accelerate DeepDoc tasks:
-   # docker compose -f docker-compose-gpu.yml up -d
+   # sed -i '1i DEVICE=gpu' .env
+   # docker compose -f docker-compose.yml up -d
    ```
    
+   > 注意：在 `v0.22.0` 之前的版本，我们会同时提供包含 embedding 模型的镜像和不含 embedding 模型的 slim 镜像。具体如下：
+
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
    | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.21.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.21.1           | &approx;9       | ✔️                    | Stable release           |
-   | v0.21.0-slim      | &approx;2       | ❌                    | Stable release           |
+   | v0.21.1-slim      | &approx;2       | ❌                    | Stable release           |
-   | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
+
-   | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
+   > 从 `v0.22.0` 开始，我们只发布 slim 版本，并且不再在镜像标签后附加 **-slim** 后缀。
 
    > [!TIP]
    > 如果你遇到 Docker 镜像拉不下来的问题，可以在 **docker/.env** 文件内根据变量 `RAGFLOW_IMAGE` 的注释提示选择华为云或者阿里云的相应镜像。
@@ -210,7 +222,7 @@
 4. 服务器启动成功后再次确认服务器状态：
 
    ```bash
-   $ docker logs -f ragflow-server
+   $ docker logs -f docker-ragflow-cpu-1
    ```
 
    _出现以下界面提示说明服务器启动成功：_
@@ -279,24 +291,14 @@ RAGFlow 默认使用 Elasticsearch 存储文本和向量数据. 如果要切换
 > [!WARNING]
 > Infinity 目前官方并未正式支持在 Linux/arm64 架构下的机器上运行.
 
-## 🔧 源码编译 Docker 镜像（不含 embedding 模型）
+## 🔧 源码编译 Docker 镜像
 
 本 Docker 镜像大小约 2 GB 左右并且依赖外部的大模型和 embedding 服务。
 
 ```bash
 git clone https://github.com/infiniflow/ragflow.git
 cd ragflow/
-docker build --platform linux/amd64 --build-arg LIGHTEN=1 --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
+docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly .
-```
-
-## 🔧 源码编译 Docker 镜像（包含 embedding 模型）
-
-本 Docker 大小约 9 GB 左右。由于已包含 embedding 模型，所以只需依赖外部的大模型服务即可。
-
-```bash
-git clone https://github.com/infiniflow/ragflow.git
-cd ragflow/
-docker build --platform linux/amd64 --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly .
 ```
 
 ## 🔨 以源代码启动服务
@@ -313,7 +315,7 @@ docker build --platform linux/amd64 --build-arg NEED_MIRROR=1 -f Dockerfile -t i
    ```bash
    git clone https://github.com/infiniflow/ragflow.git
    cd ragflow/
-   uv sync --python 3.10 --all-extras # install RAGFlow dependent python modules
+   uv sync --python 3.10 # install RAGFlow dependent python modules
    uv run download_deps.py
    pre-commit install
    ```

admin/client/README.md

@@ -4,7 +4,7 @@
 
 Admin Service is a dedicated management component designed to monitor, maintain, and administrate the RAGFlow system. It provides comprehensive tools for ensuring system stability, performing operational tasks, and managing users and permissions efficiently.
 
-The service offers real-time monitoring of critical components, including the RAGFlow server, Task Executor processes, and dependent services such as MySQL, Elasticsearch, Redis, and MinIO. It automatically checks their health status, resource usage, and uptime, and performs restarts in case of failures to minimize downtime.
+The service offers real-time monitoring of critical components, including the RAGFlow server, Task Executor processes, and dependent services such as MySQL, Infinity, Elasticsearch, Redis, and MinIO. It automatically checks their health status, resource usage, and uptime, and performs restarts in case of failures to minimize downtime.
 
 For user and system management, it supports listing, creating, modifying, and deleting users and their associated resources like knowledge bases and Agents.
 
@@ -48,13 +48,20 @@ It consists of a server-side Service and a command-line client (CLI), both imple
 1.  Ensure the Admin Service is running.
 2.  Install ragflow-cli.
     ```bash
-    pip install ragflow-cli
+    pip install ragflow-cli==0.22.1
     ```
 3.  Launch the CLI client:
     ```bash
-    ragflow-cli -h 0.0.0.0 -p 9381
+    ragflow-cli -h 127.0.0.1 -p 9381
     ```
-	Enter superuser's password to login. Default password is `admin`.
+    You will be prompted to enter the superuser's password to log in.
+    The default password is admin.
+
+    **Parameters:**
+    
+    - -h: RAGFlow admin server host address
+    
+    - -p: RAGFlow admin server port
 
 
 

admin/client/admin_client.py

@@ -21,9 +21,9 @@ from cmd import Cmd
 from Cryptodome.PublicKey import RSA
 from Cryptodome.Cipher import PKCS1_v1_5 as Cipher_pkcs1_v1_5
 from typing import Dict, List, Any
-from lark import Lark, Transformer, Tree, Token
+from lark import Lark, Transformer, Tree
 import requests
-from requests.auth import HTTPBasicAuth
+import getpass
 
 GRAMMAR = r"""
 start: command
@@ -43,6 +43,16 @@ sql_command: list_services
            | activate_user
            | list_datasets
            | list_agents
+           | create_role
+           | drop_role
+           | alter_role
+           | list_roles
+           | show_role
+           | grant_permission
+           | revoke_permission
+           | alter_user_role
+           | show_user_permission
+           | show_version
 
 // meta command definition
 meta_command: "\\" meta_command_name [meta_args]
@@ -71,6 +81,20 @@ PASSWORD: "PASSWORD"i
 DATASETS: "DATASETS"i
 OF: "OF"i
 AGENTS: "AGENTS"i
+ROLE: "ROLE"i
+ROLES: "ROLES"i
+DESCRIPTION: "DESCRIPTION"i
+GRANT: "GRANT"i
+REVOKE: "REVOKE"i
+ALL: "ALL"i
+PERMISSION: "PERMISSION"i
+TO: "TO"i
+FROM: "FROM"i
+FOR: "FOR"i
+RESOURCES: "RESOURCES"i
+ON: "ON"i
+SET: "SET"i
+VERSION: "VERSION"i
 
 list_services: LIST SERVICES ";"
 show_service: SHOW SERVICE NUMBER ";"
@@ -88,6 +112,21 @@ activate_user: ALTER USER ACTIVE quoted_string status ";"
 list_datasets: LIST DATASETS OF quoted_string ";"
 list_agents: LIST AGENTS OF quoted_string ";"
 
+create_role: CREATE ROLE identifier [DESCRIPTION quoted_string] ";"
+drop_role: DROP ROLE identifier ";"
+alter_role: ALTER ROLE identifier SET DESCRIPTION quoted_string ";"
+list_roles: LIST ROLES ";"
+show_role: SHOW ROLE identifier ";"
+
+grant_permission: GRANT action_list ON identifier TO ROLE identifier ";"
+revoke_permission: REVOKE action_list ON identifier FROM ROLE identifier ";"
+alter_user_role: ALTER USER quoted_string SET ROLE identifier ";"
+show_user_permission: SHOW USER PERMISSION quoted_string ";"
+
+show_version: SHOW VERSION ";"
+
+action_list: identifier ("," identifier)*
+
 identifier: WORD
 quoted_string: QUOTED_STRING
 status: WORD
@@ -134,34 +173,89 @@ class AdminTransformer(Transformer):
 
     def show_user(self, items):
         user_name = items[2]
-        return {"type": "show_user", "username": user_name}
+        return {"type": "show_user", "user_name": user_name}
 
     def drop_user(self, items):
         user_name = items[2]
-        return {"type": "drop_user", "username": user_name}
+        return {"type": "drop_user", "user_name": user_name}
 
     def alter_user(self, items):
         user_name = items[3]
         new_password = items[4]
-        return {"type": "alter_user", "username": user_name, "password": new_password}
+        return {"type": "alter_user", "user_name": user_name, "password": new_password}
 
     def create_user(self, items):
         user_name = items[2]
         password = items[3]
-        return {"type": "create_user", "username": user_name, "password": password, "role": "user"}
+        return {"type": "create_user", "user_name": user_name, "password": password, "role": "user"}
 
     def activate_user(self, items):
         user_name = items[3]
         activate_status = items[4]
-        return {"type": "activate_user", "activate_status": activate_status, "username": user_name}
+        return {"type": "activate_user", "activate_status": activate_status, "user_name": user_name}
 
     def list_datasets(self, items):
         user_name = items[3]
-        return {"type": "list_datasets", "username": user_name}
+        return {"type": "list_datasets", "user_name": user_name}
 
     def list_agents(self, items):
         user_name = items[3]
-        return {"type": "list_agents", "username": user_name}
+        return {"type": "list_agents", "user_name": user_name}
+
+    def create_role(self, items):
+        role_name = items[2]
+        if len(items) > 4:
+            description = items[4]
+            return {"type": "create_role", "role_name": role_name, "description": description}
+        else:
+            return {"type": "create_role", "role_name": role_name}
+
+    def drop_role(self, items):
+        role_name = items[2]
+        return {"type": "drop_role", "role_name": role_name}
+
+    def alter_role(self, items):
+        role_name = items[2]
+        description = items[5]
+        return {"type": "alter_role", "role_name": role_name, "description": description}
+
+    def list_roles(self, items):
+        return {"type": "list_roles"}
+
+    def show_role(self, items):
+        role_name = items[2]
+        return {"type": "show_role", "role_name": role_name}
+
+    def grant_permission(self, items):
+        action_list = items[1]
+        resource = items[3]
+        role_name = items[6]
+        return {"type": "grant_permission", "role_name": role_name, "resource": resource, "actions": action_list}
+
+    def revoke_permission(self, items):
+        action_list = items[1]
+        resource = items[3]
+        role_name = items[6]
+        return {
+            "type": "revoke_permission",
+            "role_name": role_name,
+            "resource": resource, "actions": action_list
+        }
+
+    def alter_user_role(self, items):
+        user_name = items[2]
+        role_name = items[5]
+        return {"type": "alter_user_role", "user_name": user_name, "role_name": role_name}
+
+    def show_user_permission(self, items):
+        user_name = items[3]
+        return {"type": "show_user_permission", "user_name": user_name}
+
+    def show_version(self, items):
+        return {"type": "show_version"}
+
+    def action_list(self, items):
+        return items
 
     def meta_command(self, items):
         command_name = str(items[0]).lower()
@@ -205,6 +299,8 @@ class AdminCLI(Cmd):
         self.is_interactive = False
         self.admin_account = "admin@ragflow.io"
         self.admin_password: str = "admin"
+        self.session = requests.Session()
+        self.access_token: str = ""
         self.host: str = ""
         self.port: int = 0
 
@@ -213,12 +309,8 @@ class AdminCLI(Cmd):
 
     def onecmd(self, command: str) -> bool:
         try:
-            # print(f"command: {command}")
             result = self.parse_command(command)
 
-            # if 'type' in result and result.get('type') == 'empty':
-            #     return False
-
             if isinstance(result, dict):
                 if 'type' in result and result.get('type') == 'empty':
                     return False
@@ -244,7 +336,7 @@ class AdminCLI(Cmd):
     def default(self, line: str) -> bool:
         return self.onecmd(line)
 
-    def parse_command(self, command_str: str) -> dict[str, str] | Tree[Token]:
+    def parse_command(self, command_str: str) -> dict[str, str]:
         if not command_str.strip():
             return {'type': 'empty'}
 
@@ -256,32 +348,38 @@ class AdminCLI(Cmd):
         except Exception as e:
             return {'type': 'error', 'message': f'Parse error: {str(e)}'}
 
-    def verify_admin(self, args):
+    def verify_admin(self, arguments: dict, single_command: bool):
-
+        self.host = arguments['host']
-        conn_info = self._parse_connection_args(args)
+        self.port = arguments['port']
-        if 'error' in conn_info:
-            print(f"Error: {conn_info['error']}")
-            return
-
-        self.host = conn_info['host']
-        self.port = conn_info['port']
         print(f"Attempt to access ip: {self.host}, port: {self.port}")
-        url = f'http://{self.host}:{self.port}/api/v1/admin/auth'
+        url = f"http://{self.host}:{self.port}/api/v1/admin/login"
+
+        attempt_count = 3
+        if single_command:
+            attempt_count = 1
 
         try_count = 0
         while True:
             try_count += 1
-            if try_count > 3:
+            if try_count > attempt_count:
                 return False
 
-            admin_passwd = input(f"password for {self.admin_account}: ").strip()
+            if single_command:
+                admin_passwd = arguments['password']
+            else:
+                admin_passwd = getpass.getpass(f"password for {self.admin_account}: ").strip()
             try:
-                self.admin_password = encode_to_base64(admin_passwd)
+                self.admin_password = encrypt(admin_passwd)
-                response = requests.get(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password))
+                response = self.session.post(url, json={'email': self.admin_account, 'password': self.admin_password})
                 if response.status_code == 200:
                     res_json = response.json()
                     error_code = res_json.get('code', -1)
                     if error_code == 0:
+                        self.session.headers.update({
+                            'Content-Type': 'application/json',
+                            'Authorization': response.headers['Authorization'],
+                            'User-Agent': 'RAGFlow-CLI/0.22.1'
+                        })
                         print("Authentication successful.")
                         return True
                     else:
@@ -289,10 +387,28 @@ class AdminCLI(Cmd):
                         print(f"Authentication failed: {error_message}, try again")
                         continue
                 else:
-                    print(f"Bad response，status: {response.status_code}, try again")
+                    print(f"Bad response，status: {response.status_code}, password is wrong")
-            except Exception:
+            except Exception as e:
+                print(str(e))
                 print(f"Can't access {self.host}, port: {self.port}")
 
+    def _format_service_detail_table(self, data):
+        if isinstance(data, list):
+            return data
+        if not all([isinstance(v, list) for v in data.values()]):
+            # normal table
+            return data
+        # handle task_executor heartbeats map, for example {'name': [{'done': 2, 'now': timestamp1}, {'done': 3, 'now': timestamp2}]
+        task_executor_list = []
+        for k, v in data.items():
+            # display latest status
+            heartbeats = sorted(v, key=lambda x: x["now"], reverse=True)
+            task_executor_list.append({
+                "task_executor_name": k,
+                **heartbeats[0],
+            } if heartbeats else {"task_executor_name": k})
+        return task_executor_list
+
     def _print_table_simple(self, data):
         if not data:
             print("No data to print")
@@ -301,7 +417,8 @@ class AdminCLI(Cmd):
             # handle single row data
             data = [data]
 
-        columns = list(data[0].keys())
+        columns = list(set().union(*(d.keys() for d in data)))
+        columns.sort()
         col_widths = {}
 
         def get_string_width(text):
@@ -341,9 +458,9 @@ class AdminCLI(Cmd):
             row = "|"
             for col in columns:
                 value = str(item.get(col, ''))
-                if len(value) > col_widths[col]:
+                if get_string_width(value) > col_widths[col]:
                     value = value[:col_widths[col] - 3] + "..."
-                row += f" {value:<{col_widths[col]}} |"
+                row += f" {value:<{col_widths[col] - (get_string_width(value) - len(value))}} |"
             print(row)
 
         print(separator)
@@ -375,23 +492,31 @@ class AdminCLI(Cmd):
                 print("\nGoodbye!")
                 break
 
-    def run_single_command(self, args):
+    def run_single_command(self, command: str):
-        conn_info = self._parse_connection_args(args)
+        result = self.parse_command(command)
-        if 'error' in conn_info:
+        self.execute_command(result)
-            print(f"Error: {conn_info['error']}")
-            return
 
-    def _parse_connection_args(self, args: List[str]) -> Dict[str, Any]:
+    def parse_connection_args(self, args: List[str]) -> Dict[str, Any]:
         parser = argparse.ArgumentParser(description='Admin CLI Client', add_help=False)
         parser.add_argument('-h', '--host', default='localhost', help='Admin service host')
-        parser.add_argument('-p', '--port', type=int, default=8080, help='Admin service port')
+        parser.add_argument('-p', '--port', type=int, default=9381, help='Admin service port')
-
+        parser.add_argument('-w', '--password', default='admin', type=str, help='Superuser password')
+        parser.add_argument('command', nargs='?', help='Single command')
         try:
             parsed_args, remaining_args = parser.parse_known_args(args)
-            return {
+            if remaining_args:
-                'host': parsed_args.host,
+                command = remaining_args[0]
-                'port': parsed_args.port,
+                return {
-            }
+                    'host': parsed_args.host,
+                    'port': parsed_args.port,
+                    'password': parsed_args.password,
+                    'command': command
+                }
+            else:
+                return {
+                    'host': parsed_args.host,
+                    'port': parsed_args.port,
+                }
         except SystemExit:
             return {'error': 'Invalid connection arguments'}
 
@@ -438,6 +563,26 @@ class AdminCLI(Cmd):
                 self._handle_list_datasets(command_dict)
             case 'list_agents':
                 self._handle_list_agents(command_dict)
+            case 'create_role':
+                self._create_role(command_dict)
+            case 'drop_role':
+                self._drop_role(command_dict)
+            case 'alter_role':
+                self._alter_role(command_dict)
+            case 'list_roles':
+                self._list_roles(command_dict)
+            case 'show_role':
+                self._show_role(command_dict)
+            case 'grant_permission':
+                self._grant_permission(command_dict)
+            case 'revoke_permission':
+                self._revoke_permission(command_dict)
+            case 'alter_user_role':
+                self._alter_user_role(command_dict)
+            case 'show_user_permission':
+                self._show_user_permission(command_dict)
+            case 'show_version':
+                self._show_version(command_dict)
             case 'meta':
                 self._handle_meta_command(command_dict)
             case _:
@@ -447,30 +592,31 @@ class AdminCLI(Cmd):
         print("Listing all services")
 
         url = f'http://{self.host}:{self.port}/api/v1/admin/services'
-        response = requests.get(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password))
+        response = self.session.get(url)
         res_json = response.json()
         if response.status_code == 200:
             self._print_table_simple(res_json['data'])
         else:
-            print(f"Fail to get all users, code: {res_json['code']}, message: {res_json['message']}")
+            print(f"Fail to get all services, code: {res_json['code']}, message: {res_json['message']}")
 
     def _handle_show_service(self, command):
         service_id: int = command['number']
         print(f"Showing service: {service_id}")
 
         url = f'http://{self.host}:{self.port}/api/v1/admin/services/{service_id}'
-        response = requests.get(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password))
+        response = self.session.get(url)
         res_json = response.json()
         if response.status_code == 200:
             res_data = res_json['data']
-            if res_data['alive']:
+            if 'status' in res_data and res_data['status'] == 'alive':
-                print(f"Service {res_data['service_name']} is alive. Detail:")
+                print(f"Service {res_data['service_name']} is alive, ")
                 if isinstance(res_data['message'], str):
                     print(res_data['message'])
                 else:
-                    self._print_table_simple(res_data['message'])
+                    data = self._format_service_detail_table(res_data['message'])
+                    self._print_table_simple(data)
             else:
-                print(f"Service {res_data['service_name']} is down. Detail: {res_data['message']}")
+                print(f"Service {res_data['service_name']} is down, {res_data['message']}")
         else:
             print(f"Fail to show service, code: {res_json['code']}, message: {res_json['message']}")
 
@@ -490,7 +636,7 @@ class AdminCLI(Cmd):
         print("Listing all users")
 
         url = f'http://{self.host}:{self.port}/api/v1/admin/users'
-        response = requests.get(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password))
+        response = self.session.get(url)
         res_json = response.json()
         if response.status_code == 200:
             self._print_table_simple(res_json['data'])
@@ -498,23 +644,25 @@ class AdminCLI(Cmd):
             print(f"Fail to get all users, code: {res_json['code']}, message: {res_json['message']}")
 
     def _handle_show_user(self, command):
-        username_tree: Tree = command['username']
+        username_tree: Tree = command['user_name']
-        username: str = username_tree.children[0].strip("'\"")
+        user_name: str = username_tree.children[0].strip("'\"")
-        print(f"Showing user: {username}")
+        print(f"Showing user: {user_name}")
-        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{username}'
+        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{user_name}'
-        response = requests.get(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password))
+        response = self.session.get(url)
         res_json = response.json()
         if response.status_code == 200:
-            self._print_table_simple(res_json['data'])
+            table_data = res_json['data']
+            table_data.pop('avatar')
+            self._print_table_simple(table_data)
         else:
-            print(f"Fail to get user {username}, code: {res_json['code']}, message: {res_json['message']}")
+            print(f"Fail to get user {user_name}, code: {res_json['code']}, message: {res_json['message']}")
 
     def _handle_drop_user(self, command):
-        username_tree: Tree = command['username']
+        username_tree: Tree = command['user_name']
-        username: str = username_tree.children[0].strip("'\"")
+        user_name: str = username_tree.children[0].strip("'\"")
-        print(f"Drop user: {username}")
+        print(f"Drop user: {user_name}")
-        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{username}'
+        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{user_name}'
-        response = requests.delete(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password))
+        response = self.session.delete(url)
         res_json = response.json()
         if response.status_code == 200:
             print(res_json["message"])
@@ -522,14 +670,13 @@ class AdminCLI(Cmd):
             print(f"Fail to drop user, code: {res_json['code']}, message: {res_json['message']}")
 
     def _handle_alter_user(self, command):
-        username_tree: Tree = command['username']
+        user_name_tree: Tree = command['user_name']
-        username: str = username_tree.children[0].strip("'\"")
+        user_name: str = user_name_tree.children[0].strip("'\"")
         password_tree: Tree = command['password']
         password: str = password_tree.children[0].strip("'\"")
-        print(f"Alter user: {username}, password: {password}")
+        print(f"Alter user: {user_name}, password: {password}")
-        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{username}/password'
+        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{user_name}/password'
-        response = requests.put(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password),
+        response = self.session.put(url, json={'new_password': encrypt(password)})
-                                json={'new_password': encrypt(password)})
         res_json = response.json()
         if response.status_code == 200:
             print(res_json["message"])
@@ -537,34 +684,32 @@ class AdminCLI(Cmd):
             print(f"Fail to alter password, code: {res_json['code']}, message: {res_json['message']}")
 
     def _handle_create_user(self, command):
-        username_tree: Tree = command['username']
+        user_name_tree: Tree = command['user_name']
-        username: str = username_tree.children[0].strip("'\"")
+        user_name: str = user_name_tree.children[0].strip("'\"")
         password_tree: Tree = command['password']
         password: str = password_tree.children[0].strip("'\"")
         role: str = command['role']
-        print(f"Create user: {username}, password: {password}, role: {role}")
+        print(f"Create user: {user_name}, password: {password}, role: {role}")
         url = f'http://{self.host}:{self.port}/api/v1/admin/users'
-        response = requests.post(
+        response = self.session.post(
             url,
-            auth=HTTPBasicAuth(self.admin_account, self.admin_password),
+            json={'user_name': user_name, 'password': encrypt(password), 'role': role}
-            json={'username': username, 'password': encrypt(password), 'role': role}
         )
         res_json = response.json()
         if response.status_code == 200:
             self._print_table_simple(res_json['data'])
         else:
-            print(f"Fail to create user {username}, code: {res_json['code']}, message: {res_json['message']}")
+            print(f"Fail to create user {user_name}, code: {res_json['code']}, message: {res_json['message']}")
 
     def _handle_activate_user(self, command):
-        username_tree: Tree = command['username']
+        user_name_tree: Tree = command['user_name']
-        username: str = username_tree.children[0].strip("'\"")
+        user_name: str = user_name_tree.children[0].strip("'\"")
         activate_tree: Tree = command['activate_status']
         activate_status: str = activate_tree.children[0].strip("'\"")
         if activate_status.lower() in ['on', 'off']:
-            print(f"Alter user {username} activate status, turn {activate_status.lower()}.")
+            print(f"Alter user {user_name} activate status, turn {activate_status.lower()}.")
-            url = f'http://{self.host}:{self.port}/api/v1/admin/users/{username}/activate'
+            url = f'http://{self.host}:{self.port}/api/v1/admin/users/{user_name}/activate'
-            response = requests.put(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password),
+            response = self.session.put(url, json={'activate_status': activate_status})
-                                    json={'activate_status': activate_status})
             res_json = response.json()
             if response.status_code == 200:
                 print(res_json["message"])
@@ -574,28 +719,194 @@ class AdminCLI(Cmd):
             print(f"Unknown activate status: {activate_status}.")
 
     def _handle_list_datasets(self, command):
-        username_tree: Tree = command['username']
+        username_tree: Tree = command['user_name']
-        username: str = username_tree.children[0].strip("'\"")
+        user_name: str = username_tree.children[0].strip("'\"")
-        print(f"Listing all datasets of user: {username}")
+        print(f"Listing all datasets of user: {user_name}")
-        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{username}/datasets'
+        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{user_name}/datasets'
-        response = requests.get(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password))
+        response = self.session.get(url)
         res_json = response.json()
         if response.status_code == 200:
-            self._print_table_simple(res_json['data'])
+            table_data = res_json['data']
+            for t in table_data:
+                t.pop('avatar')
+            self._print_table_simple(table_data)
         else:
-            print(f"Fail to get all datasets of {username}, code: {res_json['code']}, message: {res_json['message']}")
+            print(f"Fail to get all datasets of {user_name}, code: {res_json['code']}, message: {res_json['message']}")
 
     def _handle_list_agents(self, command):
-        username_tree: Tree = command['username']
+        username_tree: Tree = command['user_name']
-        username: str = username_tree.children[0].strip("'\"")
+        user_name: str = username_tree.children[0].strip("'\"")
-        print(f"Listing all agents of user: {username}")
+        print(f"Listing all agents of user: {user_name}")
-        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{username}/agents'
+        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{user_name}/agents'
-        response = requests.get(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password))
+        response = self.session.get(url)
+        res_json = response.json()
+        if response.status_code == 200:
+            table_data = res_json['data']
+            for t in table_data:
+                t.pop('avatar')
+            self._print_table_simple(table_data)
+        else:
+            print(f"Fail to get all agents of {user_name}, code: {res_json['code']}, message: {res_json['message']}")
+
+    def _create_role(self, command):
+        role_name_tree: Tree = command['role_name']
+        role_name: str = role_name_tree.children[0].strip("'\"")
+        desc_str: str = ''
+        if 'description' in command:
+            desc_tree: Tree = command['description']
+            desc_str = desc_tree.children[0].strip("'\"")
+
+        print(f"create role name: {role_name}, description: {desc_str}")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/roles'
+        response = self.session.post(
+            url,
+            json={'role_name': role_name, 'description': desc_str}
+        )
         res_json = response.json()
         if response.status_code == 200:
             self._print_table_simple(res_json['data'])
         else:
-            print(f"Fail to get all agents of {username}, code: {res_json['code']}, message: {res_json['message']}")
+            print(f"Fail to create role {role_name}, code: {res_json['code']}, message: {res_json['message']}")
+
+    def _drop_role(self, command):
+        role_name_tree: Tree = command['role_name']
+        role_name: str = role_name_tree.children[0].strip("'\"")
+        print(f"drop role name: {role_name}")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/roles/{role_name}'
+        response = self.session.delete(url)
+        res_json = response.json()
+        if response.status_code == 200:
+            self._print_table_simple(res_json['data'])
+        else:
+            print(f"Fail to drop role {role_name}, code: {res_json['code']}, message: {res_json['message']}")
+
+    def _alter_role(self, command):
+        role_name_tree: Tree = command['role_name']
+        role_name: str = role_name_tree.children[0].strip("'\"")
+        desc_tree: Tree = command['description']
+        desc_str: str = desc_tree.children[0].strip("'\"")
+
+        print(f"alter role name: {role_name}, description: {desc_str}")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/roles/{role_name}'
+        response = self.session.put(
+            url,
+            json={'description': desc_str}
+        )
+        res_json = response.json()
+        if response.status_code == 200:
+            self._print_table_simple(res_json['data'])
+        else:
+            print(
+                f"Fail to update role {role_name} with description: {desc_str}, code: {res_json['code']}, message: {res_json['message']}")
+
+    def _list_roles(self, command):
+        print("Listing all roles")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/roles'
+        response = self.session.get(url)
+        res_json = response.json()
+        if response.status_code == 200:
+            self._print_table_simple(res_json['data'])
+        else:
+            print(f"Fail to list roles, code: {res_json['code']}, message: {res_json['message']}")
+
+    def _show_role(self, command):
+        role_name_tree: Tree = command['role_name']
+        role_name: str = role_name_tree.children[0].strip("'\"")
+        print(f"show role: {role_name}")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/roles/{role_name}/permission'
+        response = self.session.get(url)
+        res_json = response.json()
+        if response.status_code == 200:
+            self._print_table_simple(res_json['data'])
+        else:
+            print(f"Fail to list roles, code: {res_json['code']}, message: {res_json['message']}")
+
+    def _grant_permission(self, command):
+        role_name_tree: Tree = command['role_name']
+        role_name_str: str = role_name_tree.children[0].strip("'\"")
+        resource_tree: Tree = command['resource']
+        resource_str: str = resource_tree.children[0].strip("'\"")
+        action_tree_list: list = command['actions']
+        actions: list = []
+        for action_tree in action_tree_list:
+            action_str: str = action_tree.children[0].strip("'\"")
+            actions.append(action_str)
+        print(f"grant role_name: {role_name_str}, resource: {resource_str}, actions: {actions}")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/roles/{role_name_str}/permission'
+        response = self.session.post(
+            url,
+            json={'actions': actions, 'resource': resource_str}
+        )
+        res_json = response.json()
+        if response.status_code == 200:
+            self._print_table_simple(res_json['data'])
+        else:
+            print(
+                f"Fail to grant role {role_name_str} with {actions} on {resource_str}, code: {res_json['code']}, message: {res_json['message']}")
+
+    def _revoke_permission(self, command):
+        role_name_tree: Tree = command['role_name']
+        role_name_str: str = role_name_tree.children[0].strip("'\"")
+        resource_tree: Tree = command['resource']
+        resource_str: str = resource_tree.children[0].strip("'\"")
+        action_tree_list: list = command['actions']
+        actions: list = []
+        for action_tree in action_tree_list:
+            action_str: str = action_tree.children[0].strip("'\"")
+            actions.append(action_str)
+        print(f"revoke role_name: {role_name_str}, resource: {resource_str}, actions: {actions}")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/roles/{role_name_str}/permission'
+        response = self.session.delete(
+            url,
+            json={'actions': actions, 'resource': resource_str}
+        )
+        res_json = response.json()
+        if response.status_code == 200:
+            self._print_table_simple(res_json['data'])
+        else:
+            print(
+                f"Fail to revoke role {role_name_str} with {actions} on {resource_str}, code: {res_json['code']}, message: {res_json['message']}")
+
+    def _alter_user_role(self, command):
+        role_name_tree: Tree = command['role_name']
+        role_name_str: str = role_name_tree.children[0].strip("'\"")
+        user_name_tree: Tree = command['user_name']
+        user_name_str: str = user_name_tree.children[0].strip("'\"")
+        print(f"alter_user_role user_name: {user_name_str}, role_name: {role_name_str}")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{user_name_str}/role'
+        response = self.session.put(
+            url,
+            json={'role_name': role_name_str}
+        )
+        res_json = response.json()
+        if response.status_code == 200:
+            self._print_table_simple(res_json['data'])
+        else:
+            print(
+                f"Fail to alter user: {user_name_str} to role {role_name_str}, code: {res_json['code']}, message: {res_json['message']}")
+
+    def _show_user_permission(self, command):
+        user_name_tree: Tree = command['user_name']
+        user_name_str: str = user_name_tree.children[0].strip("'\"")
+        print(f"show_user_permission user_name: {user_name_str}")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{user_name_str}/permission'
+        response = self.session.get(url)
+        res_json = response.json()
+        if response.status_code == 200:
+            self._print_table_simple(res_json['data'])
+        else:
+            print(
+                f"Fail to show user: {user_name_str} permission, code: {res_json['code']}, message: {res_json['message']}")
+
+    def _show_version(self, command):
+        print("show_version")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/version'
+        response = self.session.get(url)
+        res_json = response.json()
+        if response.status_code == 200:
+            self._print_table_simple(res_json['data'])
+        else:
+            print(f"Fail to show version, code: {res_json['code']}, message: {res_json['message']}")
 
     def _handle_meta_command(self, command):
         meta_command = command['command']
@@ -638,27 +949,29 @@ def main():
 
     cli = AdminCLI()
 
-    if len(sys.argv) == 1 or (len(sys.argv) > 1 and sys.argv[1] == '-'):
+    args = cli.parse_connection_args(sys.argv)
-        print(r"""
+    if 'error' in args:
-            ____  ___   ______________                 ___       __          _     
+        print(f"Error: {args['error']}")
-           / __ \/   | / ____/ ____/ /___ _      __   /   | ____/ /___ ___  (_)___ 
+        return
-          / /_/ / /| |/ / __/ /_  / / __ \ | /| / /  / /| |/ __  / __ `__ \/ / __ \
+
-         / _, _/ ___ / /_/ / __/ / / /_/ / |/ |/ /  / ___ / /_/ / / / / / / / / / /
+    if 'command' in args:
-        /_/ |_/_/  |_\____/_/   /_/\____/|__/|__/  /_/  |_\__,_/_/ /_/ /_/_/_/ /_/ 
+        if 'password' not in args:
-        """)
+            print("Error: password is missing")
-        if cli.verify_admin(sys.argv):
+            return
-            cli.cmdloop()
+        if cli.verify_admin(args, single_command=True):
+            command: str = args['command']
+            print(f"Run single command: {command}")
+            cli.run_single_command(command)
     else:
-        print(r"""
+        if cli.verify_admin(args, single_command=False):
-            ____  ___   ______________                 ___       __          _     
+            print(r"""
-           / __ \/   | / ____/ ____/ /___ _      __   /   | ____/ /___ ___  (_)___ 
+                ____  ___   ______________                 ___       __          _     
-          / /_/ / /| |/ / __/ /_  / / __ \ | /| / /  / /| |/ __  / __ `__ \/ / __ \
+               / __ \/   | / ____/ ____/ /___ _      __   /   | ____/ /___ ___  (_)___ 
-         / _, _/ ___ / /_/ / __/ / / /_/ / |/ |/ /  / ___ / /_/ / / / / / / / / / /
+              / /_/ / /| |/ / __/ /_  / / __ \ | /| / /  / /| |/ __  / __ `__ \/ / __ \
-        /_/ |_/_/  |_\____/_/   /_/\____/|__/|__/  /_/  |_\__,_/_/ /_/ /_/_/_/ /_/ 
+             / _, _/ ___ / /_/ / __/ / / /_/ / |/ |/ /  / ___ / /_/ / / / / / / / / / /
-        """)
+            /_/ |_/_/  |_\____/_/   /_/\____/|__/|__/  /_/  |_\__,_/_/ /_/ /_/_/_/ /_/ 
-        if cli.verify_admin(sys.argv):
+            """)
             cli.cmdloop()
-            # cli.run_single_command(sys.argv[1:])
 
 
 if __name__ == '__main__':

admin/client/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ragflow-cli"
-version = "0.21.0.dev5"
+version = "0.22.1"
 description = "Admin Service's client of [RAGFlow](https://github.com/infiniflow/ragflow). The Admin Service provides user management and system monitoring. "
 authors = [{ name = "Lynn", email = "lynn_inf@hotmail.com" }]
 license = { text = "Apache License, Version 2.0" }
@@ -8,7 +8,7 @@ readme = "README.md"
 requires-python = ">=3.10,<3.13"
 dependencies = [
     "requests>=2.30.0,<3.0.0",
-    "beartype>=0.18.5,<0.19.0",
+    "beartype>=0.20.0,<1.0.0",
     "pycryptodomex>=3.10.0",
     "lark>=1.1.0",
 ]

admin/client/uv.lock

@@ -0,0 +1,298 @@
+version = 1
+revision = 3
+requires-python = ">=3.10, <3.13"
+
+[[package]]
+name = "beartype"
+version = "0.22.6"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/88/e2/105ceb1704cb80fe4ab3872529ab7b6f365cf7c74f725e6132d0efcf1560/beartype-0.22.6.tar.gz", hash = "sha256:97fbda69c20b48c5780ac2ca60ce3c1bb9af29b3a1a0216898ffabdd523e48f4", size = 1588975, upload-time = "2025-11-20T04:47:14.736Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/98/c9/ceecc71fe2c9495a1d8e08d44f5f31f5bca1350d5b2e27a4b6265424f59e/beartype-0.22.6-py3-none-any.whl", hash = "sha256:0584bc46a2ea2a871509679278cda992eadde676c01356ab0ac77421f3c9a093", size = 1324807, upload-time = "2025-11-20T04:47:11.837Z" },
+]
+
+[[package]]
+name = "certifi"
+version = "2025.11.12"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/a2/8c/58f469717fa48465e4a50c014a0400602d3c437d7c0c468e17ada824da3a/certifi-2025.11.12.tar.gz", hash = "sha256:d8ab5478f2ecd78af242878415affce761ca6bc54a22a27e026d7c25357c3316", size = 160538, upload-time = "2025-11-12T02:54:51.517Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/70/7d/9bc192684cea499815ff478dfcdc13835ddf401365057044fb721ec6bddb/certifi-2025.11.12-py3-none-any.whl", hash = "sha256:97de8790030bbd5c2d96b7ec782fc2f7820ef8dba6db909ccf95449f2d062d4b", size = 159438, upload-time = "2025-11-12T02:54:49.735Z" },
+]
+
+[[package]]
+name = "charset-normalizer"
+version = "3.4.4"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/13/69/33ddede1939fdd074bce5434295f38fae7136463422fe4fd3e0e89b98062/charset_normalizer-3.4.4.tar.gz", hash = "sha256:94537985111c35f28720e43603b8e7b43a6ecfb2ce1d3058bbe955b73404e21a", size = 129418, upload-time = "2025-10-14T04:42:32.879Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/1f/b8/6d51fc1d52cbd52cd4ccedd5b5b2f0f6a11bbf6765c782298b0f3e808541/charset_normalizer-3.4.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:e824f1492727fa856dd6eda4f7cee25f8518a12f3c4a56a74e8095695089cf6d", size = 209709, upload-time = "2025-10-14T04:40:11.385Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/5c/af/1f9d7f7faafe2ddfb6f72a2e07a548a629c61ad510fe60f9630309908fef/charset_normalizer-3.4.4-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4bd5d4137d500351a30687c2d3971758aac9a19208fc110ccb9d7188fbe709e8", size = 148814, upload-time = "2025-10-14T04:40:13.135Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/79/3d/f2e3ac2bbc056ca0c204298ea4e3d9db9b4afe437812638759db2c976b5f/charset_normalizer-3.4.4-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:027f6de494925c0ab2a55eab46ae5129951638a49a34d87f4c3eda90f696b4ad", size = 144467, upload-time = "2025-10-14T04:40:14.728Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/ec/85/1bf997003815e60d57de7bd972c57dc6950446a3e4ccac43bc3070721856/charset_normalizer-3.4.4-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:f820802628d2694cb7e56db99213f930856014862f3fd943d290ea8438d07ca8", size = 162280, upload-time = "2025-10-14T04:40:16.14Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/3e/8e/6aa1952f56b192f54921c436b87f2aaf7c7a7c3d0d1a765547d64fd83c13/charset_normalizer-3.4.4-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:798d75d81754988d2565bff1b97ba5a44411867c0cf32b77a7e8f8d84796b10d", size = 159454, upload-time = "2025-10-14T04:40:17.567Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/36/3b/60cbd1f8e93aa25d1c669c649b7a655b0b5fb4c571858910ea9332678558/charset_normalizer-3.4.4-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9d1bb833febdff5c8927f922386db610b49db6e0d4f4ee29601d71e7c2694313", size = 153609, upload-time = "2025-10-14T04:40:19.08Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/64/91/6a13396948b8fd3c4b4fd5bc74d045f5637d78c9675585e8e9fbe5636554/charset_normalizer-3.4.4-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:9cd98cdc06614a2f768d2b7286d66805f94c48cde050acdbbb7db2600ab3197e", size = 151849, upload-time = "2025-10-14T04:40:20.607Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/b7/7a/59482e28b9981d105691e968c544cc0df3b7d6133152fb3dcdc8f135da7a/charset_normalizer-3.4.4-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:077fbb858e903c73f6c9db43374fd213b0b6a778106bc7032446a8e8b5b38b93", size = 151586, upload-time = "2025-10-14T04:40:21.719Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/92/59/f64ef6a1c4bdd2baf892b04cd78792ed8684fbc48d4c2afe467d96b4df57/charset_normalizer-3.4.4-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:244bfb999c71b35de57821b8ea746b24e863398194a4014e4c76adc2bbdfeff0", size = 145290, upload-time = "2025-10-14T04:40:23.069Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/6b/63/3bf9f279ddfa641ffa1962b0db6a57a9c294361cc2f5fcac997049a00e9c/charset_normalizer-3.4.4-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:64b55f9dce520635f018f907ff1b0df1fdc31f2795a922fb49dd14fbcdf48c84", size = 163663, upload-time = "2025-10-14T04:40:24.17Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/ed/09/c9e38fc8fa9e0849b172b581fd9803bdf6e694041127933934184e19f8c3/charset_normalizer-3.4.4-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:faa3a41b2b66b6e50f84ae4a68c64fcd0c44355741c6374813a800cd6695db9e", size = 151964, upload-time = "2025-10-14T04:40:25.368Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/d2/d1/d28b747e512d0da79d8b6a1ac18b7ab2ecfd81b2944c4c710e166d8dd09c/charset_normalizer-3.4.4-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:6515f3182dbe4ea06ced2d9e8666d97b46ef4c75e326b79bb624110f122551db", size = 161064, upload-time = "2025-10-14T04:40:26.806Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/bb/9a/31d62b611d901c3b9e5500c36aab0ff5eb442043fb3a1c254200d3d397d9/charset_normalizer-3.4.4-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:cc00f04ed596e9dc0da42ed17ac5e596c6ccba999ba6bd92b0e0aef2f170f2d6", size = 155015, upload-time = "2025-10-14T04:40:28.284Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/1f/f3/107e008fa2bff0c8b9319584174418e5e5285fef32f79d8ee6a430d0039c/charset_normalizer-3.4.4-cp310-cp310-win32.whl", hash = "sha256:f34be2938726fc13801220747472850852fe6b1ea75869a048d6f896838c896f", size = 99792, upload-time = "2025-10-14T04:40:29.613Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/eb/66/e396e8a408843337d7315bab30dbf106c38966f1819f123257f5520f8a96/charset_normalizer-3.4.4-cp310-cp310-win_amd64.whl", hash = "sha256:a61900df84c667873b292c3de315a786dd8dac506704dea57bc957bd31e22c7d", size = 107198, upload-time = "2025-10-14T04:40:30.644Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/b5/58/01b4f815bf0312704c267f2ccb6e5d42bcc7752340cd487bc9f8c3710597/charset_normalizer-3.4.4-cp310-cp310-win_arm64.whl", hash = "sha256:cead0978fc57397645f12578bfd2d5ea9138ea0fac82b2f63f7f7c6877986a69", size = 100262, upload-time = "2025-10-14T04:40:32.108Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/ed/27/c6491ff4954e58a10f69ad90aca8a1b6fe9c5d3c6f380907af3c37435b59/charset_normalizer-3.4.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:6e1fcf0720908f200cd21aa4e6750a48ff6ce4afe7ff5a79a90d5ed8a08296f8", size = 206988, upload-time = "2025-10-14T04:40:33.79Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/94/59/2e87300fe67ab820b5428580a53cad894272dbb97f38a7a814a2a1ac1011/charset_normalizer-3.4.4-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5f819d5fe9234f9f82d75bdfa9aef3a3d72c4d24a6e57aeaebba32a704553aa0", size = 147324, upload-time = "2025-10-14T04:40:34.961Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/07/fb/0cf61dc84b2b088391830f6274cb57c82e4da8bbc2efeac8c025edb88772/charset_normalizer-3.4.4-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:a59cb51917aa591b1c4e6a43c132f0cdc3c76dbad6155df4e28ee626cc77a0a3", size = 142742, upload-time = "2025-10-14T04:40:36.105Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/62/8b/171935adf2312cd745d290ed93cf16cf0dfe320863ab7cbeeae1dcd6535f/charset_normalizer-3.4.4-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:8ef3c867360f88ac904fd3f5e1f902f13307af9052646963ee08ff4f131adafc", size = 160863, upload-time = "2025-10-14T04:40:37.188Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/09/73/ad875b192bda14f2173bfc1bc9a55e009808484a4b256748d931b6948442/charset_normalizer-3.4.4-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d9e45d7faa48ee908174d8fe84854479ef838fc6a705c9315372eacbc2f02897", size = 157837, upload-time = "2025-10-14T04:40:38.435Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/6d/fc/de9cce525b2c5b94b47c70a4b4fb19f871b24995c728e957ee68ab1671ea/charset_normalizer-3.4.4-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:840c25fb618a231545cbab0564a799f101b63b9901f2569faecd6b222ac72381", size = 151550, upload-time = "2025-10-14T04:40:40.053Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/55/c2/43edd615fdfba8c6f2dfbd459b25a6b3b551f24ea21981e23fb768503ce1/charset_normalizer-3.4.4-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:ca5862d5b3928c4940729dacc329aa9102900382fea192fc5e52eb69d6093815", size = 149162, upload-time = "2025-10-14T04:40:41.163Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/03/86/bde4ad8b4d0e9429a4e82c1e8f5c659993a9a863ad62c7df05cf7b678d75/charset_normalizer-3.4.4-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:d9c7f57c3d666a53421049053eaacdd14bbd0a528e2186fcb2e672effd053bb0", size = 150019, upload-time = "2025-10-14T04:40:42.276Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/1f/86/a151eb2af293a7e7bac3a739b81072585ce36ccfb4493039f49f1d3cae8c/charset_normalizer-3.4.4-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:277e970e750505ed74c832b4bf75dac7476262ee2a013f5574dd49075879e161", size = 143310, upload-time = "2025-10-14T04:40:43.439Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/b5/fe/43dae6144a7e07b87478fdfc4dbe9efd5defb0e7ec29f5f58a55aeef7bf7/charset_normalizer-3.4.4-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:31fd66405eaf47bb62e8cd575dc621c56c668f27d46a61d975a249930dd5e2a4", size = 162022, upload-time = "2025-10-14T04:40:44.547Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/80/e6/7aab83774f5d2bca81f42ac58d04caf44f0cc2b65fc6db2b3b2e8a05f3b3/charset_normalizer-3.4.4-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:0d3d8f15c07f86e9ff82319b3d9ef6f4bf907608f53fe9d92b28ea9ae3d1fd89", size = 149383, upload-time = "2025-10-14T04:40:46.018Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/4f/e8/b289173b4edae05c0dde07f69f8db476a0b511eac556dfe0d6bda3c43384/charset_normalizer-3.4.4-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:9f7fcd74d410a36883701fafa2482a6af2ff5ba96b9a620e9e0721e28ead5569", size = 159098, upload-time = "2025-10-14T04:40:47.081Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/d8/df/fe699727754cae3f8478493c7f45f777b17c3ef0600e28abfec8619eb49c/charset_normalizer-3.4.4-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:ebf3e58c7ec8a8bed6d66a75d7fb37b55e5015b03ceae72a8e7c74495551e224", size = 152991, upload-time = "2025-10-14T04:40:48.246Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/1a/86/584869fe4ddb6ffa3bd9f491b87a01568797fb9bd8933f557dba9771beaf/charset_normalizer-3.4.4-cp311-cp311-win32.whl", hash = "sha256:eecbc200c7fd5ddb9a7f16c7decb07b566c29fa2161a16cf67b8d068bd21690a", size = 99456, upload-time = "2025-10-14T04:40:49.376Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/65/f6/62fdd5feb60530f50f7e38b4f6a1d5203f4d16ff4f9f0952962c044e919a/charset_normalizer-3.4.4-cp311-cp311-win_amd64.whl", hash = "sha256:5ae497466c7901d54b639cf42d5b8c1b6a4fead55215500d2f486d34db48d016", size = 106978, upload-time = "2025-10-14T04:40:50.844Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/7a/9d/0710916e6c82948b3be62d9d398cb4fcf4e97b56d6a6aeccd66c4b2f2bd5/charset_normalizer-3.4.4-cp311-cp311-win_arm64.whl", hash = "sha256:65e2befcd84bc6f37095f5961e68a6f077bf44946771354a28ad434c2cce0ae1", size = 99969, upload-time = "2025-10-14T04:40:52.272Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f3/85/1637cd4af66fa687396e757dec650f28025f2a2f5a5531a3208dc0ec43f2/charset_normalizer-3.4.4-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:0a98e6759f854bd25a58a73fa88833fba3b7c491169f86ce1180c948ab3fd394", size = 208425, upload-time = "2025-10-14T04:40:53.353Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/9d/6a/04130023fef2a0d9c62d0bae2649b69f7b7d8d24ea5536feef50551029df/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b5b290ccc2a263e8d185130284f8501e3e36c5e02750fc6b6bdeb2e9e96f1e25", size = 148162, upload-time = "2025-10-14T04:40:54.558Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/78/29/62328d79aa60da22c9e0b9a66539feae06ca0f5a4171ac4f7dc285b83688/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:74bb723680f9f7a6234dcf67aea57e708ec1fbdf5699fb91dfd6f511b0a320ef", size = 144558, upload-time = "2025-10-14T04:40:55.677Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/86/bb/b32194a4bf15b88403537c2e120b817c61cd4ecffa9b6876e941c3ee38fe/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:f1e34719c6ed0b92f418c7c780480b26b5d9c50349e9a9af7d76bf757530350d", size = 161497, upload-time = "2025-10-14T04:40:57.217Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/19/89/a54c82b253d5b9b111dc74aca196ba5ccfcca8242d0fb64146d4d3183ff1/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:2437418e20515acec67d86e12bf70056a33abdacb5cb1655042f6538d6b085a8", size = 159240, upload-time = "2025-10-14T04:40:58.358Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/c0/10/d20b513afe03acc89ec33948320a5544d31f21b05368436d580dec4e234d/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:11d694519d7f29d6cd09f6ac70028dba10f92f6cdd059096db198c283794ac86", size = 153471, upload-time = "2025-10-14T04:40:59.468Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/61/fa/fbf177b55bdd727010f9c0a3c49eefa1d10f960e5f09d1d887bf93c2e698/charset_normalizer-3.4.4-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:ac1c4a689edcc530fc9d9aa11f5774b9e2f33f9a0c6a57864e90908f5208d30a", size = 150864, upload-time = "2025-10-14T04:41:00.623Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/05/12/9fbc6a4d39c0198adeebbde20b619790e9236557ca59fc40e0e3cebe6f40/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:21d142cc6c0ec30d2efee5068ca36c128a30b0f2c53c1c07bd78cb6bc1d3be5f", size = 150647, upload-time = "2025-10-14T04:41:01.754Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/ad/1f/6a9a593d52e3e8c5d2b167daf8c6b968808efb57ef4c210acb907c365bc4/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:5dbe56a36425d26d6cfb40ce79c314a2e4dd6211d51d6d2191c00bed34f354cc", size = 145110, upload-time = "2025-10-14T04:41:03.231Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/30/42/9a52c609e72471b0fc54386dc63c3781a387bb4fe61c20231a4ebcd58bdd/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:5bfbb1b9acf3334612667b61bd3002196fe2a1eb4dd74d247e0f2a4d50ec9bbf", size = 162839, upload-time = "2025-10-14T04:41:04.715Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/c4/5b/c0682bbf9f11597073052628ddd38344a3d673fda35a36773f7d19344b23/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:d055ec1e26e441f6187acf818b73564e6e6282709e9bcb5b63f5b23068356a15", size = 150667, upload-time = "2025-10-14T04:41:05.827Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/e4/24/a41afeab6f990cf2daf6cb8c67419b63b48cf518e4f56022230840c9bfb2/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:af2d8c67d8e573d6de5bc30cdb27e9b95e49115cd9baad5ddbd1a6207aaa82a9", size = 160535, upload-time = "2025-10-14T04:41:06.938Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/2a/e5/6a4ce77ed243c4a50a1fecca6aaaab419628c818a49434be428fe24c9957/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:780236ac706e66881f3b7f2f32dfe90507a09e67d1d454c762cf642e6e1586e0", size = 154816, upload-time = "2025-10-14T04:41:08.101Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/a8/ef/89297262b8092b312d29cdb2517cb1237e51db8ecef2e9af5edbe7b683b1/charset_normalizer-3.4.4-cp312-cp312-win32.whl", hash = "sha256:5833d2c39d8896e4e19b689ffc198f08ea58116bee26dea51e362ecc7cd3ed26", size = 99694, upload-time = "2025-10-14T04:41:09.23Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/3d/2d/1e5ed9dd3b3803994c155cd9aacb60c82c331bad84daf75bcb9c91b3295e/charset_normalizer-3.4.4-cp312-cp312-win_amd64.whl", hash = "sha256:a79cfe37875f822425b89a82333404539ae63dbdddf97f84dcbc3d339aae9525", size = 107131, upload-time = "2025-10-14T04:41:10.467Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/d0/d9/0ed4c7098a861482a7b6a95603edce4c0d9db2311af23da1fb2b75ec26fc/charset_normalizer-3.4.4-cp312-cp312-win_arm64.whl", hash = "sha256:376bec83a63b8021bb5c8ea75e21c4ccb86e7e45ca4eb81146091b56599b80c3", size = 100390, upload-time = "2025-10-14T04:41:11.915Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/0a/4c/925909008ed5a988ccbb72dcc897407e5d6d3bd72410d69e051fc0c14647/charset_normalizer-3.4.4-py3-none-any.whl", hash = "sha256:7a32c560861a02ff789ad905a2fe94e3f840803362c84fecf1851cb4cf3dc37f", size = 53402, upload-time = "2025-10-14T04:42:31.76Z" },
+]
+
+[[package]]
+name = "colorama"
+version = "0.4.6"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/d8/53/6f443c9a4a8358a93a6792e2acffb9d9d5cb0a5cfd8802644b7b1c9a02e4/colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44", size = 27697, upload-time = "2022-10-25T02:36:22.414Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335, upload-time = "2022-10-25T02:36:20.889Z" },
+]
+
+[[package]]
+name = "exceptiongroup"
+version = "1.3.1"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+dependencies = [
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/50/79/66800aadf48771f6b62f7eb014e352e5d06856655206165d775e675a02c9/exceptiongroup-1.3.1.tar.gz", hash = "sha256:8b412432c6055b0b7d14c310000ae93352ed6754f70fa8f7c34141f91c4e3219", size = 30371, upload-time = "2025-11-21T23:01:54.787Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/8a/0e/97c33bf5009bdbac74fd2beace167cab3f978feb69cc36f1ef79360d6c4e/exceptiongroup-1.3.1-py3-none-any.whl", hash = "sha256:a7a39a3bd276781e98394987d3a5701d0c4edffb633bb7a5144577f82c773598", size = 16740, upload-time = "2025-11-21T23:01:53.443Z" },
+]
+
+[[package]]
+name = "idna"
+version = "3.11"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/6f/6d/0703ccc57f3a7233505399edb88de3cbd678da106337b9fcde432b65ed60/idna-3.11.tar.gz", hash = "sha256:795dafcc9c04ed0c1fb032c2aa73654d8e8c5023a7df64a53f39190ada629902", size = 194582, upload-time = "2025-10-12T14:55:20.501Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/0e/61/66938bbb5fc52dbdf84594873d5b51fb1f7c7794e9c0f5bd885f30bc507b/idna-3.11-py3-none-any.whl", hash = "sha256:771a87f49d9defaf64091e6e6fe9c18d4833f140bd19464795bc32d966ca37ea", size = 71008, upload-time = "2025-10-12T14:55:18.883Z" },
+]
+
+[[package]]
+name = "iniconfig"
+version = "2.3.0"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/72/34/14ca021ce8e5dfedc35312d08ba8bf51fdd999c576889fc2c24cb97f4f10/iniconfig-2.3.0.tar.gz", hash = "sha256:c76315c77db068650d49c5b56314774a7804df16fee4402c1f19d6d15d8c4730", size = 20503, upload-time = "2025-10-18T21:55:43.219Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/cb/b1/3846dd7f199d53cb17f49cba7e651e9ce294d8497c8c150530ed11865bb8/iniconfig-2.3.0-py3-none-any.whl", hash = "sha256:f631c04d2c48c52b84d0d0549c99ff3859c98df65b3101406327ecc7d53fbf12", size = 7484, upload-time = "2025-10-18T21:55:41.639Z" },
+]
+
+[[package]]
+name = "lark"
+version = "1.3.1"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/da/34/28fff3ab31ccff1fd4f6c7c7b0ceb2b6968d8ea4950663eadcb5720591a0/lark-1.3.1.tar.gz", hash = "sha256:b426a7a6d6d53189d318f2b6236ab5d6429eaf09259f1ca33eb716eed10d2905", size = 382732, upload-time = "2025-10-27T18:25:56.653Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/82/3d/14ce75ef66813643812f3093ab17e46d3a206942ce7376d31ec2d36229e7/lark-1.3.1-py3-none-any.whl", hash = "sha256:c629b661023a014c37da873b4ff58a817398d12635d3bbb2c5a03be7fe5d1e12", size = 113151, upload-time = "2025-10-27T18:25:54.882Z" },
+]
+
+[[package]]
+name = "packaging"
+version = "25.0"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/a1/d4/1fc4078c65507b51b96ca8f8c3ba19e6a61c8253c72794544580a7b6c24d/packaging-25.0.tar.gz", hash = "sha256:d443872c98d677bf60f6a1f2f8c1cb748e8fe762d2bf9d3148b5599295b0fc4f", size = 165727, upload-time = "2025-04-19T11:48:59.673Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/20/12/38679034af332785aac8774540895e234f4d07f7545804097de4b666afd8/packaging-25.0-py3-none-any.whl", hash = "sha256:29572ef2b1f17581046b3a2227d5c611fb25ec70ca1ba8554b24b0e69331a484", size = 66469, upload-time = "2025-04-19T11:48:57.875Z" },
+]
+
+[[package]]
+name = "pluggy"
+version = "1.6.0"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f9/e2/3e91f31a7d2b083fe6ef3fa267035b518369d9511ffab804f839851d2779/pluggy-1.6.0.tar.gz", hash = "sha256:7dcc130b76258d33b90f61b658791dede3486c3e6bfb003ee5c9bfb396dd22f3", size = 69412, upload-time = "2025-05-15T12:30:07.975Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/54/20/4d324d65cc6d9205fabedc306948156824eb9f0ee1633355a8f7ec5c66bf/pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746", size = 20538, upload-time = "2025-05-15T12:30:06.134Z" },
+]
+
+[[package]]
+name = "pycryptodomex"
+version = "3.23.0"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/c9/85/e24bf90972a30b0fcd16c73009add1d7d7cd9140c2498a68252028899e41/pycryptodomex-3.23.0.tar.gz", hash = "sha256:71909758f010c82bc99b0abf4ea12012c98962fbf0583c2164f8b84533c2e4da", size = 4922157, upload-time = "2025-05-17T17:23:41.434Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/dd/9c/1a8f35daa39784ed8adf93a694e7e5dc15c23c741bbda06e1d45f8979e9e/pycryptodomex-3.23.0-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:06698f957fe1ab229a99ba2defeeae1c09af185baa909a31a5d1f9d42b1aaed6", size = 2499240, upload-time = "2025-05-17T17:22:46.953Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/7a/62/f5221a191a97157d240cf6643747558759126c76ee92f29a3f4aee3197a5/pycryptodomex-3.23.0-cp37-abi3-macosx_10_9_x86_64.whl", hash = "sha256:b2c2537863eccef2d41061e82a881dcabb04944c5c06c5aa7110b577cc487545", size = 1644042, upload-time = "2025-05-17T17:22:49.098Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/8c/fd/5a054543c8988d4ed7b612721d7e78a4b9bf36bc3c5ad45ef45c22d0060e/pycryptodomex-3.23.0-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:43c446e2ba8df8889e0e16f02211c25b4934898384c1ec1ec04d7889c0333587", size = 2186227, upload-time = "2025-05-17T17:22:51.139Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/c8/a9/8862616a85cf450d2822dbd4fff1fcaba90877907a6ff5bc2672cafe42f8/pycryptodomex-3.23.0-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f489c4765093fb60e2edafdf223397bc716491b2b69fe74367b70d6999257a5c", size = 2272578, upload-time = "2025-05-17T17:22:53.676Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/46/9f/bda9c49a7c1842820de674ab36c79f4fbeeee03f8ff0e4f3546c3889076b/pycryptodomex-3.23.0-cp37-abi3-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bdc69d0d3d989a1029df0eed67cc5e8e5d968f3724f4519bd03e0ec68df7543c", size = 2312166, upload-time = "2025-05-17T17:22:56.585Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/03/cc/870b9bf8ca92866ca0186534801cf8d20554ad2a76ca959538041b7a7cf4/pycryptodomex-3.23.0-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:6bbcb1dd0f646484939e142462d9e532482bc74475cecf9c4903d4e1cd21f003", size = 2185467, upload-time = "2025-05-17T17:22:59.237Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/96/e3/ce9348236d8e669fea5dd82a90e86be48b9c341210f44e25443162aba187/pycryptodomex-3.23.0-cp37-abi3-musllinux_1_2_i686.whl", hash = "sha256:8a4fcd42ccb04c31268d1efeecfccfd1249612b4de6374205376b8f280321744", size = 2346104, upload-time = "2025-05-17T17:23:02.112Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/a5/e9/e869bcee87beb89040263c416a8a50204f7f7a83ac11897646c9e71e0daf/pycryptodomex-3.23.0-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:55ccbe27f049743a4caf4f4221b166560d3438d0b1e5ab929e07ae1702a4d6fd", size = 2271038, upload-time = "2025-05-17T17:23:04.872Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/8d/67/09ee8500dd22614af5fbaa51a4aee6e342b5fa8aecf0a6cb9cbf52fa6d45/pycryptodomex-3.23.0-cp37-abi3-win32.whl", hash = "sha256:189afbc87f0b9f158386bf051f720e20fa6145975f1e76369303d0f31d1a8d7c", size = 1771969, upload-time = "2025-05-17T17:23:07.115Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/69/96/11f36f71a865dd6df03716d33bd07a67e9d20f6b8d39820470b766af323c/pycryptodomex-3.23.0-cp37-abi3-win_amd64.whl", hash = "sha256:52e5ca58c3a0b0bd5e100a9fbc8015059b05cffc6c66ce9d98b4b45e023443b9", size = 1803124, upload-time = "2025-05-17T17:23:09.267Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f9/93/45c1cdcbeb182ccd2e144c693eaa097763b08b38cded279f0053ed53c553/pycryptodomex-3.23.0-cp37-abi3-win_arm64.whl", hash = "sha256:02d87b80778c171445d67e23d1caef279bf4b25c3597050ccd2e13970b57fd51", size = 1707161, upload-time = "2025-05-17T17:23:11.414Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f3/b8/3e76d948c3c4ac71335bbe75dac53e154b40b0f8f1f022dfa295257a0c96/pycryptodomex-3.23.0-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:ebfff755c360d674306e5891c564a274a47953562b42fb74a5c25b8fc1fb1cb5", size = 1627695, upload-time = "2025-05-17T17:23:17.38Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/6a/cf/80f4297a4820dfdfd1c88cf6c4666a200f204b3488103d027b5edd9176ec/pycryptodomex-3.23.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:eca54f4bb349d45afc17e3011ed4264ef1cc9e266699874cdd1349c504e64798", size = 1675772, upload-time = "2025-05-17T17:23:19.202Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/d1/42/1e969ee0ad19fe3134b0e1b856c39bd0b70d47a4d0e81c2a8b05727394c9/pycryptodomex-3.23.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4f2596e643d4365e14d0879dc5aafe6355616c61c2176009270f3048f6d9a61f", size = 1668083, upload-time = "2025-05-17T17:23:21.867Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/6e/c3/1de4f7631fea8a992a44ba632aa40e0008764c0fb9bf2854b0acf78c2cf2/pycryptodomex-3.23.0-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:fdfac7cda115bca3a5abb2f9e43bc2fb66c2b65ab074913643803ca7083a79ea", size = 1706056, upload-time = "2025-05-17T17:23:24.031Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f2/5f/af7da8e6f1e42b52f44a24d08b8e4c726207434e2593732d39e7af5e7256/pycryptodomex-3.23.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:14c37aaece158d0ace436f76a7bb19093db3b4deade9797abfc39ec6cd6cc2fe", size = 1806478, upload-time = "2025-05-17T17:23:26.066Z" },
+]
+
+[[package]]
+name = "pygments"
+version = "2.19.2"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/b0/77/a5b8c569bf593b0140bde72ea885a803b82086995367bf2037de0159d924/pygments-2.19.2.tar.gz", hash = "sha256:636cb2477cec7f8952536970bc533bc43743542f70392ae026374600add5b887", size = 4968631, upload-time = "2025-06-21T13:39:12.283Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/c7/21/705964c7812476f378728bdf590ca4b771ec72385c533964653c68e86bdc/pygments-2.19.2-py3-none-any.whl", hash = "sha256:86540386c03d588bb81d44bc3928634ff26449851e99741617ecb9037ee5ec0b", size = 1225217, upload-time = "2025-06-21T13:39:07.939Z" },
+]
+
+[[package]]
+name = "pytest"
+version = "9.0.1"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+dependencies = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "exceptiongroup", marker = "python_full_version < '3.11'" },
+    { name = "iniconfig" },
+    { name = "packaging" },
+    { name = "pluggy" },
+    { name = "pygments" },
+    { name = "tomli", marker = "python_full_version < '3.11'" },
+]
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/07/56/f013048ac4bc4c1d9be45afd4ab209ea62822fb1598f40687e6bf45dcea4/pytest-9.0.1.tar.gz", hash = "sha256:3e9c069ea73583e255c3b21cf46b8d3c56f6e3a1a8f6da94ccb0fcf57b9d73c8", size = 1564125, upload-time = "2025-11-12T13:05:09.333Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/0b/8b/6300fb80f858cda1c51ffa17075df5d846757081d11ab4aa35cef9e6258b/pytest-9.0.1-py3-none-any.whl", hash = "sha256:67be0030d194df2dfa7b556f2e56fb3c3315bd5c8822c6951162b92b32ce7dad", size = 373668, upload-time = "2025-11-12T13:05:07.379Z" },
+]
+
+[[package]]
+name = "ragflow-cli"
+version = "0.22.1"
+source = { virtual = "." }
+dependencies = [
+    { name = "beartype" },
+    { name = "lark" },
+    { name = "pycryptodomex" },
+    { name = "requests" },
+]
+
+[package.dev-dependencies]
+test = [
+    { name = "pytest" },
+    { name = "requests" },
+    { name = "requests-toolbelt" },
+]
+
+[package.metadata]
+requires-dist = [
+    { name = "beartype", specifier = ">=0.20.0,<1.0.0" },
+    { name = "lark", specifier = ">=1.1.0" },
+    { name = "pycryptodomex", specifier = ">=3.10.0" },
+    { name = "requests", specifier = ">=2.30.0,<3.0.0" },
+]
+
+[package.metadata.requires-dev]
+test = [
+    { name = "pytest", specifier = ">=8.3.5" },
+    { name = "requests", specifier = ">=2.32.3" },
+    { name = "requests-toolbelt", specifier = ">=1.0.0" },
+]
+
+[[package]]
+name = "requests"
+version = "2.32.5"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+dependencies = [
+    { name = "certifi" },
+    { name = "charset-normalizer" },
+    { name = "idna" },
+    { name = "urllib3" },
+]
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/c9/74/b3ff8e6c8446842c3f5c837e9c3dfcfe2018ea6ecef224c710c85ef728f4/requests-2.32.5.tar.gz", hash = "sha256:dbba0bac56e100853db0ea71b82b4dfd5fe2bf6d3754a8893c3af500cec7d7cf", size = 134517, upload-time = "2025-08-18T20:46:02.573Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/1e/db/4254e3eabe8020b458f1a747140d32277ec7a271daf1d235b70dc0b4e6e3/requests-2.32.5-py3-none-any.whl", hash = "sha256:2462f94637a34fd532264295e186976db0f5d453d1cdd31473c85a6a161affb6", size = 64738, upload-time = "2025-08-18T20:46:00.542Z" },
+]
+
+[[package]]
+name = "requests-toolbelt"
+version = "1.0.0"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+dependencies = [
+    { name = "requests" },
+]
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f3/61/d7545dafb7ac2230c70d38d31cbfe4cc64f7144dc41f6e4e4b78ecd9f5bb/requests-toolbelt-1.0.0.tar.gz", hash = "sha256:7681a0a3d047012b5bdc0ee37d7f8f07ebe76ab08caeccfc3921ce23c88d5bc6", size = 206888, upload-time = "2023-05-01T04:11:33.229Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/3f/51/d4db610ef29373b879047326cbf6fa98b6c1969d6f6dc423279de2b1be2c/requests_toolbelt-1.0.0-py2.py3-none-any.whl", hash = "sha256:cccfdd665f0a24fcf4726e690f65639d272bb0637b9b92dfd91a5568ccf6bd06", size = 54481, upload-time = "2023-05-01T04:11:28.427Z" },
+]
+
+[[package]]
+name = "tomli"
+version = "2.3.0"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/52/ed/3f73f72945444548f33eba9a87fc7a6e969915e7b1acc8260b30e1f76a2f/tomli-2.3.0.tar.gz", hash = "sha256:64be704a875d2a59753d80ee8a533c3fe183e3f06807ff7dc2232938ccb01549", size = 17392, upload-time = "2025-10-08T22:01:47.119Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/b3/2e/299f62b401438d5fe1624119c723f5d877acc86a4c2492da405626665f12/tomli-2.3.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:88bd15eb972f3664f5ed4b57c1634a97153b4bac4479dcb6a495f41921eb7f45", size = 153236, upload-time = "2025-10-08T22:01:00.137Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/86/7f/d8fffe6a7aefdb61bced88fcb5e280cfd71e08939da5894161bd71bea022/tomli-2.3.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:883b1c0d6398a6a9d29b508c331fa56adbcdff647f6ace4dfca0f50e90dfd0ba", size = 148084, upload-time = "2025-10-08T22:01:01.63Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/47/5c/24935fb6a2ee63e86d80e4d3b58b222dafaf438c416752c8b58537c8b89a/tomli-2.3.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d1381caf13ab9f300e30dd8feadb3de072aeb86f1d34a8569453ff32a7dea4bf", size = 234832, upload-time = "2025-10-08T22:01:02.543Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/89/da/75dfd804fc11e6612846758a23f13271b76d577e299592b4371a4ca4cd09/tomli-2.3.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a0e285d2649b78c0d9027570d4da3425bdb49830a6156121360b3f8511ea3441", size = 242052, upload-time = "2025-10-08T22:01:03.836Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/70/8c/f48ac899f7b3ca7eb13af73bacbc93aec37f9c954df3c08ad96991c8c373/tomli-2.3.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:0a154a9ae14bfcf5d8917a59b51ffd5a3ac1fd149b71b47a3a104ca4edcfa845", size = 239555, upload-time = "2025-10-08T22:01:04.834Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/ba/28/72f8afd73f1d0e7829bfc093f4cb98ce0a40ffc0cc997009ee1ed94ba705/tomli-2.3.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:74bf8464ff93e413514fefd2be591c3b0b23231a77f901db1eb30d6f712fc42c", size = 245128, upload-time = "2025-10-08T22:01:05.84Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/b6/eb/a7679c8ac85208706d27436e8d421dfa39d4c914dcf5fa8083a9305f58d9/tomli-2.3.0-cp311-cp311-win32.whl", hash = "sha256:00b5f5d95bbfc7d12f91ad8c593a1659b6387b43f054104cda404be6bda62456", size = 96445, upload-time = "2025-10-08T22:01:06.896Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/0a/fe/3d3420c4cb1ad9cb462fb52967080575f15898da97e21cb6f1361d505383/tomli-2.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:4dc4ce8483a5d429ab602f111a93a6ab1ed425eae3122032db7e9acf449451be", size = 107165, upload-time = "2025-10-08T22:01:08.107Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/ff/b7/40f36368fcabc518bb11c8f06379a0fd631985046c038aca08c6d6a43c6e/tomli-2.3.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:d7d86942e56ded512a594786a5ba0a5e521d02529b3826e7761a05138341a2ac", size = 154891, upload-time = "2025-10-08T22:01:09.082Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f9/3f/d9dd692199e3b3aab2e4e4dd948abd0f790d9ded8cd10cbaae276a898434/tomli-2.3.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:73ee0b47d4dad1c5e996e3cd33b8a76a50167ae5f96a2607cbe8cc773506ab22", size = 148796, upload-time = "2025-10-08T22:01:10.266Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/60/83/59bff4996c2cf9f9387a0f5a3394629c7efa5ef16142076a23a90f1955fa/tomli-2.3.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:792262b94d5d0a466afb5bc63c7daa9d75520110971ee269152083270998316f", size = 242121, upload-time = "2025-10-08T22:01:11.332Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/45/e5/7c5119ff39de8693d6baab6c0b6dcb556d192c165596e9fc231ea1052041/tomli-2.3.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:4f195fe57ecceac95a66a75ac24d9d5fbc98ef0962e09b2eddec5d39375aae52", size = 250070, upload-time = "2025-10-08T22:01:12.498Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/45/12/ad5126d3a278f27e6701abde51d342aa78d06e27ce2bb596a01f7709a5a2/tomli-2.3.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e31d432427dcbf4d86958c184b9bfd1e96b5b71f8eb17e6d02531f434fd335b8", size = 245859, upload-time = "2025-10-08T22:01:13.551Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/fb/a1/4d6865da6a71c603cfe6ad0e6556c73c76548557a8d658f9e3b142df245f/tomli-2.3.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:7b0882799624980785240ab732537fcfc372601015c00f7fc367c55308c186f6", size = 250296, upload-time = "2025-10-08T22:01:14.614Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/a0/b7/a7a7042715d55c9ba6e8b196d65d2cb662578b4d8cd17d882d45322b0d78/tomli-2.3.0-cp312-cp312-win32.whl", hash = "sha256:ff72b71b5d10d22ecb084d345fc26f42b5143c5533db5e2eaba7d2d335358876", size = 97124, upload-time = "2025-10-08T22:01:15.629Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/06/1e/f22f100db15a68b520664eb3328fb0ae4e90530887928558112c8d1f4515/tomli-2.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:1cb4ed918939151a03f33d4242ccd0aa5f11b3547d0cf30f7c74a408a5b99878", size = 107698, upload-time = "2025-10-08T22:01:16.51Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/77/b8/0135fadc89e73be292b473cb820b4f5a08197779206b33191e801feeae40/tomli-2.3.0-py3-none-any.whl", hash = "sha256:e95b1af3c5b07d9e643909b5abbec77cd9f1217e6d0bca72b0234736b9fb1f1b", size = 14408, upload-time = "2025-10-08T22:01:46.04Z" },
+]
+
+[[package]]
+name = "typing-extensions"
+version = "4.15.0"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/72/94/1a15dd82efb362ac84269196e94cf00f187f7ed21c242792a923cdb1c61f/typing_extensions-4.15.0.tar.gz", hash = "sha256:0cea48d173cc12fa28ecabc3b837ea3cf6f38c6d1136f85cbaaf598984861466", size = 109391, upload-time = "2025-08-25T13:49:26.313Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/18/67/36e9267722cc04a6b9f15c7f3441c2363321a3ea07da7ae0c0707beb2a9c/typing_extensions-4.15.0-py3-none-any.whl", hash = "sha256:f0fa19c6845758ab08074a0cfa8b7aecb71c999ca73d62883bc25cc018c4e548", size = 44614, upload-time = "2025-08-25T13:49:24.86Z" },
+]
+
+[[package]]
+name = "urllib3"
+version = "2.5.0"
+source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/15/22/9ee70a2574a4f4599c47dd506532914ce044817c7752a79b6a51286319bc/urllib3-2.5.0.tar.gz", hash = "sha256:3fc47733c7e419d4bc3f6b3dc2b4f890bb743906a30d56ba4a5bfa4bbff92760", size = 393185, upload-time = "2025-06-18T14:07:41.644Z" }
+wheels = [
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/a7/c2/fe1e52489ae3122415c51f387e221dd0773709bad6c6cdaa599e8a2c5185/urllib3-2.5.0-py3-none-any.whl", hash = "sha256:e6b01673c0fa6a13e374b50871808eb3bf7046c4b125b216f6bf1cc604cff0dc", size = 129795, upload-time = "2025-06-18T14:07:40.39Z" },
+]

admin/pyproject.toml

@@ -1,24 +0,0 @@
-[project]
-name = "ragflow-cli"
-version = "0.21.0.dev2"
-description = "Admin Service's client of [RAGFlow](https://github.com/infiniflow/ragflow). The Admin Service provides user management and system monitoring. "
-authors = [{ name = "Lynn", email = "lynn_inf@hotmail.com" }]
-license = { text = "Apache License, Version 2.0" }
-readme = "README.md"
-requires-python = ">=3.10,<3.13"
-dependencies = [
-    "requests>=2.30.0,<3.0.0",
-    "beartype>=0.18.5,<0.19.0",
-    "pycryptodomex>=3.10.0",
-    "lark>=1.1.0",
-]
-
-[dependency-groups]
-test = [
-    "pytest>=8.3.5",
-    "requests>=2.32.3",
-    "requests-toolbelt>=1.0.0",
-]
-
-[project.scripts]
-ragflow-cli = "ragflow_cli.admin_client:main"

admin/server/admin_server.py

@@ -20,17 +20,25 @@ import logging
 import time
 import threading
 import traceback
-from werkzeug.serving import run_simple
+import faulthandler
+
 from flask import Flask
+from flask_login import LoginManager
+from werkzeug.serving import run_simple
 from routes import admin_bp
-from api.utils.log_utils import init_root_logger
+from common.log_utils import init_root_logger
-from api.constants import SERVICE_CONF
+from common.constants import SERVICE_CONF
-from api import settings
+from common.config_utils import show_configs
-from admin.server.config import load_configurations, SERVICE_CONFIGS
+from common import settings
+from config import load_configurations, SERVICE_CONFIGS
+from auth import init_default_admin, setup_auth
+from flask_session import Session
+from common.versions import get_ragflow_version
 
 stop_event = threading.Event()
 
 if __name__ == '__main__':
+    faulthandler.enable()
     init_root_logger("admin_service")
     logging.info(r"""
         ____  ___   ______________                 ___       __          _     
@@ -42,7 +50,19 @@ if __name__ == '__main__':
 
     app = Flask(__name__)
     app.register_blueprint(admin_bp)
+    app.config["SESSION_PERMANENT"] = False
+    app.config["SESSION_TYPE"] = "filesystem"
+    app.config["MAX_CONTENT_LENGTH"] = int(
+        os.environ.get("MAX_CONTENT_LENGTH", 1024 * 1024 * 1024)
+    )
+    Session(app)
+    logging.info(f'RAGFlow version: {get_ragflow_version()}')
+    show_configs()
+    login_manager = LoginManager()
+    login_manager.init_app(app)
     settings.init_settings()
+    setup_auth(login_manager)
+    init_default_admin()
     SERVICE_CONFIGS.configs = load_configurations(SERVICE_CONF)
 
     try:
@@ -52,7 +72,7 @@ if __name__ == '__main__':
             port=9381,
             application=app,
             threaded=True,
-            use_reloader=True,
+            use_reloader=False,
             use_debugger=True,
         )
     except Exception:

admin/server/auth.py

@@ -18,11 +18,119 @@
 import logging
 import uuid
 from functools import wraps
-from flask import request, jsonify
+from datetime import datetime
 
-from api.common.exceptions import AdminException
+from flask import jsonify, request
-from api.db.init_data import encode_to_base64
+from flask_login import current_user, login_user
+from itsdangerous.url_safe import URLSafeTimedSerializer as Serializer
+
+from api.common.exceptions import AdminException, UserNotFoundError
+from api.common.base64 import encode_to_base64
 from api.db.services import UserService
+from common.constants import ActiveEnum, StatusEnum
+from api.utils.crypt import decrypt
+from common.misc_utils import get_uuid
+from common.time_utils import current_timestamp, datetime_format, get_format_time
+from common.connection_utils import sync_construct_response
+from common import settings
+
+
+def setup_auth(login_manager):
+    @login_manager.request_loader
+    def load_user(web_request):
+        jwt = Serializer(secret_key=settings.SECRET_KEY)
+        authorization = web_request.headers.get("Authorization")
+        if authorization:
+            try:
+                access_token = str(jwt.loads(authorization))
+
+                if not access_token or not access_token.strip():
+                    logging.warning("Authentication attempt with empty access token")
+                    return None
+
+                # Access tokens should be UUIDs (32 hex characters)
+                if len(access_token.strip()) < 32:
+                    logging.warning(f"Authentication attempt with invalid token format: {len(access_token)} chars")
+                    return None
+
+                user = UserService.query(
+                    access_token=access_token, status=StatusEnum.VALID.value
+                )
+                if user:
+                    if not user[0].access_token or not user[0].access_token.strip():
+                        logging.warning(f"User {user[0].email} has empty access_token in database")
+                        return None
+                    return user[0]
+                else:
+                    return None
+            except Exception as e:
+                logging.warning(f"load_user got exception {e}")
+                return None
+        else:
+            return None
+
+
+def init_default_admin():
+    # Verify that at least one active admin user exists. If not, create a default one.
+    users = UserService.query(is_superuser=True)
+    if not users:
+        default_admin = {
+            "id": uuid.uuid1().hex,
+            "password": encode_to_base64("admin"),
+            "nickname": "admin",
+            "is_superuser": True,
+            "email": "admin@ragflow.io",
+            "creator": "system",
+            "status": "1",
+        }
+        if not UserService.save(**default_admin):
+            raise AdminException("Can't init admin.", 500)
+    elif not any([u.is_active == ActiveEnum.ACTIVE.value for u in users]):
+        raise AdminException("No active admin. Please update 'is_active' in db manually.", 500)
+
+
+def check_admin_auth(func):
+    @wraps(func)
+    def wrapper(*args, **kwargs):
+        user = UserService.filter_by_id(current_user.id)
+        if not user:
+            raise UserNotFoundError(current_user.email)
+        if not user.is_superuser:
+            raise AdminException("Not admin", 403)
+        if user.is_active == ActiveEnum.INACTIVE.value:
+            raise AdminException(f"User {current_user.email} inactive", 403)
+
+        return func(*args, **kwargs)
+
+    return wrapper
+
+
+def login_admin(email: str, password: str):
+    """
+    :param email: admin email
+    :param password: string before decrypt
+    """
+    users = UserService.query(email=email)
+    if not users:
+        raise UserNotFoundError(email)
+    psw = decrypt(password)
+    user = UserService.query_user(email, psw)
+    if not user:
+        raise AdminException("Email and password do not match!")
+    if not user.is_superuser:
+        raise AdminException("Not admin", 403)
+    if user.is_active == ActiveEnum.INACTIVE.value:
+        raise AdminException(f"User {email} inactive", 403)
+
+    resp = user.to_json()
+    user.access_token = get_uuid()
+    login_user(user)
+    user.update_time = (current_timestamp(),)
+    user.update_date = (datetime_format(datetime.now()),)
+    user.last_login_time = get_format_time()
+    user.save()
+    msg = "Welcome back!"
+    return sync_construct_response(data=resp, auth=user.get_id(), message=msg)
 
 
 def check_admin(username: str, password: str):
@@ -61,12 +169,18 @@ def login_verify(f):
 
         username = auth.parameters['username']
         password = auth.parameters['password']
-        # TODO: to check the username and password from DB
+        try:
-        if check_admin(username, password) is False:
+            if not check_admin(username, password):
+                return jsonify({
+                    "code": 500,
+                    "message": "Access denied",
+                    "data": None
+                }), 200
+        except Exception as e:
+            error_msg = str(e)
             return jsonify({
-                "code": 403,
+                "code": 500,
-                "message": "Access denied",
+                "message": error_msg
-                "data": None
             }), 200
 
         return f(*args, **kwargs)

admin/server/config.py

@@ -21,11 +21,26 @@ from enum import Enum
 
 from pydantic import BaseModel
 from typing import Any
-from api.utils.configs import read_config
+from common.config_utils import read_config
 from urllib.parse import urlparse
 
 
+class BaseConfig(BaseModel):
+    id: int
+    name: str
+    host: str
+    port: int
+    service_type: str
+    detail_func_name: str
+
+    def to_dict(self) -> dict[str, Any]:
+        return {'id': self.id, 'name': self.name, 'host': self.host, 'port': self.port,
+                'service_type': self.service_type}
+
+
 class ServiceConfigs:
+    configs = list[BaseConfig]
+
     def __init__(self):
         self.configs = []
         self.lock = threading.Lock()
@@ -43,19 +58,6 @@ class ServiceType(Enum):
     FILE_STORE = "file_store"
 
 
-class BaseConfig(BaseModel):
-    id: int
-    name: str
-    host: str
-    port: int
-    service_type: str
-    detail_func_name: str
-
-    def to_dict(self) -> dict[str, Any]:
-        return {'id': self.id, 'name': self.name, 'host': self.host, 'port': self.port,
-                'service_type': self.service_type}
-
-
 class MetaConfig(BaseConfig):
     meta_type: str
 
@@ -181,11 +183,13 @@ class RAGFlowServerConfig(BaseConfig):
 
 
 class TaskExecutorConfig(BaseConfig):
+    message_queue_type: str
 
     def to_dict(self) -> dict[str, Any]:
         result = super().to_dict()
         if 'extra' not in result:
             result['extra'] = dict()
+        result['extra']['message_queue_type'] = self.message_queue_type
         return result
 
 
@@ -223,13 +227,14 @@ def load_configurations(config_path: str) -> list[BaseConfig]:
     ragflow_count = 0
     id_count = 0
     for k, v in raw_configs.items():
-        match (k):
+        match k:
             case "ragflow":
                 name: str = f'ragflow_{ragflow_count}'
                 host: str = v['host']
                 http_port: int = v['http_port']
                 config = RAGFlowServerConfig(id=id_count, name=name, host=host, port=http_port,
-                                             service_type="ragflow_server", detail_func_name="check_ragflow_server_alive")
+                                             service_type="ragflow_server",
+                                             detail_func_name="check_ragflow_server_alive")
                 configurations.append(config)
                 id_count += 1
             case "es":
@@ -254,7 +259,8 @@ def load_configurations(config_path: str) -> list[BaseConfig]:
                 host = parts[0]
                 port = int(parts[1])
                 database: str = v.get('db_name', 'default_db')
-                config = InfinityConfig(id=id_count, name=name, host=host, port=port, service_type="retrieval", retrieval_type="infinity",
+                config = InfinityConfig(id=id_count, name=name, host=host, port=port, service_type="retrieval",
+                                        retrieval_type="infinity",
                                         db_name=database, detail_func_name="get_infinity_status")
                 configurations.append(config)
                 id_count += 1
@@ -266,7 +272,8 @@ def load_configurations(config_path: str) -> list[BaseConfig]:
                 port = int(parts[1])
                 user = v.get('user')
                 password = v.get('password')
-                config = MinioConfig(id=id_count, name=name, host=host, port=port, user=user, password=password, service_type="file_store",
+                config = MinioConfig(id=id_count, name=name, host=host, port=port, user=user, password=password,
+                                     service_type="file_store",
                                      store_type="minio", detail_func_name="check_minio_alive")
                 configurations.append(config)
                 id_count += 1
@@ -294,6 +301,15 @@ def load_configurations(config_path: str) -> list[BaseConfig]:
                 id_count += 1
             case "admin":
                 pass
+            case "task_executor":
+                name: str = 'task_executor'
+                host: str = v.get('host', '')
+                port: int = v.get('port', 0)
+                message_queue_type: str = v.get('message_queue_type')
+                config = TaskExecutorConfig(id=id_count, name=name, host=host, port=port, message_queue_type=message_queue_type,
+                                            service_type="task_executor", detail_func_name="check_task_executor_alive")
+                configurations.append(config)
+                id_count += 1
             case _:
                 logging.warning(f"Unknown configuration key: {k}")
                 continue

admin/server/responses.py

@@ -13,8 +13,6 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-
-
 from flask import jsonify
 
 

admin/server/roles.py

@@ -0,0 +1,76 @@
+#
+#  Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+import logging
+
+from typing import Dict, Any
+
+from api.common.exceptions import AdminException
+
+
+class RoleMgr:
+    @staticmethod
+    def create_role(role_name: str, description: str):
+        error_msg = f"not implement: create role: {role_name}, description: {description}"
+        logging.error(error_msg)
+        raise AdminException(error_msg)
+
+    @staticmethod
+    def update_role_description(role_name: str, description: str) -> Dict[str, Any]:
+        error_msg = f"not implement: update role: {role_name} with description: {description}"
+        logging.error(error_msg)
+        raise AdminException(error_msg)
+
+    @staticmethod
+    def delete_role(role_name: str) -> Dict[str, Any]:
+        error_msg = f"not implement: drop role: {role_name}"
+        logging.error(error_msg)
+        raise AdminException(error_msg)
+
+    @staticmethod
+    def list_roles() -> Dict[str, Any]:
+        error_msg = "not implement: list roles"
+        logging.error(error_msg)
+        raise AdminException(error_msg)
+
+    @staticmethod
+    def get_role_permission(role_name: str) -> Dict[str, Any]:
+        error_msg = f"not implement: show role {role_name}"
+        logging.error(error_msg)
+        raise AdminException(error_msg)
+
+    @staticmethod
+    def grant_role_permission(role_name: str, actions: list, resource: str) -> Dict[str, Any]:
+        error_msg = f"not implement: grant role {role_name} actions: {actions} on {resource}"
+        logging.error(error_msg)
+        raise AdminException(error_msg)
+
+    @staticmethod
+    def revoke_role_permission(role_name: str, actions: list, resource: str) -> Dict[str, Any]:
+        error_msg = f"not implement: revoke role {role_name} actions: {actions} on {resource}"
+        logging.error(error_msg)
+        raise AdminException(error_msg)
+
+    @staticmethod
+    def update_user_role(user_name: str, role_name: str) -> Dict[str, Any]:
+        error_msg = f"not implement: update user role: {user_name} to role {role_name}"
+        logging.error(error_msg)
+        raise AdminException(error_msg)
+
+    @staticmethod
+    def get_user_permission(user_name: str) -> Dict[str, Any]:
+        error_msg = f"not implement: get user permission: {user_name}"
+        logging.error(error_msg)
+        raise AdminException(error_msg)

admin/server/routes.py

@@ -14,17 +14,45 @@
 #  limitations under the License.
 #
 
+import secrets
 
 from flask import Blueprint, request
+from flask_login import current_user, login_required, logout_user
 
-from admin.server.auth import login_verify
+from auth import login_verify, login_admin, check_admin_auth
 from responses import success_response, error_response
 from services import UserMgr, ServiceMgr, UserServiceMgr
+from roles import RoleMgr
 from api.common.exceptions import AdminException
+from common.versions import get_ragflow_version
 
 admin_bp = Blueprint('admin', __name__, url_prefix='/api/v1/admin')
 
 
+@admin_bp.route('/login', methods=['POST'])
+def login():
+    if not request.json:
+        return error_response('Authorize admin failed.' ,400)
+    try:
+        email = request.json.get("email", "")
+        password = request.json.get("password", "")
+        return login_admin(email, password)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/logout', methods=['GET'])
+@login_required
+def logout():
+    try:
+        current_user.access_token = f"INVALID_{secrets.token_hex(16)}"
+        current_user.save()
+        logout_user()
+        return success_response(True)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
 @admin_bp.route('/auth', methods=['GET'])
 @login_verify
 def auth_admin():
@@ -35,7 +63,8 @@ def auth_admin():
 
 
 @admin_bp.route('/users', methods=['GET'])
-@login_verify
+@login_required
+@check_admin_auth
 def list_users():
     try:
         users = UserMgr.get_all_users()
@@ -45,7 +74,8 @@ def list_users():
 
 
 @admin_bp.route('/users', methods=['POST'])
-@login_verify
+@login_required
+@check_admin_auth
 def create_user():
     try:
         data = request.get_json()
@@ -71,7 +101,8 @@ def create_user():
 
 
 @admin_bp.route('/users/<username>', methods=['DELETE'])
-@login_verify
+@login_required
+@check_admin_auth
 def delete_user(username):
     try:
         res = UserMgr.delete_user(username)
@@ -87,7 +118,8 @@ def delete_user(username):
 
 
 @admin_bp.route('/users/<username>/password', methods=['PUT'])
-@login_verify
+@login_required
+@check_admin_auth
 def change_password(username):
     try:
         data = request.get_json()
@@ -105,7 +137,8 @@ def change_password(username):
 
 
 @admin_bp.route('/users/<username>/activate', methods=['PUT'])
-@login_verify
+@login_required
+@check_admin_auth
 def alter_user_activate_status(username):
     try:
         data = request.get_json()
@@ -121,7 +154,8 @@ def alter_user_activate_status(username):
 
 
 @admin_bp.route('/users/<username>', methods=['GET'])
-@login_verify
+@login_required
+@check_admin_auth
 def get_user_details(username):
     try:
         user_details = UserMgr.get_user_details(username)
@@ -134,7 +168,8 @@ def get_user_details(username):
 
 
 @admin_bp.route('/users/<username>/datasets', methods=['GET'])
-@login_verify
+@login_required
+@check_admin_auth
 def get_user_datasets(username):
     try:
         datasets_list = UserServiceMgr.get_user_datasets(username)
@@ -147,7 +182,8 @@ def get_user_datasets(username):
 
 
 @admin_bp.route('/users/<username>/agents', methods=['GET'])
-@login_verify
+@login_required
+@check_admin_auth
 def get_user_agents(username):
     try:
         agents_list = UserServiceMgr.get_user_agents(username)
@@ -160,7 +196,8 @@ def get_user_agents(username):
 
 
 @admin_bp.route('/services', methods=['GET'])
-@login_verify
+@login_required
+@check_admin_auth
 def get_services():
     try:
         services = ServiceMgr.get_all_services()
@@ -170,7 +207,8 @@ def get_services():
 
 
 @admin_bp.route('/service_types/<service_type>', methods=['GET'])
-@login_verify
+@login_required
+@check_admin_auth
 def get_services_by_type(service_type_str):
     try:
         services = ServiceMgr.get_services_by_type(service_type_str)
@@ -180,7 +218,8 @@ def get_services_by_type(service_type_str):
 
 
 @admin_bp.route('/services/<service_id>', methods=['GET'])
-@login_verify
+@login_required
+@check_admin_auth
 def get_service(service_id):
     try:
         services = ServiceMgr.get_service_details(service_id)
@@ -190,7 +229,8 @@ def get_service(service_id):
 
 
 @admin_bp.route('/services/<service_id>', methods=['DELETE'])
-@login_verify
+@login_required
+@check_admin_auth
 def shutdown_service(service_id):
     try:
         services = ServiceMgr.shutdown_service(service_id)
@@ -200,10 +240,143 @@ def shutdown_service(service_id):
 
 
 @admin_bp.route('/services/<service_id>', methods=['PUT'])
-@login_verify
+@login_required
+@check_admin_auth
 def restart_service(service_id):
     try:
         services = ServiceMgr.restart_service(service_id)
         return success_response(services)
     except Exception as e:
         return error_response(str(e), 500)
+
+
+@admin_bp.route('/roles', methods=['POST'])
+@login_required
+@check_admin_auth
+def create_role():
+    try:
+        data = request.get_json()
+        if not data or 'role_name' not in data:
+            return error_response("Role name is required", 400)
+        role_name: str = data['role_name']
+        description: str = data['description']
+        res = RoleMgr.create_role(role_name, description)
+        return success_response(res)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/roles/<role_name>', methods=['PUT'])
+@login_required
+@check_admin_auth
+def update_role(role_name: str):
+    try:
+        data = request.get_json()
+        if not data or 'description' not in data:
+            return error_response("Role description is required", 400)
+        description: str = data['description']
+        res = RoleMgr.update_role_description(role_name, description)
+        return success_response(res)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/roles/<role_name>', methods=['DELETE'])
+@login_required
+@check_admin_auth
+def delete_role(role_name: str):
+    try:
+        res = RoleMgr.delete_role(role_name)
+        return success_response(res)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/roles', methods=['GET'])
+@login_required
+@check_admin_auth
+def list_roles():
+    try:
+        res = RoleMgr.list_roles()
+        return success_response(res)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/roles/<role_name>/permission', methods=['GET'])
+@login_required
+@check_admin_auth
+def get_role_permission(role_name: str):
+    try:
+        res = RoleMgr.get_role_permission(role_name)
+        return success_response(res)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/roles/<role_name>/permission', methods=['POST'])
+@login_required
+@check_admin_auth
+def grant_role_permission(role_name: str):
+    try:
+        data = request.get_json()
+        if not data or 'actions' not in data or 'resource' not in data:
+            return error_response("Permission is required", 400)
+        actions: list = data['actions']
+        resource: str = data['resource']
+        res = RoleMgr.grant_role_permission(role_name, actions, resource)
+        return success_response(res)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/roles/<role_name>/permission', methods=['DELETE'])
+@login_required
+@check_admin_auth
+def revoke_role_permission(role_name: str):
+    try:
+        data = request.get_json()
+        if not data or 'actions' not in data or 'resource' not in data:
+            return error_response("Permission is required", 400)
+        actions: list = data['actions']
+        resource: str = data['resource']
+        res = RoleMgr.revoke_role_permission(role_name, actions, resource)
+        return success_response(res)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/users/<user_name>/role', methods=['PUT'])
+@login_required
+@check_admin_auth
+def update_user_role(user_name: str):
+    try:
+        data = request.get_json()
+        if not data or 'role_name' not in data:
+            return error_response("Role name is required", 400)
+        role_name: str = data['role_name']
+        res = RoleMgr.update_user_role(user_name, role_name)
+        return success_response(res)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/users/<user_name>/permission', methods=['GET'])
+@login_required
+@check_admin_auth
+def get_user_permission(user_name: str):
+    try:
+        res = RoleMgr.get_user_permission(user_name)
+        return success_response(res)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+@admin_bp.route('/version', methods=['GET'])
+@login_required
+@check_admin_auth
+def show_version():
+    try:
+        res = {"version": get_ragflow_version()}
+        return success_response(res)
+    except Exception as e:
+        return error_response(str(e), 500)

admin/server/services.py

@@ -13,11 +13,10 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-
+import logging
-
 import re
 from werkzeug.security import check_password_hash
-from api.db import ActiveEnum
+from common.constants import ActiveEnum
 from api.db.services import UserService
 from api.db.joint_services.user_account_service import create_new_user, delete_user_data
 from api.db.services.canvas_service import UserCanvasService
@@ -27,7 +26,7 @@ from api.utils.crypt import decrypt
 from api.utils import health_utils
 
 from api.common.exceptions import AdminException, UserAlreadyExistsError, UserNotFoundError
-from admin.server.config import SERVICE_CONFIGS
+from config import SERVICE_CONFIGS
 
 
 class UserMgr:
@@ -36,8 +35,13 @@ class UserMgr:
         users = UserService.get_all_users()
         result = []
         for user in users:
-            result.append({'email': user.email, 'nickname': user.nickname, 'create_date': user.create_date,
+            result.append({
-                           'is_active': user.is_active})
+                'email': user.email,
+                'nickname': user.nickname,
+                'create_date': user.create_date,
+                'is_active': user.is_active,
+                'is_superuser': user.is_superuser,
+            })
         return result
 
     @staticmethod
@@ -47,10 +51,10 @@ class UserMgr:
         result = []
         for user in users:
             result.append({
+                'avatar': user.avatar,
                 'email': user.email,
                 'language': user.language,
                 'last_login_time': user.last_login_time,
-                'is_authenticated': user.is_authenticated,
                 'is_active': user.is_active,
                 'is_anonymous': user.is_anonymous,
                 'login_channel': user.login_channel,
@@ -166,8 +170,8 @@ class UserServiceMgr:
         return [{
             'title': r['title'],
             'permission': r['permission'],
-            'canvas_type': r['canvas_type'],
+            'canvas_category': r['canvas_category'].split('_')[0],
-            'canvas_category': r['canvas_category']
+            'avatar': r['avatar']
         } for r in res]
 
 
@@ -181,12 +185,17 @@ class ServiceMgr:
             config_dict = config.to_dict()
             try:
                 service_detail = ServiceMgr.get_service_details(service_id)
-                if service_detail['alive']:
+                if "status" in service_detail:
-                    config_dict['status'] = 'Alive'
+                    config_dict['status'] = service_detail['status']
                 else:
-                    config_dict['status'] = 'Timeout'
+                    config_dict['status'] = 'timeout'
-            except Exception:
+            except Exception as e:
-                config_dict['status'] = 'Timeout'
+                logging.warning(f"Can't get service details, error: {e}")
+                config_dict['status'] = 'timeout'
+            if not config_dict['host']:
+                config_dict['host'] = '-'
+            if not config_dict['port']:
+                config_dict['port'] = '-'
             result.append(config_dict)
         return result
 
@@ -196,17 +205,13 @@ class ServiceMgr:
 
     @staticmethod
     def get_service_details(service_id: int):
-        service_id = int(service_id)
+        service_idx = int(service_id)
         configs = SERVICE_CONFIGS.configs
-        service_config_mapping = {
+        if service_idx < 0 or service_idx >= len(configs):
-            c.id: {
+            raise AdminException(f"invalid service_index: {service_idx}")
-                'name': c.name,
+
-                'detail_func_name': c.detail_func_name
+        service_config = configs[service_idx]
-            } for c in configs
+        service_info = {'name': service_config.name, 'detail_func_name': service_config.detail_func_name}
-        }
-        service_info = service_config_mapping.get(service_id, {})
-        if not service_info:
-            raise AdminException(f"Invalid service_id: {service_id}")
 
         detail_func = getattr(health_utils, service_info.get('detail_func_name'))
         res = detail_func()

agent/canvas.py

@@ -25,8 +25,9 @@ from typing import Any, Union, Tuple
 
 from agent.component import component_class
 from agent.component.base import ComponentBase
-from api.db.services.file_service import FileService
+from api.db.services.task_service import has_canceled
-from api.utils import get_uuid, hash_str2int
+from common.misc_utils import get_uuid, hash_str2int
+from common.exceptions import TaskCanceledException
 from rag.prompts.generator import chunks_format
 from rag.utils.redis_conn import REDIS_CONN
 
@@ -126,6 +127,7 @@ class Graph:
             self.components[k]["obj"].reset()
         try:
             REDIS_CONN.delete(f"{self.task_id}-logs")
+            REDIS_CONN.delete(f"{self.task_id}-cancel")
         except Exception as e:
             logging.exception(e)
 
@@ -153,6 +155,33 @@ class Graph:
     def get_tenant_id(self):
         return self._tenant_id
 
+    def get_value_with_variable(self,value: str) -> Any:
+        pat = re.compile(r"\{* *\{([a-zA-Z:0-9]+@[A-Za-z0-9_.]+|sys\.[A-Za-z0-9_.]+|env\.[A-Za-z0-9_.]+)\} *\}*")
+        out_parts = []
+        last = 0
+
+        for m in pat.finditer(value):
+            out_parts.append(value[last:m.start()])
+            key = m.group(1)
+            v = self.get_variable_value(key)
+            if v is None:
+                rep = ""
+            elif isinstance(v, partial):
+                buf = []
+                for chunk in v():
+                    buf.append(chunk)
+                rep = "".join(buf)
+            elif isinstance(v, str):
+                rep = v
+            else:
+                rep = json.dumps(v, ensure_ascii=False)
+
+            out_parts.append(rep)
+            last = m.end()
+
+        out_parts.append(value[last:])
+        return("".join(out_parts))
+
     def get_variable_value(self, exp: str) -> Any:
         exp = exp.strip("{").strip("}").strip(" ").strip("{").strip("}")
         if exp.find("@") < 0:
@@ -161,7 +190,86 @@ class Graph:
         cpn = self.get_component(cpn_id)
         if not cpn:
             raise Exception(f"Can't find variable: '{cpn_id}@{var_nm}'")
-        return cpn["obj"].output(var_nm)
+        parts = var_nm.split(".", 1)
+        root_key = parts[0]
+        rest = parts[1] if len(parts) > 1 else ""
+        root_val = cpn["obj"].output(root_key)
+
+        if not rest:
+            return root_val
+        return self.get_variable_param_value(root_val,rest)
+
+    def get_variable_param_value(self, obj: Any, path: str) -> Any:
+        cur = obj
+        if not path:
+            return cur
+        for key in path.split('.'):
+            if cur is None:
+                return None
+
+            if isinstance(cur, str):
+                try:
+                    cur = json.loads(cur)
+                except Exception:
+                    return None
+
+            if isinstance(cur, dict):
+                cur = cur.get(key)
+                continue
+
+            if isinstance(cur, (list, tuple)):
+                try:
+                    idx = int(key)
+                    cur = cur[idx]
+                except Exception:
+                    return None
+                continue
+
+            cur = getattr(cur, key, None)
+        return cur
+
+    def set_variable_value(self, exp: str,value):
+        exp = exp.strip("{").strip("}").strip(" ").strip("{").strip("}")
+        if exp.find("@") < 0:
+            self.globals[exp] = value
+            return
+        cpn_id, var_nm = exp.split("@")
+        cpn = self.get_component(cpn_id)
+        if not cpn:
+            raise Exception(f"Can't find variable: '{cpn_id}@{var_nm}'")
+        parts = var_nm.split(".", 1)
+        root_key = parts[0]
+        rest = parts[1] if len(parts) > 1 else ""
+        if not rest:
+            cpn["obj"].set_output(root_key, value)
+            return
+        root_val = cpn["obj"].output(root_key)
+        if not root_val:
+            root_val = {}
+        cpn["obj"].set_output(root_key, self.set_variable_param_value(root_val,rest,value))
+
+    def set_variable_param_value(self, obj: Any, path: str, value) -> Any:
+        cur = obj
+        keys = path.split('.')
+        if not path:
+            return value
+        for key in keys:
+            if key not in cur or not isinstance(cur[key], dict):
+                cur[key] = {}
+            cur = cur[key]
+        cur[keys[-1]] = value
+        return obj
+
+    def is_canceled(self) -> bool:
+        return has_canceled(self.task_id)
+
+    def cancel_task(self) -> bool:
+        try:
+            REDIS_CONN.set(f"{self.task_id}-cancel", "x")
+        except Exception as e:
+            logging.exception(e)
+            return False
+        return True
 
 
 class Canvas(Graph):
@@ -204,20 +312,21 @@ class Canvas(Graph):
             self.retrieval = []
             self.memory = []
         for k in self.globals.keys():
-            if isinstance(self.globals[k], str):
+            if k.startswith("sys.") or k.startswith("env."):
-                self.globals[k] = ""
+                if isinstance(self.globals[k], str):
-            elif isinstance(self.globals[k], int):
+                    self.globals[k] = ""
-                self.globals[k] = 0
+                elif isinstance(self.globals[k], int):
-            elif isinstance(self.globals[k], float):
+                    self.globals[k] = 0
-                self.globals[k] = 0
+                elif isinstance(self.globals[k], float):
-            elif isinstance(self.globals[k], list):
+                    self.globals[k] = 0
-                self.globals[k] = []
+                elif isinstance(self.globals[k], list):
-            elif isinstance(self.globals[k], dict):
+                    self.globals[k] = []
-                self.globals[k] = {}
+                elif isinstance(self.globals[k], dict):
-            else:
+                    self.globals[k] = {}
-                self.globals[k] = None
+                else:
+                    self.globals[k] = None
 
-    def run(self, **kwargs):
+    async def run(self, **kwargs):
         st = time.perf_counter()
         self.message_id = get_uuid()
         created_at = int(time.time())
@@ -225,6 +334,12 @@ class Canvas(Graph):
         for k, cpn in self.components.items():
             self.components[k]["obj"].reset(True)
 
+        if kwargs.get("webhook_payload"):
+            for k, cpn in self.components.items():
+                if self.components[k]["obj"].component_name.lower() == "webhook":
+                    for kk, vv in kwargs["webhook_payload"].items():
+                        self.components[k]["obj"].set_output(kk, vv)
+
         for k in kwargs.keys():
             if k in ["query", "user_id", "files"] and kwargs[k]:
                 if k == "files":
@@ -250,18 +365,37 @@ class Canvas(Graph):
             self.path.append("begin")
             self.retrieval.append({"chunks": [], "doc_aggs": []})
 
+        if self.is_canceled():
+            msg = f"Task {self.task_id} has been canceled before starting."
+            logging.info(msg)
+            raise TaskCanceledException(msg)
+
         yield decorate("workflow_started", {"inputs": kwargs.get("inputs")})
         self.retrieval.append({"chunks": {}, "doc_aggs": {}})
 
         def _run_batch(f, t):
+            if self.is_canceled():
+                msg = f"Task {self.task_id} has been canceled during batch execution."
+                logging.info(msg)
+                raise TaskCanceledException(msg)
+
             with ThreadPoolExecutor(max_workers=5) as executor:
                 thr = []
-                for i in range(f, t):
+                i = f
+                while i < t:
                     cpn = self.get_component_obj(self.path[i])
                     if cpn.component_name.lower() in ["begin", "userfillup"]:
                         thr.append(executor.submit(cpn.invoke, inputs=kwargs.get("inputs", {})))
+                        i += 1
                     else:
-                        thr.append(executor.submit(cpn.invoke, **cpn.get_input()))
+                        for _, ele in cpn.get_input_elements().items():
+                            if isinstance(ele, dict) and ele.get("_cpn_id") and ele.get("_cpn_id") not in self.path[:i] and self.path[0].lower().find("userfillup") < 0:
+                                self.path.pop(i)
+                                t -= 1
+                                break
+                        else:
+                            thr.append(executor.submit(cpn.invoke, **cpn.get_input()))
+                            i += 1
                 for t in thr:
                     t.result()
 
@@ -291,6 +425,7 @@ class Canvas(Graph):
                     "thoughts": self.get_component_thoughts(self.path[i])
                 })
             _run_batch(idx, to)
+            to = len(self.path)
             # post processing of components invocation
             for i in range(idx, to):
                 cpn = self.get_component(self.path[i])
@@ -313,6 +448,10 @@ class Canvas(Graph):
                     else:
                         yield decorate("message", {"content": cpn_obj.output("content")})
                         cite = re.search(r"\[ID:[ 0-9]+\]",  cpn_obj.output("content"))
+
+                    if isinstance(cpn_obj.output("attachment"), tuple):
+                        yield decorate("message", {"attachment": cpn_obj.output("attachment")})
+
                     yield decorate("message_end", {"reference": self.get_reference() if cite else None})
 
                     while partials:
@@ -385,9 +524,10 @@ class Canvas(Graph):
                 for c in path:
                     o = self.get_component_obj(c)
                     if o.component_name.lower() == "userfillup":
+                        o.invoke()
                         another_inputs.update(o.get_input_elements())
                         if o.get_param("enable_tips"):
-                            tips = o.get_param("tips")
+                            tips = o.output("tips")
                 self.path = path
                 yield decorate("user_inputs", {"inputs": another_inputs, "tips": tips})
                 return
@@ -401,6 +541,14 @@ class Canvas(Graph):
                            "created_at": st,
                        })
             self.history.append(("assistant", self.get_component_obj(self.path[-1]).output()))
+        elif "Task has been canceled" in self.error:
+            yield decorate("workflow_finished",
+                       {
+                           "inputs": kwargs.get("inputs"),
+                           "outputs": "Task has been canceled",
+                           "elapsed_time": time.perf_counter() - st,
+                           "created_at": st,
+                       })
 
     def is_reff(self, exp: str) -> bool:
         exp = exp.strip("{").strip("}")
@@ -443,6 +591,7 @@ class Canvas(Graph):
         return self.components[cpnnm]["obj"].get_input_elements()
 
     def get_files(self, files: Union[None, list[dict]]) -> list[str]:
+        from api.db.services.file_service import FileService
         if not files:
             return  []
         def image_to_base64(file):
@@ -509,4 +658,3 @@ class Canvas(Graph):
 
     def get_component_thoughts(self, cpn_id) -> str:
         return self.components.get(cpn_id)["obj"].thoughts()
-

agent/component/__init__.py

@@ -13,7 +13,6 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-
 import os
 import importlib
 import inspect
@@ -50,9 +49,10 @@ del _package_path, _import_submodules, _extract_classes_from_module
 
 
 def component_class(class_name):
-    for mdl in ["agent.component", "agent.tools", "rag.flow"]:
+    for module_name in ["agent.component", "agent.tools", "rag.flow"]:
         try:
-            return getattr(importlib.import_module(mdl), class_name)
+            return getattr(importlib.import_module(module_name), class_name)
         except Exception:
+            # logging.warning(f"Can't import module: {module_name}, error: {e}")
             pass
     assert False, f"Can't import {class_name}"

agent/component/agent_with_tools.py

@@ -27,10 +27,10 @@ from agent.tools.base import LLMToolPluginCallSession, ToolParamBase, ToolBase,
 from api.db.services.llm_service import LLMBundle
 from api.db.services.tenant_llm_service import TenantLLMService
 from api.db.services.mcp_server_service import MCPServerService
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 from rag.prompts.generator import next_step, COMPLETE_TASK, analyze_task, \
     citation_prompt, reflect, rank_memories, kb_prompt, citation_plus, full_question, message_fit_in
-from rag.utils.mcp_tool_call_conn import MCPToolCallSession, mcp_tool_metadata_to_openai_tool
+from common.mcp_tool_call_conn import MCPToolCallSession, mcp_tool_metadata_to_openai_tool
 from agent.component.llm import LLMParam, LLM
 
 
@@ -139,6 +139,9 @@ class Agent(LLM, ToolBase):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 20*60)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("Agent processing"):
+            return
+
         if kwargs.get("user_prompt"):
             usr_pmt = ""
             if kwargs.get("reasoning"):
@@ -152,13 +155,15 @@ class Agent(LLM, ToolBase):
             self._param.prompts = [{"role": "user", "content": usr_pmt}]
 
         if not self.tools:
+            if self.check_if_canceled("Agent processing"):
+                return
             return LLM._invoke(self, **kwargs)
 
         prompt, msg, user_defined_prompt = self._prepare_prompt_variables()
 
         downstreams = self._canvas.get_component(self._id)["downstream"] if self._canvas.get_component(self._id) else []
         ex = self.exception_handler()
-        if any([self._canvas.get_component_obj(cid).component_name.lower()=="message" for cid in downstreams]) and not self._param.output_structure and not (ex and ex["goto"]):
+        if any([self._canvas.get_component_obj(cid).component_name.lower()=="message" for cid in downstreams]) and not (ex and ex["goto"]):
             self.set_output("content", partial(self.stream_output_with_tools, prompt, msg, user_defined_prompt))
             return
 
@@ -166,6 +171,8 @@ class Agent(LLM, ToolBase):
         use_tools = []
         ans = ""
         for delta_ans, tk in self._react_with_tools_streamly(prompt, msg, use_tools, user_defined_prompt):
+            if self.check_if_canceled("Agent processing"):
+                return
             ans += delta_ans
 
         if ans.find("**ERROR**") >= 0:
@@ -186,12 +193,16 @@ class Agent(LLM, ToolBase):
         answer_without_toolcall = ""
         use_tools = []
         for delta_ans,_ in self._react_with_tools_streamly(prompt, msg, use_tools, user_defined_prompt):
+            if self.check_if_canceled("Agent streaming"):
+                return
+
             if delta_ans.find("**ERROR**") >= 0:
                 if self.get_exception_default_value():
                     self.set_output("content", self.get_exception_default_value())
                     yield self.get_exception_default_value()
                 else:
                     self.set_output("_ERROR", delta_ans)
+                    return
             answer_without_toolcall += delta_ans
             yield delta_ans
 
@@ -266,6 +277,8 @@ class Agent(LLM, ToolBase):
             st = timer()
             txt = ""
             for delta_ans in self._gen_citations(entire_txt):
+                if self.check_if_canceled("Agent streaming"):
+                    return
                 yield delta_ans, 0
                 txt += delta_ans
 
@@ -281,6 +294,8 @@ class Agent(LLM, ToolBase):
         task_desc = analyze_task(self.chat_mdl, prompt, user_request, tool_metas, user_defined_prompt)
         self.callback("analyze_task", {}, task_desc, elapsed_time=timer()-st)
         for _ in range(self._param.max_rounds + 1):
+            if self.check_if_canceled("Agent streaming"):
+                return
             response, tk = next_step(self.chat_mdl, hist, tool_metas, task_desc, user_defined_prompt)
             # self.callback("next_step", {}, str(response)[:256]+"...")
             token_count += tk
@@ -328,6 +343,8 @@ Instructions:
 6. Focus on delivering VALUE with the information already gathered
 Respond immediately with your final comprehensive answer.
         """
+        if self.check_if_canceled("Agent final instruction"):
+            return
         append_user_content(hist, final_instruction)
 
         for txt, tkcnt in complete():
@@ -346,11 +363,19 @@ Respond immediately with your final comprehensive answer.
 
         return "Error occurred."
 
-    def reset(self, temp=False):
+    def reset(self, only_output=False):
         """
         Reset all tools if they have a reset method. This avoids errors for tools like MCPToolCallSession.
         """
+        for k in self._param.outputs.keys():
+            self._param.outputs[k]["value"] = None
+            
         for k, cpn in self.tools.items():
             if hasattr(cpn, "reset") and callable(cpn.reset):
                 cpn.reset()
+        if only_output:
+            return
+        for k in self._param.inputs.keys():
+            self._param.inputs[k]["value"] = None
+        self._param.debug_inputs = {}
 

agent/component/base.py

@@ -25,7 +25,7 @@ from typing import Any, List, Union
 import pandas as pd
 import trio
 from agent import settings
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 _FEEDED_DEPRECATED_PARAMS = "_feeded_deprecated_params"
@@ -393,7 +393,7 @@ class ComponentParamBase(ABC):
 class ComponentBase(ABC):
     component_name: str
     thread_limiter = trio.CapacityLimiter(int(os.environ.get('MAX_CONCURRENT_CHATS', 10)))
-    variable_ref_patt = r"\{* *\{([a-zA-Z:0-9]+@[A-Za-z:0-9_.-]+|sys\.[a-z_]+)\} *\}*"
+    variable_ref_patt = r"\{* *\{([a-zA-Z:0-9]+@[A-Za-z0-9_.]+|sys\.[A-Za-z0-9_.]+|env\.[A-Za-z0-9_.]+)\} *\}*"
 
     def __str__(self):
         """
@@ -417,6 +417,20 @@ class ComponentBase(ABC):
         self._param = param
         self._param.check()
 
+    def is_canceled(self) -> bool:
+        return self._canvas.is_canceled()
+
+    def check_if_canceled(self, message: str = "") -> bool:
+        if self.is_canceled():
+            task_id = getattr(self._canvas, 'task_id', 'unknown')
+            log_message = f"Task {task_id} has been canceled"
+            if message:
+                log_message += f" during {message}"
+            logging.info(log_message)
+            self.set_output("_ERROR", "Task has been canceled")
+            return True
+        return False
+
     def invoke(self, **kwargs) -> dict[str, Any]:
         self.set_output("_created_time", time.perf_counter())
         try:
@@ -449,12 +463,15 @@ class ComponentBase(ABC):
         return self._param.outputs.get("_ERROR", {}).get("value")
 
     def reset(self, only_output=False):
-        for k in self._param.outputs.keys():
+        outputs: dict = self._param.outputs # for better performance
-            self._param.outputs[k]["value"] = None
+        for k in outputs.keys():
+            outputs[k]["value"] = None
         if only_output:
             return
-        for k in self._param.inputs.keys():
+
-            self._param.inputs[k]["value"] = None
+        inputs: dict = self._param.inputs # for better performance
+        for k in inputs.keys():
+            inputs[k]["value"] = None
         self._param.debug_inputs = {}
 
     def get_input(self, key: str=None) -> Union[Any, dict[str, Any]]:
@@ -514,6 +531,7 @@ class ComponentBase(ABC):
     def get_param(self, name):
         if hasattr(self._param, name):
             return getattr(self._param, name)
+        return None
 
     def debug(self, **kwargs):
         return self._invoke(**kwargs)
@@ -521,7 +539,7 @@ class ComponentBase(ABC):
     def get_parent(self) -> Union[object, None]:
         pid = self._canvas.get_component(self._id).get("parent_id")
         if not pid:
-            return
+            return None
         return self._canvas.get_component(pid)["obj"]
 
     def get_upstream(self) -> List[str]:
@@ -546,7 +564,7 @@ class ComponentBase(ABC):
 
     def exception_handler(self):
         if not self._param.exception_method:
-            return
+            return None
         return {
             "goto": self._param.exception_goto,
             "default_value": self._param.exception_default_value

agent/component/begin.py

@@ -37,7 +37,13 @@ class Begin(UserFillUp):
     component_name = "Begin"
 
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("Begin processing"):
+            return
+
         for k, v in kwargs.get("inputs", {}).items():
+            if self.check_if_canceled("Begin processing"):
+                return
+
             if isinstance(v, dict) and v.get("type", "").lower().find("file") >=0:
                 if v.get("optional") and v.get("value", None) is None:
                     v = None

agent/component/categorize.py

@@ -18,10 +18,10 @@ import os
 import re
 from abc import ABC
 
-from api.db import LLMType
+from common.constants import LLMType
 from api.db.services.llm_service import LLMBundle
 from agent.component.llm import LLMParam, LLM
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 from rag.llm.chat_model import ERROR_PREFIX
 
 
@@ -98,6 +98,9 @@ class Categorize(LLM, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("Categorize processing"):
+            return
+
         msg = self._canvas.get_history(self._param.message_history_window_size)
         if not msg:
             msg = [{"role": "user", "content": ""}]
@@ -114,10 +117,18 @@ class Categorize(LLM, ABC):
 ---- Real Data ----
 {} →
 """.format(" | ".join(["{}: \"{}\"".format(c["role"].upper(), re.sub(r"\n", "", c["content"], flags=re.DOTALL)) for c in msg]))
+
+        if self.check_if_canceled("Categorize processing"):
+            return
+
         ans = chat_mdl.chat(self._param.sys_prompt, [{"role": "user", "content": user_prompt}], self._param.gen_conf())
         logging.info(f"input: {user_prompt}, answer: {str(ans)}")
         if ERROR_PREFIX in ans:
             raise Exception(ans)
+
+        if self.check_if_canceled("Categorize processing"):
+            return
+
         # Count the number of times each category appears in the answer.
         category_counts = {}
         for c in self._param.category_description.keys():

agent/component/data_operations.py

@@ -0,0 +1,218 @@
+#
+#  Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+from abc import ABC
+import ast
+import os
+from agent.component.base import ComponentBase, ComponentParamBase
+from api.utils.api_utils import timeout
+
+class DataOperationsParam(ComponentParamBase):
+    """
+    Define the Data Operations component parameters.
+    """
+    def __init__(self):
+        super().__init__()
+        self.query = []
+        self.operations = "literal_eval"
+        self.select_keys = []
+        self.filter_values=[]
+        self.updates=[]
+        self.remove_keys=[]
+        self.rename_keys=[]
+        self.outputs = {
+            "result": {
+                "value": [],
+                "type": "Array of Object"
+            }
+        }
+    
+    def check(self):
+        self.check_valid_value(self.operations, "Support operations", ["select_keys", "literal_eval","combine","filter_values","append_or_update","remove_keys","rename_keys"])
+    
+    
+
+class DataOperations(ComponentBase,ABC):
+    component_name = "DataOperations"
+
+    def get_input_form(self) -> dict[str, dict]:
+        return {
+            k: {"name": o.get("name", ""), "type": "line"}
+            for input_item in (self._param.query or [])
+            for k, o in self.get_input_elements_from_text(input_item).items()
+        }
+
+    @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
+    def _invoke(self, **kwargs):
+        self.input_objects=[]
+        inputs = getattr(self._param, "query", None)
+        if not isinstance(inputs, (list, tuple)):
+            inputs = [inputs]
+        for input_ref in inputs:
+            input_object=self._canvas.get_variable_value(input_ref)
+            self.set_input_value(input_ref, input_object)
+            if input_object is None:
+                continue
+            if isinstance(input_object,dict):
+                self.input_objects.append(input_object)
+            elif isinstance(input_object,list):
+                self.input_objects.extend(x for x in input_object if isinstance(x, dict))
+            else:
+                continue
+        if self._param.operations == "select_keys":
+            self._select_keys()
+        elif self._param.operations == "recursive_eval":
+            self._literal_eval()
+        elif self._param.operations == "combine":
+            self._combine()
+        elif self._param.operations == "filter_values":
+            self._filter_values()
+        elif self._param.operations == "append_or_update":
+            self._append_or_update()
+        elif self._param.operations == "remove_keys":
+            self._remove_keys()
+        else:
+            self._rename_keys()
+    
+    def _select_keys(self):
+        filter_criteria: list[str] = self._param.select_keys
+        results = [{key: value for key, value in data_dict.items() if key in filter_criteria} for data_dict in self.input_objects]
+        self.set_output("result", results)
+
+
+    def _recursive_eval(self, data):
+        if isinstance(data, dict):
+            return {k: self.recursive_eval(v) for k, v in data.items()}
+        if isinstance(data, list):
+            return [self.recursive_eval(item) for item in data]
+        if isinstance(data, str):
+            try:
+                if (
+                    data.strip().startswith(("{", "[", "(", "'", '"'))
+                    or data.strip().lower() in ("true", "false", "none")
+                    or data.strip().replace(".", "").isdigit()
+                ):
+                    return ast.literal_eval(data)
+            except (ValueError, SyntaxError, TypeError, MemoryError):
+                return data
+            else:
+                return data
+        return data
+    
+    def _literal_eval(self):
+        self.set_output("result", self._recursive_eval(self.input_objects))
+
+    def _combine(self):
+        result={}
+        for obj in self.input_objects:
+            for key, value in obj.items():
+                if key not in result:
+                    result[key] = value
+                elif isinstance(result[key], list):
+                    if isinstance(value, list):
+                        result[key].extend(value)
+                    else:
+                        result[key].append(value)
+                else:
+                    result[key] = (
+                        [result[key], value] if not isinstance(value, list) else [result[key], *value]
+                    )
+        self.set_output("result", result)
+    
+    def norm(self,v):
+        s = "" if v is None else str(v)
+        return s
+    
+    def match_rule(self, obj, rule):
+        key = rule.get("key")
+        op = (rule.get("operator") or "equals").lower()
+        target = self.norm(rule.get("value"))
+        target = self._canvas.get_value_with_variable(target) or target
+        if key not in obj:
+            return False
+        val = obj.get(key, None)
+        v = self.norm(val)
+        if op == "=":
+            return v == target
+        if op == "≠":
+            return v != target
+        if op == "contains":
+            return target in v
+        if op == "start with":
+            return v.startswith(target)
+        if op == "end with":
+            return v.endswith(target)
+        return False
+        
+    def _filter_values(self):
+        results=[]
+        rules = (getattr(self._param, "filter_values", None) or [])
+        for obj in self.input_objects:
+            if not rules:
+                results.append(obj)
+                continue
+            if all(self.match_rule(obj, r) for r in rules):
+                results.append(obj)
+        self.set_output("result", results)
+            
+                
+    def _append_or_update(self):
+        results=[]
+        updates = getattr(self._param, "updates", []) or [] 
+        for obj in self.input_objects:
+            new_obj = dict(obj)
+            for item in updates:
+                if not isinstance(item, dict):
+                    continue
+                k = (item.get("key") or "").strip()
+                if not k:
+                    continue
+                new_obj[k] = self._canvas.get_value_with_variable(item.get("value")) or item.get("value")
+            results.append(new_obj)
+        self.set_output("result", results)
+
+    def _remove_keys(self):
+        results = []
+        remove_keys = getattr(self._param, "remove_keys", []) or []
+
+        for obj in (self.input_objects or []):
+            new_obj = dict(obj)
+            for k in remove_keys:
+                if not isinstance(k, str):
+                    continue
+                new_obj.pop(k, None)
+            results.append(new_obj)
+        self.set_output("result", results)
+
+    def _rename_keys(self):
+        results = []
+        rename_pairs = getattr(self._param, "rename_keys", []) or []
+
+        for obj in (self.input_objects or []):
+            new_obj = dict(obj)
+            for pair in rename_pairs:
+                if not isinstance(pair, dict):
+                    continue
+                old = (pair.get("old_key") or "").strip()
+                new = (pair.get("new_key") or "").strip()
+                if not old or not new or old == new:
+                    continue
+                if old in new_obj:
+                    new_obj[new] = new_obj.pop(old)
+            results.append(new_obj)
+        self.set_output("result", results)
+
+    def thoughts(self) -> str:
+        return "DataOperation in progress"

agent/component/fillup.py

@@ -13,7 +13,11 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-from agent.component.base import ComponentBase, ComponentParamBase
+import json
+import re
+from functools import partial
+
+from agent.component.base import ComponentParamBase, ComponentBase
 
 
 class UserFillUpParam(ComponentParamBase):
@@ -31,10 +35,35 @@ class UserFillUp(ComponentBase):
     component_name = "UserFillUp"
 
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("UserFillUp processing"):
+            return
+
+        if self._param.enable_tips:
+            content = self._param.tips
+            for k, v in self.get_input_elements_from_text(self._param.tips).items():
+                v = v["value"]
+                ans = ""
+                if isinstance(v, partial):
+                    for t in v():
+                        ans += t
+                elif isinstance(v, list):
+                    ans = ",".join([str(vv) for vv in v])
+                elif not isinstance(v, str):
+                    try:
+                        ans = json.dumps(v, ensure_ascii=False)
+                    except Exception:
+                        pass
+                else:
+                    ans = v
+                if not ans:
+                    ans = ""
+                content = re.sub(r"\{%s\}"%k, ans, content)
+
+            self.set_output("tips", content)
         for k, v in kwargs.get("inputs", {}).items():
+            if self.check_if_canceled("UserFillUp processing"):
+                return
             self.set_output(k, v)
 
     def thoughts(self) -> str:
         return "Waiting for your input..."
-
-

agent/component/invoke.py

@@ -23,7 +23,7 @@ from abc import ABC
 import requests
 
 from agent.component.base import ComponentBase, ComponentParamBase
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 from deepdoc.parser import HtmlParser
 
 
@@ -56,6 +56,9 @@ class Invoke(ComponentBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 3)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("Invoke processing"):
+            return
+
         args = {}
         for para in self._param.variables:
             if para.get("value"):
@@ -89,6 +92,9 @@ class Invoke(ComponentBase, ABC):
 
         last_e = ""
         for _ in range(self._param.max_retries + 1):
+            if self.check_if_canceled("Invoke processing"):
+                return
+
             try:
                 if method == "get":
                     response = requests.get(url=url, params=args, headers=headers, proxies=proxies, timeout=self._param.timeout)
@@ -121,6 +127,9 @@ class Invoke(ComponentBase, ABC):
 
                 return self.output("result")
             except Exception as e:
+                if self.check_if_canceled("Invoke processing"):
+                    return
+
                 last_e = e
                 logging.exception(f"Http request error: {e}")
                 time.sleep(self._param.delay_after_error)

agent/component/iteration.py

@@ -16,6 +16,13 @@
 from abc import ABC
 from agent.component.base import ComponentBase, ComponentParamBase
 
+"""
+class VariableModel(BaseModel):
+    data_type: Annotated[Literal["string", "number", "Object", "Boolean", "Array<string>", "Array<number>", "Array<object>", "Array<boolean>"], Field(default="Array<string>")]
+    input_mode: Annotated[Literal["constant", "variable"], Field(default="constant")]
+    value: Annotated[Any, Field(default=None)]
+    model_config = ConfigDict(extra="forbid")
+"""
 
 class IterationParam(ComponentParamBase):
     """
@@ -25,6 +32,7 @@ class IterationParam(ComponentParamBase):
     def __init__(self):
         super().__init__()
         self.items_ref = ""
+        self.variable={}
 
     def get_input_form(self) -> dict[str, dict]:
         return {
@@ -49,6 +57,9 @@ class Iteration(ComponentBase, ABC):
                 return cid
 
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("Iteration processing"):
+            return
+
         arr = self._canvas.get_variable_value(self._param.items_ref)
         if not isinstance(arr, list):
             self.set_output("_ERROR", self._param.items_ref + " must be an array, but its type is "+str(type(arr)))

agent/component/iterationitem.py

@@ -33,6 +33,9 @@ class IterationItem(ComponentBase, ABC):
         self._idx = 0
 
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("IterationItem processing"):
+            return
+
         parent = self.get_parent()
         arr = self._canvas.get_variable_value(parent._param.items_ref)
         if not isinstance(arr, list):
@@ -40,12 +43,17 @@ class IterationItem(ComponentBase, ABC):
             raise Exception(parent._param.items_ref + " must be an array, but its type is "+str(type(arr)))
 
         if self._idx > 0:
+            if self.check_if_canceled("IterationItem processing"):
+                return
             self.output_collation()
 
         if self._idx >= len(arr):
             self._idx = -1
             return
 
+        if self.check_if_canceled("IterationItem processing"):
+            return
+
         self.set_output("item", arr[self._idx])
         self.set_output("index", self._idx)
 

agent/component/list_operations.py

@@ -0,0 +1,168 @@
+from abc import ABC
+import os
+from agent.component.base import ComponentBase, ComponentParamBase
+from api.utils.api_utils import timeout
+
+class ListOperationsParam(ComponentParamBase):
+    """
+    Define the List Operations component parameters.
+    """
+    def __init__(self):
+        super().__init__()
+        self.query = ""
+        self.operations = "topN"
+        self.n=0
+        self.sort_method = "asc"
+        self.filter = {
+            "operator": "=",
+            "value": ""
+        }
+        self.outputs = {
+            "result": {
+                "value": [],
+                "type": "Array of ?"
+            },
+            "first": {
+                "value": "",
+                "type": "?"
+            },
+            "last": {
+                "value": "",
+                "type": "?"
+            }
+        }
+    
+    def check(self):
+        self.check_empty(self.query, "query")
+        self.check_valid_value(self.operations, "Support operations", ["topN","head","tail","filter","sort","drop_duplicates"])
+
+    def get_input_form(self) -> dict[str, dict]:
+        return {}
+    
+
+class ListOperations(ComponentBase,ABC):
+    component_name = "ListOperations"
+
+    @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
+    def _invoke(self, **kwargs):
+        self.input_objects=[]
+        inputs = getattr(self._param, "query", None)
+        self.inputs = self._canvas.get_variable_value(inputs)
+        if not isinstance(self.inputs, list):
+            raise TypeError("The input of List Operations should be an array.")
+        self.set_input_value(inputs, self.inputs)
+        if self._param.operations == "topN":
+            self._topN()
+        elif self._param.operations == "head":
+            self._head()
+        elif self._param.operations == "tail":
+            self._tail()
+        elif self._param.operations == "filter":
+            self._filter()
+        elif self._param.operations == "sort":
+            self._sort()
+        elif self._param.operations == "drop_duplicates":
+            self._drop_duplicates()
+
+
+    def _coerce_n(self):
+        try:
+            return int(getattr(self._param, "n", 0))
+        except Exception:
+            return 0
+        
+    def _set_outputs(self, outputs):
+        self._param.outputs["result"]["value"] = outputs
+        self._param.outputs["first"]["value"] = outputs[0] if outputs else None
+        self._param.outputs["last"]["value"]  = outputs[-1] if outputs else None
+        
+    def _topN(self):
+        n = self._coerce_n()
+        if n < 1:
+            outputs = []
+        else:
+            n = min(n, len(self.inputs))
+            outputs = self.inputs[:n]
+        self._set_outputs(outputs)
+
+    def _head(self):
+        n = self._coerce_n()
+        if 1 <= n <= len(self.inputs):
+            outputs = [self.inputs[n - 1]]
+        else:
+            outputs = []
+        self._set_outputs(outputs)
+
+    def _tail(self):
+        n = self._coerce_n()
+        if 1 <= n <= len(self.inputs):
+            outputs = [self.inputs[-n]]
+        else:
+            outputs = []
+        self._set_outputs(outputs)
+
+    def _filter(self):
+        self._set_outputs([i for i in self.inputs if self._eval(self._norm(i),self._param.filter["operator"],self._param.filter["value"])])
+
+    def _norm(self,v):
+        s = "" if v is None else str(v)
+        return s
+    
+    def _eval(self, v, operator, value):
+        if operator == "=":
+            return v == value
+        elif operator == "≠":
+            return v != value
+        elif operator == "contains":
+            return value in v
+        elif operator == "start with":
+            return v.startswith(value)
+        elif operator == "end with":
+            return v.endswith(value)
+        else:
+            return False
+
+    def _sort(self):
+        items = self.inputs or []
+        method = getattr(self._param, "sort_method", "asc") or "asc"
+        reverse = method == "desc"
+
+        if not items:
+            self._set_outputs([])
+            return
+
+        first = items[0]
+
+        if isinstance(first, dict):
+            outputs = sorted(
+                items,
+                key=lambda x: self._hashable(x),
+                reverse=reverse,
+            )
+        else:
+            outputs = sorted(items, reverse=reverse)
+
+        self._set_outputs(outputs)
+
+    def _drop_duplicates(self):
+        seen = set()
+        outs = []
+        for item in self.inputs:
+            k = self._hashable(item)
+            if k in seen:
+                continue
+            seen.add(k)
+            outs.append(item)
+        self._set_outputs(outs)
+
+    def _hashable(self,x):
+        if isinstance(x, dict):
+            return tuple(sorted((k, self._hashable(v)) for k, v in x.items()))
+        if isinstance(x, (list, tuple)):
+            return tuple(self._hashable(v) for v in x)
+        if isinstance(x, set):
+            return tuple(sorted(self._hashable(v) for v in x))
+        return x
+    
+    def thoughts(self) -> str:
+        return "ListOperation in progress"

agent/component/llm.py

@@ -21,12 +21,12 @@ from copy import deepcopy
 from typing import Any, Generator
 import json_repair
 from functools import partial
-from api.db import LLMType
+from common.constants import LLMType
 from api.db.services.llm_service import LLMBundle
 from api.db.services.tenant_llm_service import TenantLLMService
 from agent.component.base import ComponentBase, ComponentParamBase
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
-from rag.prompts.generator import tool_call_summary, message_fit_in, citation_prompt
+from rag.prompts.generator import tool_call_summary, message_fit_in, citation_prompt, structured_output_prompt
 
 
 class LLMParam(ComponentParamBase):
@@ -207,6 +207,9 @@ class LLM(ComponentBase):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("LLM processing"):
+            return
+
         def clean_formated_answer(ans: str) -> str:
             ans = re.sub(r"^.*</think>", "", ans, flags=re.DOTALL)
             ans = re.sub(r"^.*```json", "", ans, flags=re.DOTALL)
@@ -214,11 +217,18 @@ class LLM(ComponentBase):
 
         prompt, msg, _ = self._prepare_prompt_variables()
         error: str = ""
-
+        output_structure=None
-        if self._param.output_structure:
+        try:
-            prompt += "\nThe output MUST follow this JSON format:\n"+json.dumps(self._param.output_structure, ensure_ascii=False, indent=2)
+            output_structure = self._param.outputs['structured']
-            prompt += "\nRedundant information is FORBIDDEN."
+        except Exception:
+            pass
+        if output_structure and isinstance(output_structure, dict) and output_structure.get("properties"):
+            schema=json.dumps(output_structure, ensure_ascii=False, indent=2)
+            prompt += structured_output_prompt(schema)
             for _ in range(self._param.max_retries+1):
+                if self.check_if_canceled("LLM processing"):
+                    return
+
                 _, msg = message_fit_in([{"role": "system", "content": prompt}, *msg], int(self.chat_mdl.max_length * 0.97))
                 error = ""
                 ans = self._generate(msg)
@@ -228,7 +238,7 @@ class LLM(ComponentBase):
                     error = ans
                     continue
                 try:
-                    self.set_output("structured_content", json_repair.loads(clean_formated_answer(ans)))
+                    self.set_output("structured", json_repair.loads(clean_formated_answer(ans)))
                     return
                 except Exception:
                     msg.append({"role": "user", "content": "The answer can't not be parsed as JSON"})
@@ -239,11 +249,14 @@ class LLM(ComponentBase):
 
         downstreams = self._canvas.get_component(self._id)["downstream"] if self._canvas.get_component(self._id) else []
         ex = self.exception_handler()
-        if any([self._canvas.get_component_obj(cid).component_name.lower()=="message" for cid in downstreams]) and not self._param.output_structure and not (ex and ex["goto"]):
+        if any([self._canvas.get_component_obj(cid).component_name.lower()=="message" for cid in downstreams]) and not (ex and ex["goto"]):
             self.set_output("content", partial(self._stream_output, prompt, msg))
             return
 
         for _ in range(self._param.max_retries+1):
+            if self.check_if_canceled("LLM processing"):
+                return
+
             _, msg = message_fit_in([{"role": "system", "content": prompt}, *msg], int(self.chat_mdl.max_length * 0.97))
             error = ""
             ans = self._generate(msg)
@@ -265,6 +278,9 @@ class LLM(ComponentBase):
         _, msg = message_fit_in([{"role": "system", "content": prompt}, *msg], int(self.chat_mdl.max_length * 0.97))
         answer = ""
         for ans in self._generate_streamly(msg):
+            if self.check_if_canceled("LLM streaming"):
+                return
+
             if ans.find("**ERROR**") >= 0:
                 if self.get_exception_default_value():
                     self.set_output("content", self.get_exception_default_value())

agent/component/message.py

@@ -17,13 +17,17 @@ import json
 import os
 import random
 import re
+import logging
+import tempfile
 from functools import partial
 from typing import Any
 
 from agent.component.base import ComponentBase, ComponentParamBase
 from jinja2 import Template as Jinja2Template
 
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
+from common.misc_utils import get_uuid
+from common import settings
 
 
 class MessageParam(ComponentParamBase):
@@ -34,6 +38,7 @@ class MessageParam(ComponentParamBase):
         super().__init__()
         self.content = []
         self.stream = True
+        self.output_format = None  # default output format
         self.outputs = {
             "content": {
                 "type": "str"
@@ -49,6 +54,9 @@ class MessageParam(ComponentParamBase):
 class Message(ComponentBase):
     component_name = "Message"
 
+    def get_input_elements(self) -> dict[str, Any]:
+        return self.get_input_elements_from_text("".join(self._param.content))
+
     def get_kwargs(self, script:str, kwargs:dict = {}, delimiter:str=None) -> tuple[str, dict[str, str | list | Any]]:
         for k,v in self.get_input_elements_from_text(script).items():
             if k in kwargs:
@@ -86,6 +94,9 @@ class Message(ComponentBase):
         all_content = ""
         cache = {}
         for r in re.finditer(self.variable_ref_patt, rand_cnt, flags=re.DOTALL):
+            if self.check_if_canceled("Message streaming"):
+                return
+
             all_content += rand_cnt[s: r.start()]
             yield rand_cnt[s: r.start()]
             s = r.end()
@@ -96,30 +107,38 @@ class Message(ComponentBase):
                 continue
 
             v = self._canvas.get_variable_value(exp)
-            if not v:
+            if v is None:
                 v = ""
             if isinstance(v, partial):
                 cnt = ""
                 for t in v():
+                    if self.check_if_canceled("Message streaming"):
+                        return
+
                     all_content += t
                     cnt += t
                     yield t
-
+                self.set_input_value(exp, cnt)
                 continue
             elif not isinstance(v, str):
                 try:
-                    v = json.dumps(v, ensure_ascii=False, indent=2)
+                    v = json.dumps(v, ensure_ascii=False)
                 except Exception:
                     v = str(v)
             yield v
+            self.set_input_value(exp, v)
             all_content += v
             cache[exp] = v
 
         if s < len(rand_cnt):
+            if self.check_if_canceled("Message streaming"):
+                return
+
             all_content += rand_cnt[s: ]
             yield rand_cnt[s: ]
 
         self.set_output("content", all_content)
+        self._convert_content(all_content)
 
     def _is_jinjia2(self, content:str) -> bool:
         patt = [
@@ -129,6 +148,9 @@ class Message(ComponentBase):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("Message processing"):
+            return
+
         rand_cnt = random.choice(self._param.content)
         if self._param.stream and not self._is_jinjia2(rand_cnt):
             self.set_output("content", partial(self._stream, rand_cnt))
@@ -141,10 +163,79 @@ class Message(ComponentBase):
         except Exception:
             pass
 
+        if self.check_if_canceled("Message processing"):
+            return
+
         for n, v in kwargs.items():
             content = re.sub(n, v, content)
 
         self.set_output("content", content)
+        self._convert_content(content)
 
     def thoughts(self) -> str:
         return ""
+
+    def _convert_content(self, content):
+        if not self._param.output_format:
+            return
+
+        import pypandoc
+        doc_id = get_uuid()
+        
+        if self._param.output_format.lower() not in {"markdown", "html", "pdf", "docx"}:
+            self._param.output_format = "markdown"
+
+        try:
+            if self._param.output_format in {"markdown", "html"}:
+                if isinstance(content, str):
+                    converted = pypandoc.convert_text(
+                        content,
+                        to=self._param.output_format,
+                        format="markdown",
+                    )
+                else:
+                    converted = pypandoc.convert_file(
+                        content,
+                        to=self._param.output_format,
+                        format="markdown",
+                    )
+
+                binary_content = converted.encode("utf-8")
+
+            else:  # pdf, docx
+                with tempfile.NamedTemporaryFile(suffix=f".{self._param.output_format}", delete=False) as tmp:
+                    tmp_name = tmp.name
+
+                try:
+                    if isinstance(content, str):
+                        pypandoc.convert_text(
+                            content,
+                            to=self._param.output_format,
+                            format="markdown",
+                            outputfile=tmp_name,
+                        )
+                    else:
+                        pypandoc.convert_file(
+                            content,
+                            to=self._param.output_format,
+                            format="markdown",
+                            outputfile=tmp_name,
+                        )
+
+                    with open(tmp_name, "rb") as f:
+                        binary_content = f.read()
+
+                finally:
+                    if os.path.exists(tmp_name):
+                        os.remove(tmp_name)
+
+            settings.STORAGE_IMPL.put(self._canvas._tenant_id, doc_id, binary_content)
+            self.set_output("attachment", {
+                "doc_id":doc_id, 
+                "format":self._param.output_format, 
+                "file_name":f"{doc_id[:8]}.{self._param.output_format}"})
+
+            logging.info(f"Converted content uploaded as {doc_id} (format={self._param.output_format})")
+
+        except Exception as e:
+            logging.error(f"Error converting content to {self._param.output_format}: {e}")

agent/component/string_transform.py

@@ -16,9 +16,11 @@
 import os
 import re
 from abc import ABC
+from typing import Any
+
 from jinja2 import Template as Jinja2Template
 from agent.component.base import ComponentParamBase
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 from .message import Message
 
 
@@ -43,6 +45,9 @@ class StringTransformParam(ComponentParamBase):
 class StringTransform(Message, ABC):
     component_name = "StringTransform"
 
+    def get_input_elements(self) -> dict[str, Any]:
+        return self.get_input_elements_from_text(self._param.script)
+
     def get_input_form(self) -> dict[str, dict]:
         if self._param.method == "split":
             return {
@@ -58,17 +63,24 @@ class StringTransform(Message, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("StringTransform processing"):
+            return
+
         if self._param.method == "split":
             self._split(kwargs.get("line"))
         else:
             self._merge(kwargs)
 
     def _split(self, line:str|None = None):
+        if self.check_if_canceled("StringTransform split processing"):
+            return
+
         var = self._canvas.get_variable_value(self._param.split_ref) if not line else line
         if not var:
             var = ""
         assert isinstance(var, str), "The input variable is not a string: {}".format(type(var))
         self.set_input_value(self._param.split_ref, var)
+
         res = []
         for i,s in enumerate(re.split(r"(%s)"%("|".join([re.escape(d) for d in self._param.delimiters])), var, flags=re.DOTALL)):
             if i % 2 == 1:
@@ -77,6 +89,9 @@ class StringTransform(Message, ABC):
         self.set_output("result", res)
 
     def _merge(self, kwargs:dict[str, str] = {}):
+        if self.check_if_canceled("StringTransform merge processing"):
+            return
+
         script = self._param.script
         script, kwargs = self.get_kwargs(script, kwargs, self._param.delimiters[0])
 

agent/component/switch.py

@@ -19,7 +19,7 @@ from abc import ABC
 from typing import Any
 
 from agent.component.base import ComponentBase, ComponentParamBase
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 class SwitchParam(ComponentParamBase):
@@ -63,9 +63,18 @@ class Switch(ComponentBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 3)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("Switch processing"):
+            return
+
         for cond in self._param.conditions:
+            if self.check_if_canceled("Switch processing"):
+                return
+
             res = []
             for item in cond["items"]:
+                if self.check_if_canceled("Switch processing"):
+                    return
+
                 if not item["cpn_id"]:
                     continue
                 cpn_v = self._canvas.get_variable_value(item["cpn_id"])

agent/component/varaiable_aggregator.py

@@ -0,0 +1,84 @@
+#
+#  Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+from typing import Any
+import os
+
+from common.connection_utils import timeout
+from agent.component.base import ComponentBase, ComponentParamBase
+
+
+class VariableAggregatorParam(ComponentParamBase):
+    """
+    Parameters for VariableAggregator
+
+    - groups: list of dicts {"group_name": str, "variables": [variable selectors]}
+    """
+
+    def __init__(self):
+        super().__init__()
+        # each group expects: {"group_name": str, "variables": List[str]}
+        self.groups = []
+
+    def check(self):
+        self.check_empty(self.groups, "[VariableAggregator] groups")
+        for g in self.groups:
+            if not g.get("group_name"):
+                raise ValueError("[VariableAggregator] group_name can not be empty!")
+            if not g.get("variables"):
+                raise ValueError(
+                    f"[VariableAggregator] variables of group `{g.get('group_name')}` can not be empty"
+                )
+            if not isinstance(g.get("variables"), list):
+                raise ValueError(
+                    f"[VariableAggregator] variables of group `{g.get('group_name')}` should be a list of strings"
+                )
+
+    def get_input_form(self) -> dict[str, dict]:
+        return {
+            "variables": {
+                "name": "Variables",
+                "type": "list",
+            }
+        }
+
+
+class VariableAggregator(ComponentBase):
+    component_name = "VariableAggregator"
+
+    @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 3)))
+    def _invoke(self, **kwargs):
+        # Group mode: for each group, pick the first available variable
+        for group in self._param.groups:
+            gname = group.get("group_name")
+
+            # record candidate selectors within this group
+            self.set_input_value(f"{gname}.variables", list(group.get("variables", [])))
+            for selector in group.get("variables", []):
+                val = self._canvas.get_variable_value(selector['value'])
+                if val:
+                    self.set_output(gname, val)
+                    break
+            
+    @staticmethod
+    def _to_object(value: Any) -> Any:
+        # Try to convert value to serializable object if it has to_object()
+        try:
+            return value.to_object()  # type: ignore[attr-defined]
+        except Exception:
+            return value
+
+    def thoughts(self) -> str:
+        return "Aggregating variables from canvas and grouping as configured."

agent/component/variable_assigner.py

@@ -0,0 +1,192 @@
+#
+#  Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+from abc import ABC
+import os
+import numbers
+from agent.component.base import ComponentBase, ComponentParamBase
+from api.utils.api_utils import timeout
+
+class VariableAssignerParam(ComponentParamBase):
+    """
+    Define the Variable Assigner component parameters.
+    """
+    def __init__(self):
+        super().__init__()
+        self.variables=[]
+
+    def check(self):
+        return True
+    
+    def get_input_form(self) -> dict[str, dict]:
+        return {
+            "items": {
+                "type": "json",
+                "name": "Items"
+            }
+        }
+
+class VariableAssigner(ComponentBase,ABC):
+    component_name = "VariableAssigner"
+
+    @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
+    def _invoke(self, **kwargs):
+        if not isinstance(self._param.variables,list):
+            return
+        else:
+            for item in self._param.variables:
+                if any([not item.get("variable"), not item.get("operator"), not item.get("parameter")]):
+                    assert "Variable is not complete."
+                variable=item["variable"]
+                operator=item["operator"]
+                parameter=item["parameter"]
+                variable_value=self._canvas.get_variable_value(variable)
+                new_variable=self._operate(variable_value,operator,parameter)
+                self._canvas.set_variable_value(variable, new_variable)
+
+    def _operate(self,variable,operator,parameter):
+        if operator == "overwrite":
+            return self._overwrite(parameter)
+        elif operator == "clear":
+            return self._clear(variable)
+        elif operator == "set":
+            return self._set(variable,parameter)
+        elif operator == "append":
+            return self._append(variable,parameter)
+        elif operator == "extend":
+            return self._extend(variable,parameter)
+        elif operator == "remove_first":
+            return self._remove_first(variable)
+        elif operator == "remove_last":
+            return self._remove_last(variable)
+        elif operator == "+=":
+            return self._add(variable,parameter)
+        elif operator == "-=":
+            return self._subtract(variable,parameter)
+        elif operator == "*=":
+            return self._multiply(variable,parameter)
+        elif operator == "/=":
+            return self._divide(variable,parameter)
+        else:
+            return
+    
+    def _overwrite(self,parameter):
+        return self._canvas.get_variable_value(parameter)
+
+    def _clear(self,variable):
+        if isinstance(variable,list):
+            return []
+        elif isinstance(variable,str):
+            return ""
+        elif isinstance(variable,dict):
+            return {}
+        elif isinstance(variable,int):
+            return 0
+        elif isinstance(variable,float):
+            return 0.0
+        elif isinstance(variable,bool):
+            return False
+        else:
+            return None
+
+    def _set(self,variable,parameter):
+        if variable is None:
+            return self._canvas.get_value_with_variable(parameter)
+        elif isinstance(variable,str):
+            return self._canvas.get_value_with_variable(parameter)
+        elif isinstance(variable,bool):
+            return parameter
+        elif isinstance(variable,int):
+            return parameter
+        elif isinstance(variable,float):
+            return parameter
+        else:
+            return parameter
+
+    def _append(self,variable,parameter):
+        parameter=self._canvas.get_variable_value(parameter)
+        if variable is None:
+            variable=[]
+        if not isinstance(variable,list):
+            return "ERROR:VARIABLE_NOT_LIST"
+        elif len(variable)!=0 and not isinstance(parameter,type(variable[0])):
+            return "ERROR:PARAMETER_NOT_LIST_ELEMENT_TYPE"
+        else:
+            variable.append(parameter)
+            return variable
+
+    def _extend(self,variable,parameter):
+        parameter=self._canvas.get_variable_value(parameter)
+        if variable is None:
+            variable=[]
+        if not isinstance(variable,list):
+            return "ERROR:VARIABLE_NOT_LIST"
+        elif not isinstance(parameter,list):
+            return "ERROR:PARAMETER_NOT_LIST"
+        elif len(variable)!=0 and len(parameter)!=0 and not isinstance(parameter[0],type(variable[0])):
+            return "ERROR:PARAMETER_NOT_LIST_ELEMENT_TYPE"
+        else:
+            return variable + parameter
+
+    def _remove_first(self,variable):
+        if len(variable)==0:
+            return variable
+        if not isinstance(variable,list):
+            return "ERROR:VARIABLE_NOT_LIST"
+        else:
+            return variable[1:]
+
+    def _remove_last(self,variable):
+        if len(variable)==0:
+            return variable
+        if not isinstance(variable,list):
+            return "ERROR:VARIABLE_NOT_LIST"
+        else:
+            return variable[:-1]
+
+    def is_number(self, value):
+        if isinstance(value, bool):
+            return False
+        return isinstance(value, numbers.Number)
+
+    def _add(self,variable,parameter):
+        if self.is_number(variable) and self.is_number(parameter):
+            return variable + parameter
+        else:
+            return "ERROR:VARIABLE_NOT_NUMBER or PARAMETER_NOT_NUMBER"
+
+    def _subtract(self,variable,parameter):
+        if self.is_number(variable) and self.is_number(parameter):
+            return variable - parameter
+        else:
+            return "ERROR:VARIABLE_NOT_NUMBER or PARAMETER_NOT_NUMBER"
+
+    def _multiply(self,variable,parameter):
+        if self.is_number(variable) and self.is_number(parameter):
+            return variable * parameter
+        else:
+            return "ERROR:VARIABLE_NOT_NUMBER or PARAMETER_NOT_NUMBER"
+
+    def _divide(self,variable,parameter):
+        if self.is_number(variable) and self.is_number(parameter):
+            if  parameter==0:
+                return "ERROR:DIVIDE_BY_ZERO"
+            else:
+                return variable/parameter
+        else:
+            return  "ERROR:VARIABLE_NOT_NUMBER or PARAMETER_NOT_NUMBER"
+
+    def thoughts(self) -> str:
+        return "Assign variables from canvas."

agent/component/webhook.py

@@ -0,0 +1,38 @@
+#
+#  Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+from agent.component.base import ComponentParamBase, ComponentBase
+
+
+class WebhookParam(ComponentParamBase):
+
+    """
+    Define the Begin component parameters.
+    """
+    def __init__(self):
+        super().__init__()
+
+    def get_input_form(self) -> dict[str, dict]:
+        return getattr(self, "inputs")
+
+
+class Webhook(ComponentBase):
+    component_name = "Webhook"
+
+    def _invoke(self, **kwargs):
+        pass
+
+    def thoughts(self) -> str:
+        return ""

agent/templates/advanced_ingestion_pipeline.json

@@ -2,10 +2,12 @@
     "id": 23,
     "title": {
         "en": "Advanced Ingestion Pipeline",
+        "de": "Erweiterte Ingestion Pipeline",
         "zh": "编排复杂的 Ingestion Pipeline"
     },
     "description": {
         "en": "This template demonstrates how to use an LLM to generate summaries, keywords, Q&A, and metadata for each chunk to support diverse retrieval needs.",
+        "de": "Diese Vorlage demonstriert, wie ein LLM verwendet wird, um Zusammenfassungen, Schlüsselwörter, Fragen & Antworten und Metadaten für jedes Segment zu generieren, um vielfältige Abrufanforderungen zu unterstützen.",
         "zh": "此模板演示如何利用大模型为切片生成摘要、关键词、问答及元数据，以满足多样化的召回需求。"
     },
     "canvas_type": "Ingestion Pipeline",

agent/templates/chunk_summary.json

@@ -2,10 +2,12 @@
     "id": 24,
     "title": {
         "en": "Chunk Summary",
+        "de": "Segmentzusammenfassung",
         "zh": "总结切片"
     },
     "description": {
         "en": "This template uses an LLM to generate chunk summaries for building text and vector indexes. During retrieval, summaries enhance matching, and the original chunks are returned as results.",
+        "de": "Diese Vorlage nutzt ein LLM zur Generierung von Segmentzusammenfassungen für den Aufbau von Text- und Vektorindizes. Bei der Abfrage verbessern die Zusammenfassungen die Übereinstimmung, während die ursprünglichen Segmente als Ergebnisse zurückgegeben werden.",
         "zh": "此模板利用大模型生成切片摘要，并据此建立全文索引与向量。检索时以摘要提升匹配效果，最终召回对应的原文切片。"
     },
     "canvas_type": "Ingestion Pipeline",
@@ -350,7 +352,7 @@
                             ]
                         },
                         "label": "Tokenizer",
-                        "name": "Tokenizer"
+                        "name": "Indexer"
                     },
                     "dragging": false,
                     "id": "Tokenizer:EightRocketsAppear",

agent/templates/deep_research.json

@@ -3,9 +3,11 @@
     "id": 1,
     "title": {
         "en": "Deep Research",
+        "de": "Tiefgehende Recherche",
         "zh": "深度研究"},
     "description": {
         "en": "For professionals in sales, marketing, policy, or consulting, the Multi-Agent Deep Research Agent conducts structured, multi-step investigations across diverse sources and delivers consulting-style reports with clear citations.",
+        "de": "Für Fachleute in Vertrieb, Marketing, Politik oder Beratung führt der Multi-Agenten-Tiefenforschungsagent strukturierte, mehrstufige Untersuchungen über verschiedene Quellen durch und liefert Berichte im Beratungsstil mit klaren Quellenangaben.",
         "zh": "专为销售、市场、政策或咨询领域的专业人士设计，多智能体的深度研究会结合多源信息进行结构化、多步骤地回答问题，并附带有清晰的引用。"},
     "canvas_type": "Recommended",
     "dsl": {

agent/templates/ecommerce_customer_service_workflow.json

@@ -2,10 +2,12 @@
     "id": 22,
     "title": {
         "en": "Ecommerce Customer Service Workflow",
+        "de": "Ecommerce Kundenservice Workflow",
         "zh": "电子商务客户服务工作流程"
     },
     "description": {
         "en": "This template helps e-commerce platforms address complex customer needs, such as comparing product features, providing usage support, and coordinating home installation services.",
+        "de": "Diese Vorlage hilft E-Commerce-Plattformen, komplexe Kundenbedürfnisse zu erfüllen, wie z.B. den Vergleich von Produktmerkmalen, die Bereitstellung von Nutzungsunterstützung und die Koordination von Hausinstallationsdiensten.",
         "zh": "该模板可帮助电子商务平台解决复杂的客户需求，例如比较产品功能、提供使用支持和协调家庭安装服务。"
     },
     "canvas_type": "Customer Support",

agent/templates/generate_SEO_blog.json

@@ -2,9 +2,11 @@
     "id": 8,
     "title": {
         "en": "Generate SEO Blog",
+        "de": "SEO Blog generieren",
         "zh": "生成SEO博客"},
     "description": {
         "en": "This is a multi-agent version of the SEO blog generation workflow. It simulates a small team of AI “writers”, where each agent plays a specialized role — just like a real editorial team.",
+        "de": "Dies ist eine Multi-Agenten-Version des Workflows zur Erstellung von SEO-Blogs. Sie simuliert ein kleines Team von KI-„Autoren“, in dem jeder Agent eine spezielle Rolle übernimmt – genau wie in einem echten Redaktionsteam.",
         "zh": "多智能体架构可根据简单的用户输入自动生成完整的SEO博客文章。模拟小型“作家”团队，其中每个智能体扮演一个专业角色——就像真正的编辑团队。"},
     "canvas_type": "Agent",
     "dsl": {

agent/templates/knowledge_base_report.json

@@ -2,9 +2,11 @@
     "id": 20,
     "title": {
         "en": "Report Agent Using Knowledge Base",
+        "de": "Berichtsagent mit Wissensdatenbank",
         "zh": "知识库检索智能体"},
     "description": {
         "en": "A report generation assistant using local knowledge base, with advanced capabilities in task planning, reasoning, and reflective analysis. Recommended for academic research paper Q&A",
+        "de": "Ein Berichtsgenerierungsassistent, der eine lokale Wissensdatenbank nutzt, mit erweiterten Fähigkeiten in Aufgabenplanung, Schlussfolgerung und reflektierender Analyse. Empfohlen für akademische Forschungspapier-Fragen und -Antworten.",
         "zh": "一个使用本地知识库的报告生成助手，具备高级能力，包括任务规划、推理和反思性分析。推荐用于学术研究论文问答。"},
     "canvas_type": "Agent",
     "dsl": {

agent/templates/knowledge_base_report_r.json

@@ -2,9 +2,11 @@
     "id": 21,
     "title": {
         "en": "Report Agent Using Knowledge Base",
+        "de": "Berichtsagent mit Wissensdatenbank",
         "zh": "知识库检索智能体"},
     "description": {
         "en": "A report generation assistant using local knowledge base, with advanced capabilities in task planning, reasoning, and reflective analysis. Recommended for academic research paper Q&A",
+        "de": "Ein Berichtsgenerierungsassistent, der eine lokale Wissensdatenbank nutzt, mit erweiterten Fähigkeiten in Aufgabenplanung, Schlussfolgerung und reflektierender Analyse. Empfohlen für akademische Forschungspapier-Fragen und -Antworten.",
         "zh": "一个使用本地知识库的报告生成助手，具备高级能力，包括任务规划、推理和反思性分析。推荐用于学术研究论文问答。"},
     "canvas_type": "Recommended",
     "dsl": {

agent/templates/market_generate_seo_blog.json

@@ -2,9 +2,11 @@
     "id": 12,
     "title": {
         "en": "Generate SEO Blog",
+        "de": "SEO Blog generieren",
         "zh": "生成SEO博客"},
     "description": {
-        "en": "This workflow automatically generates a complete SEO-optimized blog article based on a simple user input. You don’t need any writing experience. Just provide a topic or short request — the system will handle the rest.",
+        "en": "This workflow automatically generates a complete SEO-optimized blog article based on a simple user input. You don't need any writing experience. Just provide a topic or short request — the system will handle the rest.",
+        "de": "Dieser Workflow generiert automatisch einen vollständigen SEO-optimierten Blogartikel basierend auf einer einfachen Benutzereingabe. Sie benötigen keine Schreiberfahrung. Geben Sie einfach ein Thema oder eine kurze Anfrage ein – das System übernimmt den Rest.",
         "zh": "此工作流根据简单的用户输入自动生成完整的SEO博客文章。你无需任何写作经验，只需提供一个主题或简短请求，系统将处理其余部分。"},
     "canvas_type": "Marketing",
     "dsl": {

agent/templates/seo_blog.json

@@ -2,9 +2,11 @@
     "id": 4,
     "title": {
         "en": "Generate SEO Blog",
+        "de": "SEO Blog generieren",
         "zh": "生成SEO博客"},
     "description": {
-        "en": "This workflow automatically generates a complete SEO-optimized blog article based on a simple user input. You don’t need any writing experience. Just provide a topic or short request — the system will handle the rest.",
+        "en": "This workflow automatically generates a complete SEO-optimized blog article based on a simple user input. You don't need any writing experience. Just provide a topic or short request — the system will handle the rest.",
+        "de": "Dieser Workflow generiert automatisch einen vollständigen SEO-optimierten Blogartikel basierend auf einer einfachen Benutzereingabe. Sie benötigen keine Schreiberfahrung. Geben Sie einfach ein Thema oder eine kurze Anfrage ein – das System übernimmt den Rest.",
         "zh": "此工作流根据简单的用户输入自动生成完整的SEO博客文章。你无需任何写作经验，只需提供一个主题或简短请求，系统将处理其余部分。"},
     "canvas_type": "Recommended",
     "dsl": {

agent/templates/sql_assistant.json

@@ -2,10 +2,12 @@
     "id": 17,
     "title": {
         "en": "SQL Assistant",
+        "de": "SQL Assistent",
         "zh": "SQL助理"},
     "description": {
-        "en": "SQL Assistant is an AI-powered tool that lets business users turn plain-English questions into fully formed SQL queries. Simply type your question (e.g., “Show me last quarter’s top 10 products by revenue”) and SQL Assistant generates the exact SQL, runs it against your database, and returns the results in seconds. ",
+        "en": "SQL Assistant is an AI-powered tool that lets business users turn plain-English questions into fully formed SQL queries. Simply type your question (e.g., 'Show me last quarter's top 10 products by revenue') and SQL Assistant generates the exact SQL, runs it against your database, and returns the results in seconds. ",
-        "zh": "用户能够将简单文本问题转化为完整的SQL查询并输出结果。只需输入您的问题（例如，“展示上个季度前十名按收入排序的产品”），SQL助理就会生成精确的SQL语句，对其运行您的数据库，并几秒钟内返回结果。"},
+        "de": "SQL-Assistent ist ein KI-gestütztes Tool, mit dem Geschäftsanwender einfache englische Fragen in vollständige SQL-Abfragen umwandeln können. Geben Sie einfach Ihre Frage ein (z.B. 'Zeige mir die Top 10 Produkte des letzten Quartals nach Umsatz') und der SQL-Assistent generiert das exakte SQL, führt es gegen Ihre Datenbank aus und liefert die Ergebnisse in Sekunden.",
+        "zh": "用户能够将简单文本问题转化为完整的SQL查询并输出结果。只需输入您的问题（例如，展示上个季度前十名按收入排序的产品），SQL助理就会生成精确的SQL语句，对其运行您的数据库，并几秒钟内返回结果。"},
     "canvas_type": "Marketing",
     "dsl": {
             "components": {
@@ -81,10 +83,10 @@
                                     "value": []
                                 }
                             },
-                            "password": "20010812Yy!",
+                            "password": "",
                             "port": 3306,
                             "sql": "{Agent:WickedGoatsDivide@content}",
-                            "username": "13637682833@163.com"
+                            "username": ""
                         }
                     },
                     "upstream": [
@@ -525,10 +527,10 @@
                                         "value": []
                                     }
                                 },
-                                "password": "20010812Yy!",
+                                "password": "",
                                 "port": 3306,
                                 "sql": "{Agent:WickedGoatsDivide@content}",
-                                "username": "13637682833@163.com"
+                                "username": ""
                             },
                             "label": "ExeSQL",
                             "name": "ExeSQL"

agent/templates/title_chunker.json

@@ -2,10 +2,12 @@
     "id": 25,
     "title": {
         "en": "Title Chunker",
+        "de": "Titel basierte Segmentierung",
         "zh": "标题切片"
     },
     "description": {
         "en": "This template slices the parsed file based on its title structure. It is ideal for documents with well-defined headings, such as product manuals, legal contracts, research reports, and academic papers.",
+        "de": "Diese Vorlage segmentiert die geparste Datei basierend auf ihrer Titelstruktur. Sie eignet sich ideal für Dokumente mit klar definierten Überschriften, wie Produkthandbücher, Verträge, Forschungsberichte und wissenschaftliche Arbeiten.",
         "zh": "此模板将解析后的文件按标题结构进行切片，适用于具有清晰标题层级的文档类型，如产品手册、合同法规、研究报告和学术论文等。"
     },
     "canvas_type": "Ingestion Pipeline",

agent/templates/user_interaction.json

@@ -0,0 +1,519 @@
+{
+    "id": 27,
+    "title": {
+        "en": "Interactive Agent",
+        "zh": "可交互的 Agent"
+    },
+    "description": {
+        "en": "During the Agent’s execution, users can actively intervene and interact with the Agent to adjust or guide its output, ensuring the final result aligns with their intentions.",
+        "zh": "在 Agent 的运行过程中，用户可以随时介入，与 Agent 进行交互，以调整或引导生成结果，使最终输出更符合预期。"
+    },
+    "canvas_type": "Agent",
+    "dsl": {
+        "components": {
+            "Agent:LargeFliesMelt": {
+            "downstream": [
+                "UserFillUp:GoldBroomsRelate"
+            ],
+            "obj": {
+                "component_name": "Agent",
+                "params": {
+                "cite": true,
+                "delay_after_error": 1,
+                "description": "",
+                "exception_default_value": "",
+                "exception_goto": [],
+                "exception_method": "",
+                "frequencyPenaltyEnabled": false,
+                "frequency_penalty": 0.7,
+                "llm_id": "qwen-turbo@Tongyi-Qianwen",
+                "maxTokensEnabled": false,
+                "max_retries": 3,
+                "max_rounds": 1,
+                "max_tokens": 256,
+                "mcp": [],
+                "message_history_window_size": 12,
+                "outputs": {
+                    "content": {
+                    "type": "string",
+                    "value": ""
+                    },
+                    "structured": {}
+                },
+                "presencePenaltyEnabled": false,
+                "presence_penalty": 0.4,
+                "prompts": [
+                    {
+                    "content": "User query:{sys.query}",
+                    "role": "user"
+                    }
+                ],
+                "sys_prompt": "<role>\nYou are the Planning Agent in a multi-agent RAG workflow.\nYour sole job is to design a crisp, executable Search Plan for the next agent. Do not search or answer the user’s question.\n</role>\n<objectives>\nUnderstand the user’s task and decompose it into evidence-seeking steps.\nProduce high-quality queries and retrieval settings tailored to the task type (fact lookup, multi-hop reasoning, comparison, statistics, how-to, etc.).\nIdentify missing information that would materially change the plan (≤3 concise questions).\nOptimize for source trustworthiness, diversity, and recency; define stopping criteria to avoid over-searching.\nAnswer in 150 words.\n<objectives>",
+                "temperature": 0.1,
+                "temperatureEnabled": false,
+                "tools": [],
+                "topPEnabled": false,
+                "top_p": 0.3,
+                "user_prompt": "",
+                "visual_files_var": ""
+                }
+            },
+            "upstream": [
+                "begin"
+            ]
+            },
+            "Agent:TangyWordsType": {
+            "downstream": [
+                "Message:FreshWallsStudy"
+            ],
+            "obj": {
+                "component_name": "Agent",
+                "params": {
+                "cite": true,
+                "delay_after_error": 1,
+                "description": "",
+                "exception_default_value": "",
+                "exception_goto": [],
+                "exception_method": "",
+                "frequencyPenaltyEnabled": false,
+                "frequency_penalty": 0.7,
+                "llm_id": "qwen-turbo@Tongyi-Qianwen",
+                "maxTokensEnabled": false,
+                "max_retries": 3,
+                "max_rounds": 1,
+                "max_tokens": 256,
+                "mcp": [],
+                "message_history_window_size": 12,
+                "outputs": {
+                    "content": {
+                    "type": "string",
+                    "value": ""
+                    },
+                    "structured": {}
+                },
+                "presencePenaltyEnabled": false,
+                "presence_penalty": 0.4,
+                "prompts": [
+                    {
+                    "content": "Search Plan: {Agent:LargeFliesMelt@content}\n\n\n\nAwait Response feedback:{UserFillUp:GoldBroomsRelate@instructions}\n",
+                    "role": "user"
+                    }
+                ],
+                "sys_prompt": "<role>\nYou are the Search Agent.\nYour job is to execute the approved Search Plan, integrate the Await Response feedback, retrieve evidence, and produce a well-grounded answer.\n</role>\n<objectives>\nTranslate the plan + feedback into concrete searches.\nCollect diverse, trustworthy, and recent evidence meeting the plan’s evidence bar.\nSynthesize a concise answer; include citations next to claims they support.\nIf evidence is insufficient or conflicting, clearly state limitations and propose next steps.\n</objectives>\n <tools>\nRetrieval: You must use Retrieval to do the search.\n </tools>\n",
+                "temperature": 0.1,
+                "temperatureEnabled": false,
+                "tools": [
+                    {
+                    "component_name": "Retrieval",
+                    "name": "Retrieval",
+                    "params": {
+                        "cross_languages": [],
+                        "description": "",
+                        "empty_response": "",
+                        "kb_ids": [],
+                        "keywords_similarity_weight": 0.7,
+                        "outputs": {
+                        "formalized_content": {
+                            "type": "string",
+                            "value": ""
+                        },
+                        "json": {
+                            "type": "Array<Object>",
+                            "value": []
+                        }
+                        },
+                        "rerank_id": "",
+                        "similarity_threshold": 0.2,
+                        "toc_enhance": false,
+                        "top_k": 1024,
+                        "top_n": 8,
+                        "use_kg": false
+                    }
+                    }
+                ],
+                "topPEnabled": false,
+                "top_p": 0.3,
+                "user_prompt": "",
+                "visual_files_var": ""
+                }
+            },
+            "upstream": [
+                "UserFillUp:GoldBroomsRelate"
+            ]
+            },
+            "Message:FreshWallsStudy": {
+            "downstream": [],
+            "obj": {
+                "component_name": "Message",
+                "params": {
+                "content": [
+                    "{Agent:TangyWordsType@content}"
+                ]
+                }
+            },
+            "upstream": [
+                "Agent:TangyWordsType"
+            ]
+            },
+            "UserFillUp:GoldBroomsRelate": {
+            "downstream": [
+                "Agent:TangyWordsType"
+            ],
+            "obj": {
+                "component_name": "UserFillUp",
+                "params": {
+                "enable_tips": true,
+                "inputs": {
+                    "instructions": {
+                    "name": "instructions",
+                    "optional": false,
+                    "options": [],
+                    "type": "paragraph"
+                    }
+                },
+                "outputs": {
+                    "instructions": {
+                    "name": "instructions",
+                    "optional": false,
+                    "options": [],
+                    "type": "paragraph"
+                    }
+                },
+                "tips": "Here is my search plan:\n{Agent:LargeFliesMelt@content}\nAre you okay with it?"
+                }
+            },
+            "upstream": [
+                "Agent:LargeFliesMelt"
+            ]
+            },
+            "begin": {
+            "downstream": [
+                "Agent:LargeFliesMelt"
+            ],
+            "obj": {
+                "component_name": "Begin",
+                "params": {}
+            },
+            "upstream": []
+            }
+        },
+        "globals": {
+            "sys.conversation_turns": 0,
+            "sys.files": [],
+            "sys.query": "",
+            "sys.user_id": ""
+        },
+        "graph": {
+            "edges": [
+            {
+                "data": {
+                "isHovered": false
+                },
+                "id": "xy-edge__beginstart-Agent:LargeFliesMeltend",
+                "source": "begin",
+                "sourceHandle": "start",
+                "target": "Agent:LargeFliesMelt",
+                "targetHandle": "end"
+            },
+            {
+                "data": {
+                "isHovered": false
+                },
+                "id": "xy-edge__Agent:LargeFliesMeltstart-UserFillUp:GoldBroomsRelateend",
+                "source": "Agent:LargeFliesMelt",
+                "sourceHandle": "start",
+                "target": "UserFillUp:GoldBroomsRelate",
+                "targetHandle": "end"
+            },
+            {
+                "data": {
+                "isHovered": false
+                },
+                "id": "xy-edge__UserFillUp:GoldBroomsRelatestart-Agent:TangyWordsTypeend",
+                "source": "UserFillUp:GoldBroomsRelate",
+                "sourceHandle": "start",
+                "target": "Agent:TangyWordsType",
+                "targetHandle": "end"
+            },
+            {
+                "id": "xy-edge__Agent:TangyWordsTypetool-Tool:NastyBatsGoend",
+                "source": "Agent:TangyWordsType",
+                "sourceHandle": "tool",
+                "target": "Tool:NastyBatsGo",
+                "targetHandle": "end"
+            },
+            {
+                "id": "xy-edge__Agent:TangyWordsTypestart-Message:FreshWallsStudyend",
+                "source": "Agent:TangyWordsType",
+                "sourceHandle": "start",
+                "target": "Message:FreshWallsStudy",
+                "targetHandle": "end"
+            }
+            ],
+            "nodes": [
+            {
+                "data": {
+                "label": "Begin",
+                "name": "begin"
+                },
+                "dragging": false,
+                "id": "begin",
+                "measured": {
+                "height": 50,
+                "width": 200
+                },
+                "position": {
+                "x": 154.9008789064451,
+                "y": 119.51001744285344
+                },
+                "selected": false,
+                "sourcePosition": "left",
+                "targetPosition": "right",
+                "type": "beginNode"
+            },
+            {
+                "data": {
+                "form": {
+                    "cite": true,
+                    "delay_after_error": 1,
+                    "description": "",
+                    "exception_default_value": "",
+                    "exception_goto": [],
+                    "exception_method": "",
+                    "frequencyPenaltyEnabled": false,
+                    "frequency_penalty": 0.7,
+                    "llm_id": "qwen-turbo@Tongyi-Qianwen",
+                    "maxTokensEnabled": false,
+                    "max_retries": 3,
+                    "max_rounds": 1,
+                    "max_tokens": 256,
+                    "mcp": [],
+                    "message_history_window_size": 12,
+                    "outputs": {
+                    "content": {
+                        "type": "string",
+                        "value": ""
+                    },
+                    "structured": {}
+                    },
+                    "presencePenaltyEnabled": false,
+                    "presence_penalty": 0.4,
+                    "prompts": [
+                    {
+                        "content": "User query:{sys.query}",
+                        "role": "user"
+                    }
+                    ],
+                    "sys_prompt": "<role>\nYou are the Planning Agent in a multi-agent RAG workflow.\nYour sole job is to design a crisp, executable Search Plan for the next agent. Do not search or answer the user’s question.\n</role>\n<objectives>\nUnderstand the user’s task and decompose it into evidence-seeking steps.\nProduce high-quality queries and retrieval settings tailored to the task type (fact lookup, multi-hop reasoning, comparison, statistics, how-to, etc.).\nIdentify missing information that would materially change the plan (≤3 concise questions).\nOptimize for source trustworthiness, diversity, and recency; define stopping criteria to avoid over-searching.\nAnswer in 150 words.\n<objectives>",
+                    "temperature": 0.1,
+                    "temperatureEnabled": false,
+                    "tools": [],
+                    "topPEnabled": false,
+                    "top_p": 0.3,
+                    "user_prompt": "",
+                    "visual_files_var": ""
+                },
+                "label": "Agent",
+                "name": "Planning Agent"
+                },
+                "dragging": false,
+                "id": "Agent:LargeFliesMelt",
+                "measured": {
+                "height": 90,
+                "width": 200
+                },
+                "position": {
+                "x": 443.96309330796714,
+                "y": 104.61370811205677
+                },
+                "selected": false,
+                "sourcePosition": "right",
+                "targetPosition": "left",
+                "type": "agentNode"
+            },
+            {
+                "data": {
+                "form": {
+                    "enable_tips": true,
+                    "inputs": {
+                    "instructions": {
+                        "name": "instructions",
+                        "optional": false,
+                        "options": [],
+                        "type": "paragraph"
+                    }
+                    },
+                    "outputs": {
+                    "instructions": {
+                        "name": "instructions",
+                        "optional": false,
+                        "options": [],
+                        "type": "paragraph"
+                    }
+                    },
+                    "tips": "Here is my search plan:\n{Agent:LargeFliesMelt@content}\nAre you okay with it?"
+                },
+                "label": "UserFillUp",
+                "name": "Await Response"
+                },
+                "dragging": false,
+                "id": "UserFillUp:GoldBroomsRelate",
+                "measured": {
+                "height": 50,
+                "width": 200
+                },
+                "position": {
+                "x": 683.3409492927474,
+                "y": 116.76274137645598
+                },
+                "selected": false,
+                "sourcePosition": "right",
+                "targetPosition": "left",
+                "type": "ragNode"
+            },
+            {
+                "data": {
+                "form": {
+                    "cite": true,
+                    "delay_after_error": 1,
+                    "description": "",
+                    "exception_default_value": "",
+                    "exception_goto": [],
+                    "exception_method": "",
+                    "frequencyPenaltyEnabled": false,
+                    "frequency_penalty": 0.7,
+                    "llm_id": "qwen-turbo@Tongyi-Qianwen",
+                    "maxTokensEnabled": false,
+                    "max_retries": 3,
+                    "max_rounds": 1,
+                    "max_tokens": 256,
+                    "mcp": [],
+                    "message_history_window_size": 12,
+                    "outputs": {
+                    "content": {
+                        "type": "string",
+                        "value": ""
+                    },
+                    "structured": {}
+                    },
+                    "presencePenaltyEnabled": false,
+                    "presence_penalty": 0.4,
+                    "prompts": [
+                    {
+                        "content": "Search Plan: {Agent:LargeFliesMelt@content}\n\n\n\nAwait Response feedback:{UserFillUp:GoldBroomsRelate@instructions}\n",
+                        "role": "user"
+                    }
+                    ],
+                    "sys_prompt": "<role>\nYou are the Search Agent.\nYour job is to execute the approved Search Plan, integrate the Await Response feedback, retrieve evidence, and produce a well-grounded answer.\n</role>\n<objectives>\nTranslate the plan + feedback into concrete searches.\nCollect diverse, trustworthy, and recent evidence meeting the plan’s evidence bar.\nSynthesize a concise answer; include citations next to claims they support.\nIf evidence is insufficient or conflicting, clearly state limitations and propose next steps.\n</objectives>\n <tools>\nRetrieval: You must use Retrieval to do the search.\n </tools>\n",
+                    "temperature": 0.1,
+                    "temperatureEnabled": false,
+                    "tools": [
+                    {
+                        "component_name": "Retrieval",
+                        "name": "Retrieval",
+                        "params": {
+                        "cross_languages": [],
+                        "description": "",
+                        "empty_response": "",
+                        "kb_ids": [],
+                        "keywords_similarity_weight": 0.7,
+                        "outputs": {
+                            "formalized_content": {
+                            "type": "string",
+                            "value": ""
+                            },
+                            "json": {
+                            "type": "Array<Object>",
+                            "value": []
+                            }
+                        },
+                        "rerank_id": "",
+                        "similarity_threshold": 0.2,
+                        "toc_enhance": false,
+                        "top_k": 1024,
+                        "top_n": 8,
+                        "use_kg": false
+                        }
+                    }
+                    ],
+                    "topPEnabled": false,
+                    "top_p": 0.3,
+                    "user_prompt": "",
+                    "visual_files_var": ""
+                },
+                "label": "Agent",
+                "name": "Search Agent"
+                },
+                "dragging": false,
+                "id": "Agent:TangyWordsType",
+                "measured": {
+                "height": 90,
+                "width": 200
+                },
+                "position": {
+                "x": 944.6411255659472,
+                "y": 99.84499066368488
+                },
+                "selected": true,
+                "sourcePosition": "right",
+                "targetPosition": "left",
+                "type": "agentNode"
+            },
+            {
+                "data": {
+                "form": {
+                    "description": "This is an agent for a specific task.",
+                    "user_prompt": "This is the order you need to send to the agent."
+                },
+                "label": "Tool",
+                "name": "flow.tool_0"
+                },
+                "id": "Tool:NastyBatsGo",
+                "measured": {
+                "height": 50,
+                "width": 200
+                },
+                "position": {
+                "x": 862.6411255659472,
+                "y": 239.84499066368488
+                },
+                "sourcePosition": "right",
+                "targetPosition": "left",
+                "type": "toolNode"
+            },
+            {
+                "data": {
+                "form": {
+                    "content": [
+                    "{Agent:TangyWordsType@content}"
+                    ]
+                },
+                "label": "Message",
+                "name": "Message"
+                },
+                "dragging": false,
+                "id": "Message:FreshWallsStudy",
+                "measured": {
+                "height": 50,
+                "width": 200
+                },
+                "position": {
+                "x": 1216.7057997987163,
+                "y": 120.48541298149814
+                },
+                "selected": false,
+                "sourcePosition": "right",
+                "targetPosition": "left",
+                "type": "messageNode"
+            }
+            ]
+        },
+        "history": [],
+        "messages": [],
+        "path": [],
+        "retrieval": [],
+        "variables": {}
+        },
+        "avatar":
+    "data:image/png;base64,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"
+}

agent/test/client.py

@@ -16,7 +16,7 @@
 import argparse
 import os
 from agent.canvas import Canvas
-from api import settings
+from common import settings
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()

agent/tools/arxiv.py

@@ -19,7 +19,7 @@ import time
 from abc import ABC
 import arxiv
 from agent.tools.base import ToolParamBase, ToolMeta, ToolBase
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 class ArXivParam(ToolParamBase):
@@ -63,12 +63,18 @@ class ArXiv(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 12)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("ArXiv processing"):
+            return
+
         if not kwargs.get("query"):
             self.set_output("formalized_content", "")
             return ""
 
         last_e = ""
         for _ in range(self._param.max_retries+1):
+            if self.check_if_canceled("ArXiv processing"):
+                return
+
             try:
                 sort_choices = {"relevance": arxiv.SortCriterion.Relevance,
                                 "lastUpdatedDate": arxiv.SortCriterion.LastUpdatedDate,
@@ -79,12 +85,20 @@ class ArXiv(ToolBase, ABC):
                     max_results=self._param.top_n,
                     sort_by=sort_choices[self._param.sort_by]
                 )
-                self._retrieve_chunks(list(arxiv_client.results(search)),
+                results = list(arxiv_client.results(search))
+
+                if self.check_if_canceled("ArXiv processing"):
+                    return
+
+                self._retrieve_chunks(results,
                                       get_title=lambda r: r.title,
                                       get_url=lambda r: r.pdf_url,
                                       get_content=lambda r: r.summary)
                 return self.output("formalized_content")
             except Exception as e:
+                if self.check_if_canceled("ArXiv processing"):
+                    return
+
                 last_e = e
                 logging.exception(f"ArXiv error: {e}")
                 time.sleep(self._param.delay_after_error)

agent/tools/base.py

@@ -20,10 +20,9 @@ from copy import deepcopy
 from functools import partial
 from typing import TypedDict, List, Any
 from agent.component.base import ComponentParamBase, ComponentBase
-from api.utils import hash_str2int
+from common.misc_utils import hash_str2int
-from rag.llm.chat_model import ToolCallSession
 from rag.prompts.generator import kb_prompt
-from rag.utils.mcp_tool_call_conn import MCPToolCallSession
+from common.mcp_tool_call_conn import MCPToolCallSession, ToolCallSession
 from timeit import default_timer as timer
 
 
@@ -125,6 +124,9 @@ class ToolBase(ComponentBase):
         return self._param.get_meta()
 
     def invoke(self, **kwargs):
+        if self.check_if_canceled("Tool processing"):
+            return
+
         self.set_output("_created_time", time.perf_counter())
         try:
             res = self._invoke(**kwargs)

agent/tools/code_exec.py

@@ -13,16 +13,20 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import ast
 import base64
+import json
 import logging
 import os
 from abc import ABC
-from strenum import StrEnum
 from typing import Optional
+
 from pydantic import BaseModel, Field, field_validator
-from agent.tools.base import ToolParamBase, ToolBase, ToolMeta
+from strenum import StrEnum
-from api import settings
+
-from api.utils.api_utils import timeout
+from agent.tools.base import ToolBase, ToolMeta, ToolParamBase
+from common import settings
+from common.connection_utils import timeout
 
 
 class Language(StrEnum):
@@ -62,7 +66,7 @@ class CodeExecParam(ToolParamBase):
     """
 
     def __init__(self):
-        self.meta:ToolMeta = {
+        self.meta: ToolMeta = {
             "name": "execute_code",
             "description": """
 This tool has a sandbox that can execute code written in 'Python'/'Javascript'. It recieves a piece of code and return a Json string.
@@ -99,16 +103,12 @@ module.exports = { main };
                     "enum": ["python", "javascript"],
                     "required": True,
                 },
-                "script": {
+                "script": {"type": "string", "description": "A piece of code in right format. There MUST be main function.", "required": True},
-                    "type": "string",
+            },
-                    "description": "A piece of code in right format. There MUST be main function.",
-                    "required": True
-                }
-            }
         }
         super().__init__()
         self.lang = Language.PYTHON.value
-        self.script = "def main(arg1: str, arg2: str) -> dict: return {\"result\": arg1 + arg2}"
+        self.script = 'def main(arg1: str, arg2: str) -> dict: return {"result": arg1 + arg2}'
         self.arguments = {}
         self.outputs = {"result": {"value": "", "type": "string"}}
 
@@ -119,18 +119,18 @@ module.exports = { main };
     def get_input_form(self) -> dict[str, dict]:
         res = {}
         for k, v in self.arguments.items():
-            res[k] = {
+            res[k] = {"type": "line", "name": k}
-                "type": "line",
-                "name": k
-            }
         return res
 
 
 class CodeExec(ToolBase, ABC):
     component_name = "CodeExec"
 
-    @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
+    @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10 * 60)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("CodeExec processing"):
+            return
+
         lang = kwargs.get("lang", self._param.lang)
         script = kwargs.get("script", self._param.script)
         arguments = {}
@@ -140,24 +140,33 @@ class CodeExec(ToolBase, ABC):
                 continue
             arguments[k] = self._canvas.get_variable_value(v) if v else None
 
-        self._execute_code(
+        self._execute_code(language=lang, code=script, arguments=arguments)
-            language=lang,
-            code=script,
-            arguments=arguments
-        )
 
     def _execute_code(self, language: str, code: str, arguments: dict):
         import requests
 
+        if self.check_if_canceled("CodeExec execution"):
+            return
+
         try:
             code_b64 = self._encode_code(code)
             code_req = CodeExecutionRequest(code_b64=code_b64, language=language, arguments=arguments).model_dump()
         except Exception as e:
+            if self.check_if_canceled("CodeExec execution"):
+                return
+
             self.set_output("_ERROR", "construct code request error: " + str(e))
 
         try:
-            resp = requests.post(url=f"http://{settings.SANDBOX_HOST}:9385/run", json=code_req, timeout=int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
+            if self.check_if_canceled("CodeExec execution"):
+                return "Task has been canceled"
+
+            resp = requests.post(url=f"http://{settings.SANDBOX_HOST}:9385/run", json=code_req, timeout=int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10 * 60)))
             logging.info(f"http://{settings.SANDBOX_HOST}:9385/run,  code_req: {code_req}, resp.status_code {resp.status_code}:")
+
+            if self.check_if_canceled("CodeExec execution"):
+                return "Task has been canceled"
+
             if resp.status_code != 200:
                 resp.raise_for_status()
             body = resp.json()
@@ -166,30 +175,17 @@ class CodeExec(ToolBase, ABC):
                 if stderr:
                     self.set_output("_ERROR", stderr)
                     return
-                try:
+                raw_stdout = body.get("stdout", "")
-                    rt = eval(body.get("stdout", ""))
+                parsed_stdout = self._deserialize_stdout(raw_stdout)
-                except Exception:
+                logging.info(f"[CodeExec]: http://{settings.SANDBOX_HOST}:9385/run -> {parsed_stdout}")
-                    rt = body.get("stdout", "")
+                self._populate_outputs(parsed_stdout, raw_stdout)
-                logging.info(f"http://{settings.SANDBOX_HOST}:9385/run -> {rt}")
-                if isinstance(rt, tuple):
-                    for i, (k, o) in enumerate(self._param.outputs.items()):
-                        if k.find("_") == 0:
-                            continue
-                        o["value"] = rt[i]
-                elif isinstance(rt, dict):
-                    for i, (k, o) in enumerate(self._param.outputs.items()):
-                        if k not in rt or k.find("_") == 0:
-                            continue
-                        o["value"] = rt[k]
-                else:
-                    for i, (k, o) in enumerate(self._param.outputs.items()):
-                        if k.find("_") == 0:
-                            continue
-                        o["value"] = rt
             else:
                 self.set_output("_ERROR", "There is no response from sandbox")
 
         except Exception as e:
+            if self.check_if_canceled("CodeExec execution"):
+                return
+
             self.set_output("_ERROR", "Exception executing code: " + str(e))
 
         return self.output()
@@ -199,3 +195,149 @@ class CodeExec(ToolBase, ABC):
 
     def thoughts(self) -> str:
         return "Running a short script to process data."
+
+    def _deserialize_stdout(self, stdout: str):
+        text = str(stdout).strip()
+        if not text:
+            return ""
+        for loader in (json.loads, ast.literal_eval):
+            try:
+                return loader(text)
+            except Exception:
+                continue
+        return text
+
+    def _coerce_output_value(self, value, expected_type: Optional[str]):
+        if expected_type is None:
+            return value
+
+        etype = expected_type.strip().lower()
+        inner_type = None
+        if etype.startswith("array<") and etype.endswith(">"):
+            inner_type = etype[6:-1].strip()
+            etype = "array"
+
+        try:
+            if etype == "string":
+                return "" if value is None else str(value)
+
+            if etype == "number":
+                if value is None or value == "":
+                    return None
+                if isinstance(value, (int, float)):
+                    return value
+                if isinstance(value, str):
+                    try:
+                        return float(value)
+                    except Exception:
+                        return value
+                return float(value)
+
+            if etype == "boolean":
+                if isinstance(value, bool):
+                    return value
+                if isinstance(value, str):
+                    lv = value.lower()
+                    if lv in ("true", "1", "yes", "y", "on"):
+                        return True
+                    if lv in ("false", "0", "no", "n", "off"):
+                        return False
+                return bool(value)
+
+            if etype == "array":
+                candidate = value
+                if isinstance(candidate, str):
+                    parsed = self._deserialize_stdout(candidate)
+                    candidate = parsed
+                if isinstance(candidate, tuple):
+                    candidate = list(candidate)
+                if not isinstance(candidate, list):
+                    candidate = [] if candidate is None else [candidate]
+
+                if inner_type == "string":
+                    return ["" if v is None else str(v) for v in candidate]
+                if inner_type == "number":
+                    coerced = []
+                    for v in candidate:
+                        try:
+                            if v is None or v == "":
+                                coerced.append(None)
+                            elif isinstance(v, (int, float)):
+                                coerced.append(v)
+                            else:
+                                coerced.append(float(v))
+                        except Exception:
+                            coerced.append(v)
+                    return coerced
+                return candidate
+
+            if etype == "object":
+                if isinstance(value, dict):
+                    return value
+                if isinstance(value, str):
+                    parsed = self._deserialize_stdout(value)
+                    if isinstance(parsed, dict):
+                        return parsed
+                return value
+        except Exception:
+            return value
+
+        return value
+
+    def _populate_outputs(self, parsed_stdout, raw_stdout: str):
+        outputs_items = list(self._param.outputs.items())
+        logging.info(f"[CodeExec]: outputs schema keys: {[k for k, _ in outputs_items]}")
+        if not outputs_items:
+            return
+
+        if isinstance(parsed_stdout, dict):
+            for key, meta in outputs_items:
+                if key.startswith("_"):
+                    continue
+                val = self._get_by_path(parsed_stdout, key)
+                coerced = self._coerce_output_value(val, meta.get("type"))
+                logging.info(f"[CodeExec]: populate dict key='{key}' raw='{val}' coerced='{coerced}'")
+                self.set_output(key, coerced)
+            return
+
+        if isinstance(parsed_stdout, (list, tuple)):
+            for idx, (key, meta) in enumerate(outputs_items):
+                if key.startswith("_"):
+                    continue
+                val = parsed_stdout[idx] if idx < len(parsed_stdout) else None
+                coerced = self._coerce_output_value(val, meta.get("type"))
+                logging.info(f"[CodeExec]: populate list key='{key}' raw='{val}' coerced='{coerced}'")
+                self.set_output(key, coerced)
+            return
+
+        default_val = parsed_stdout if parsed_stdout is not None else raw_stdout
+        for idx, (key, meta) in enumerate(outputs_items):
+            if key.startswith("_"):
+                continue
+            val = default_val if idx == 0 else None
+            coerced = self._coerce_output_value(val, meta.get("type"))
+            logging.info(f"[CodeExec]: populate scalar key='{key}' raw='{val}' coerced='{coerced}'")
+            self.set_output(key, coerced)
+
+    def _get_by_path(self, data, path: str):
+        if not path:
+            return None
+        cur = data
+        for part in path.split("."):
+            part = part.strip()
+            if not part:
+                return None
+            if isinstance(cur, dict):
+                cur = cur.get(part)
+            elif isinstance(cur, list):
+                try:
+                    idx = int(part)
+                    cur = cur[idx]
+                except Exception:
+                    return None
+            else:
+                return None
+            if cur is None:
+                return None
+        logging.info(f"[CodeExec]: resolve path '{path}' -> {cur}")
+        return cur

agent/tools/crawler.py

@@ -52,6 +52,9 @@ class Crawler(ToolBase, ABC):
             return Crawler.be_output(f"An unexpected error occurred: {str(e)}")
 
     async def get_web(self, url):
+        if self.check_if_canceled("Crawler async operation"):
+            return
+
         proxy = self._param.proxy if self._param.proxy else None
         async with AsyncWebCrawler(verbose=True, proxy=proxy) as crawler:
             result = await crawler.arun(
@@ -59,6 +62,9 @@ class Crawler(ToolBase, ABC):
                 bypass_cache=True
             )
 
+            if self.check_if_canceled("Crawler async operation"):
+                return
+
             if self._param.extract_type == 'html':
                 return result.cleaned_html
             elif self._param.extract_type == 'markdown':

agent/tools/deepl.py

@@ -46,11 +46,16 @@ class DeepL(ComponentBase, ABC):
     component_name = "DeepL"
 
     def _run(self, history, **kwargs):
+        if self.check_if_canceled("DeepL processing"):
+            return
         ans = self.get_input()
         ans = " - ".join(ans["content"]) if "content" in ans else ""
         if not ans:
             return DeepL.be_output("")
 
+        if self.check_if_canceled("DeepL processing"):
+            return
+
         try:
             translator = deepl.Translator(self._param.auth_key)
             result = translator.translate_text(ans, source_lang=self._param.source_lang,
@@ -58,4 +63,6 @@ class DeepL(ComponentBase, ABC):
 
             return DeepL.be_output(result.text)
         except Exception as e:
+            if self.check_if_canceled("DeepL processing"):
+                return
             DeepL.be_output("**Error**:" + str(e))

agent/tools/duckduckgo.py

@@ -19,7 +19,7 @@ import time
 from abc import ABC
 from duckduckgo_search import DDGS
 from agent.tools.base import ToolMeta, ToolParamBase, ToolBase
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 class DuckDuckGoParam(ToolParamBase):
@@ -75,17 +75,30 @@ class DuckDuckGo(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 12)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("DuckDuckGo processing"):
+            return
+
         if not kwargs.get("query"):
             self.set_output("formalized_content", "")
             return ""
 
         last_e = ""
         for _ in range(self._param.max_retries+1):
+            if self.check_if_canceled("DuckDuckGo processing"):
+                return
+
             try:
                 if kwargs.get("topic", "general") == "general":
                     with DDGS() as ddgs:
+                        if self.check_if_canceled("DuckDuckGo processing"):
+                            return
+
                         # {'title': '', 'href': '', 'body': ''}
                         duck_res = ddgs.text(kwargs["query"], max_results=self._param.top_n)
+
+                        if self.check_if_canceled("DuckDuckGo processing"):
+                            return
+
                         self._retrieve_chunks(duck_res,
                                               get_title=lambda r: r["title"],
                                               get_url=lambda r: r.get("href", r.get("url")),
@@ -94,8 +107,15 @@ class DuckDuckGo(ToolBase, ABC):
                         return self.output("formalized_content")
                 else:
                     with DDGS() as ddgs:
+                        if self.check_if_canceled("DuckDuckGo processing"):
+                            return
+
                         # {'date': '', 'title': '', 'body': '', 'url': '', 'image': '', 'source': ''}
                         duck_res = ddgs.news(kwargs["query"], max_results=self._param.top_n)
+
+                        if self.check_if_canceled("DuckDuckGo processing"):
+                            return
+
                         self._retrieve_chunks(duck_res,
                                               get_title=lambda r: r["title"],
                                               get_url=lambda r: r.get("href", r.get("url")),
@@ -103,6 +123,9 @@ class DuckDuckGo(ToolBase, ABC):
                         self.set_output("json", duck_res)
                         return self.output("formalized_content")
             except Exception as e:
+                if self.check_if_canceled("DuckDuckGo processing"):
+                    return
+
                 last_e = e
                 logging.exception(f"DuckDuckGo error: {e}")
                 time.sleep(self._param.delay_after_error)

agent/tools/email.py

@@ -25,7 +25,7 @@ from email.header import Header
 from email.utils import formataddr
 
 from agent.tools.base import ToolParamBase, ToolBase, ToolMeta
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 class EmailParam(ToolParamBase):
@@ -101,19 +101,27 @@ class Email(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 60)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("Email processing"):
+            return
+
         if not kwargs.get("to_email"):
             self.set_output("success", False)
             return ""
 
         last_e = ""
         for _ in range(self._param.max_retries+1):
+            if self.check_if_canceled("Email processing"):
+                return
+
             try:
                 # Parse JSON string passed from upstream
                 email_data = kwargs
 
                 # Validate required fields
                 if "to_email" not in email_data:
-                    return Email.be_output("Missing required field: to_email")
+                    self.set_output("_ERROR", "Missing required field: to_email")
+                    self.set_output("success", False)
+                    return False
 
                 # Create email object
                 msg = MIMEMultipart('alternative')
@@ -133,6 +141,9 @@ class Email(ToolBase, ABC):
                 # Connect to SMTP server and send
                 logging.info(f"Connecting to SMTP server {self._param.smtp_server}:{self._param.smtp_port}")
 
+                if self.check_if_canceled("Email processing"):
+                    return
+
                 context = smtplib.ssl.create_default_context()
                 with smtplib.SMTP(self._param.smtp_server, self._param.smtp_port) as server:
                     server.ehlo()
@@ -149,6 +160,10 @@ class Email(ToolBase, ABC):
 
                     # Send email
                     logging.info(f"Sending email to recipients: {recipients}")
+
+                    if self.check_if_canceled("Email processing"):
+                        return
+
                     try:
                         server.send_message(msg, self._param.email, recipients)
                         success = True

agent/tools/exesql.py

@@ -22,7 +22,7 @@ import pymysql
 import psycopg2
 import pyodbc
 from agent.tools.base import ToolParamBase, ToolBase, ToolMeta
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 class ExeSQLParam(ToolParamBase):
@@ -81,6 +81,8 @@ class ExeSQL(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 60)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("ExeSQL processing"):
+            return
 
         def convert_decimals(obj):
             from decimal import Decimal
@@ -96,6 +98,9 @@ class ExeSQL(ToolBase, ABC):
         if not sql:
             raise Exception("SQL for `ExeSQL` MUST not be empty.")
 
+        if self.check_if_canceled("ExeSQL processing"):
+            return
+
         vars = self.get_input_elements_from_text(sql)
         args = {}
         for k, o in vars.items():
@@ -108,6 +113,9 @@ class ExeSQL(ToolBase, ABC):
             self.set_input_value(k, args[k])
         sql = self.string_format(sql, args)
 
+        if self.check_if_canceled("ExeSQL processing"):
+            return
+
         sqls = sql.split(";")
         if self._param.db_type in ["mysql", "mariadb"]:
             db = pymysql.connect(db=self._param.database, user=self._param.username, host=self._param.host,
@@ -181,6 +189,10 @@ class ExeSQL(ToolBase, ABC):
             sql_res = []
             formalized_content = []
             for single_sql in sqls:
+                if self.check_if_canceled("ExeSQL processing"):
+                    ibm_db.close(conn)
+                    return
+
                 single_sql = single_sql.replace("```", "").strip()
                 if not single_sql:
                     continue
@@ -190,6 +202,9 @@ class ExeSQL(ToolBase, ABC):
                 rows = []
                 row = ibm_db.fetch_assoc(stmt)
                 while row and len(rows) < self._param.max_records:
+                    if self.check_if_canceled("ExeSQL processing"):
+                        ibm_db.close(conn)
+                        return
                     rows.append(row)
                     row = ibm_db.fetch_assoc(stmt)
 
@@ -220,6 +235,11 @@ class ExeSQL(ToolBase, ABC):
         sql_res = []
         formalized_content = []
         for single_sql in sqls:
+            if self.check_if_canceled("ExeSQL processing"):
+                cursor.close()
+                db.close()
+                return
+
             single_sql = single_sql.replace('```','')
             if not single_sql:
                 continue
@@ -244,6 +264,9 @@ class ExeSQL(ToolBase, ABC):
             sql_res.append(convert_decimals(single_res.to_dict(orient='records')))
             formalized_content.append(single_res.to_markdown(index=False, floatfmt=".6f"))
 
+        cursor.close()
+        db.close()
+
         self.set_output("json", sql_res)
         self.set_output("formalized_content", "\n\n".join(formalized_content))
         return self.output("formalized_content")

agent/tools/github.py

@@ -19,7 +19,7 @@ import time
 from abc import ABC
 import requests
 from agent.tools.base import ToolParamBase, ToolMeta, ToolBase
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 class GitHubParam(ToolParamBase):
@@ -59,17 +59,27 @@ class GitHub(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 12)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("GitHub processing"):
+            return
+
         if not kwargs.get("query"):
             self.set_output("formalized_content", "")
             return ""
 
         last_e = ""
         for _ in range(self._param.max_retries+1):
+            if self.check_if_canceled("GitHub processing"):
+                return
+
             try:
                 url = 'https://api.github.com/search/repositories?q=' + kwargs["query"] + '&sort=stars&order=desc&per_page=' + str(
                     self._param.top_n)
                 headers = {"Content-Type": "application/vnd.github+json", "X-GitHub-Api-Version": '2022-11-28'}
                 response = requests.get(url=url, headers=headers).json()
+
+                if self.check_if_canceled("GitHub processing"):
+                    return
+
                 self._retrieve_chunks(response['items'],
                                       get_title=lambda r: r["name"],
                                       get_url=lambda r: r["html_url"],
@@ -77,6 +87,9 @@ class GitHub(ToolBase, ABC):
                 self.set_output("json", response['items'])
                 return self.output("formalized_content")
             except Exception as e:
+                if self.check_if_canceled("GitHub processing"):
+                    return
+
                 last_e = e
                 logging.exception(f"GitHub error: {e}")
                 time.sleep(self._param.delay_after_error)

agent/tools/google.py

@@ -19,7 +19,7 @@ import time
 from abc import ABC
 from serpapi import GoogleSearch
 from agent.tools.base import ToolParamBase, ToolMeta, ToolBase
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 class GoogleParam(ToolParamBase):
@@ -118,6 +118,9 @@ class Google(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 12)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("Google processing"):
+            return
+
         if not kwargs.get("q"):
             self.set_output("formalized_content", "")
             return ""
@@ -132,8 +135,15 @@ class Google(ToolBase, ABC):
         }
         last_e = ""
         for _ in range(self._param.max_retries+1):
+            if self.check_if_canceled("Google processing"):
+                return
+
             try:
                 search = GoogleSearch(params).get_dict()
+
+                if self.check_if_canceled("Google processing"):
+                    return
+
                 self._retrieve_chunks(search["organic_results"],
                                       get_title=lambda r: r["title"],
                                       get_url=lambda r: r["link"],
@@ -142,6 +152,9 @@ class Google(ToolBase, ABC):
                 self.set_output("json", search["organic_results"])
                 return self.output("formalized_content")
             except Exception as e:
+                if self.check_if_canceled("Google processing"):
+                    return
+
                 last_e = e
                 logging.exception(f"Google error: {e}")
                 time.sleep(self._param.delay_after_error)

agent/tools/googlescholar.py

@@ -19,7 +19,7 @@ import time
 from abc import ABC
 from scholarly import scholarly
 from agent.tools.base import ToolMeta, ToolParamBase, ToolBase
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 class GoogleScholarParam(ToolParamBase):
@@ -65,15 +65,25 @@ class GoogleScholar(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 12)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("GoogleScholar processing"):
+            return
+
         if not kwargs.get("query"):
             self.set_output("formalized_content", "")
             return ""
 
         last_e = ""
         for _ in range(self._param.max_retries+1):
+            if self.check_if_canceled("GoogleScholar processing"):
+                return
+
             try:
                 scholar_client = scholarly.search_pubs(kwargs["query"], patents=self._param.patents, year_low=self._param.year_low,
                                                        year_high=self._param.year_high, sort_by=self._param.sort_by)
+
+                if self.check_if_canceled("GoogleScholar processing"):
+                    return
+
                 self._retrieve_chunks(scholar_client,
                                       get_title=lambda r: r['bib']['title'],
                                       get_url=lambda r: r["pub_url"],
@@ -82,6 +92,9 @@ class GoogleScholar(ToolBase, ABC):
                 self.set_output("json", list(scholar_client))
                 return self.output("formalized_content")
             except Exception as e:
+                if self.check_if_canceled("GoogleScholar processing"):
+                    return
+
                 last_e = e
                 logging.exception(f"GoogleScholar error: {e}")
                 time.sleep(self._param.delay_after_error)

agent/tools/jin10.py

@@ -50,6 +50,9 @@ class Jin10(ComponentBase, ABC):
     component_name = "Jin10"
 
     def _run(self, history, **kwargs):
+        if self.check_if_canceled("Jin10 processing"):
+            return
+
         ans = self.get_input()
         ans = " - ".join(ans["content"]) if "content" in ans else ""
         if not ans:
@@ -58,6 +61,9 @@ class Jin10(ComponentBase, ABC):
         jin10_res = []
         headers = {'secret-key': self._param.secret_key}
         try:
+            if self.check_if_canceled("Jin10 processing"):
+                return
+
             if self._param.type == "flash":
                 params = {
                     'category': self._param.flash_type,
@@ -69,6 +75,8 @@ class Jin10(ComponentBase, ABC):
                     headers=headers, data=json.dumps(params))
                 response = response.json()
                 for i in response['data']:
+                    if self.check_if_canceled("Jin10 processing"):
+                        return
                     jin10_res.append({"content": i['data']['content']})
             if self._param.type == "calendar":
                 params = {
@@ -79,6 +87,8 @@ class Jin10(ComponentBase, ABC):
                     headers=headers, data=json.dumps(params))
 
                 response = response.json()
+                if self.check_if_canceled("Jin10 processing"):
+                    return
                 jin10_res.append({"content": pd.DataFrame(response['data']).to_markdown()})
             if self._param.type == "symbols":
                 params = {
@@ -90,8 +100,12 @@ class Jin10(ComponentBase, ABC):
                     url='https://open-data-api.jin10.com/data-api/' + self._param.symbols_datatype + '?type=' + self._param.symbols_type,
                     headers=headers, data=json.dumps(params))
                 response = response.json()
+                if self.check_if_canceled("Jin10 processing"):
+                    return
                 if self._param.symbols_datatype == "symbols":
                     for i in response['data']:
+                        if self.check_if_canceled("Jin10 processing"):
+                            return
                         i['Commodity Code'] = i['c']
                         i['Stock Exchange'] = i['e']
                         i['Commodity Name'] = i['n']
@@ -99,6 +113,8 @@ class Jin10(ComponentBase, ABC):
                         del i['c'], i['e'], i['n'], i['t']
                 if self._param.symbols_datatype == "quotes":
                     for i in response['data']:
+                        if self.check_if_canceled("Jin10 processing"):
+                            return
                         i['Selling Price'] = i['a']
                         i['Buying Price'] = i['b']
                         i['Commodity Code'] = i['c']
@@ -120,8 +136,12 @@ class Jin10(ComponentBase, ABC):
                     url='https://open-data-api.jin10.com/data-api/news',
                     headers=headers, data=json.dumps(params))
                 response = response.json()
+                if self.check_if_canceled("Jin10 processing"):
+                    return
                 jin10_res.append({"content": pd.DataFrame(response['data']).to_markdown()})
         except Exception as e:
+            if self.check_if_canceled("Jin10 processing"):
+                return
             return Jin10.be_output("**ERROR**: " + str(e))
 
         if not jin10_res:

agent/tools/pubmed.py

@@ -21,7 +21,7 @@ from Bio import Entrez
 import re
 import xml.etree.ElementTree as ET
 from agent.tools.base import ToolParamBase, ToolMeta, ToolBase
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 class PubMedParam(ToolParamBase):
@@ -71,23 +71,40 @@ class PubMed(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 12)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("PubMed processing"):
+            return
+
         if not kwargs.get("query"):
             self.set_output("formalized_content", "")
             return ""
 
         last_e = ""
         for _ in range(self._param.max_retries+1):
+            if self.check_if_canceled("PubMed processing"):
+                return
+
             try:
                 Entrez.email = self._param.email
                 pubmedids = Entrez.read(Entrez.esearch(db='pubmed', retmax=self._param.top_n, term=kwargs["query"]))['IdList']
+
+                if self.check_if_canceled("PubMed processing"):
+                    return
+
                 pubmedcnt = ET.fromstring(re.sub(r'<(/?)b>|<(/?)i>', '', Entrez.efetch(db='pubmed', id=",".join(pubmedids),
                                                                                        retmode="xml").read().decode("utf-8")))
+
+                if self.check_if_canceled("PubMed processing"):
+                    return
+
                 self._retrieve_chunks(pubmedcnt.findall("PubmedArticle"),
                                       get_title=lambda child: child.find("MedlineCitation").find("Article").find("ArticleTitle").text,
                                       get_url=lambda child: "https://pubmed.ncbi.nlm.nih.gov/" + child.find("MedlineCitation").find("PMID").text,
                                       get_content=lambda child: self._format_pubmed_content(child),)
                 return self.output("formalized_content")
             except Exception as e:
+                if self.check_if_canceled("PubMed processing"):
+                    return
+
                 last_e = e
                 logging.exception(f"PubMed error: {e}")
                 time.sleep(self._param.delay_after_error)

agent/tools/qweather.py

@@ -58,12 +58,18 @@ class QWeather(ComponentBase, ABC):
     component_name = "QWeather"
 
     def _run(self, history, **kwargs):
+        if self.check_if_canceled("Qweather processing"):
+            return
+
         ans = self.get_input()
         ans = "".join(ans["content"]) if "content" in ans else ""
         if not ans:
             return QWeather.be_output("")
 
         try:
+            if self.check_if_canceled("Qweather processing"):
+                return
+
             response = requests.get(
                 url="https://geoapi.qweather.com/v2/city/lookup?location=" + ans + "&key=" + self._param.web_apikey).json()
             if response["code"] == "200":
@@ -71,16 +77,23 @@ class QWeather(ComponentBase, ABC):
             else:
                 return QWeather.be_output("**Error**" + self._param.error_code[response["code"]])
 
+            if self.check_if_canceled("Qweather processing"):
+                return
+
             base_url = "https://api.qweather.com/v7/" if self._param.user_type == 'paid' else "https://devapi.qweather.com/v7/"
 
             if self._param.type == "weather":
                 url = base_url + "weather/" + self._param.time_period + "?location=" + location_id + "&key=" + self._param.web_apikey + "&lang=" + self._param.lang
                 response = requests.get(url=url).json()
+                if self.check_if_canceled("Qweather processing"):
+                    return
                 if response["code"] == "200":
                     if self._param.time_period == "now":
                         return QWeather.be_output(str(response["now"]))
                     else:
                         qweather_res = [{"content": str(i) + "\n"} for i in response["daily"]]
+                        if self.check_if_canceled("Qweather processing"):
+                            return
                         if not qweather_res:
                             return QWeather.be_output("")
 
@@ -92,6 +105,8 @@ class QWeather(ComponentBase, ABC):
             elif self._param.type == "indices":
                 url = base_url + "indices/1d?type=0&location=" + location_id + "&key=" + self._param.web_apikey + "&lang=" + self._param.lang
                 response = requests.get(url=url).json()
+                if self.check_if_canceled("Qweather processing"):
+                    return
                 if response["code"] == "200":
                     indices_res = response["daily"][0]["date"] + "\n" + "\n".join(
                         [i["name"] + ": " + i["category"] + ", " + i["text"] for i in response["daily"]])
@@ -103,9 +118,13 @@ class QWeather(ComponentBase, ABC):
             elif self._param.type == "airquality":
                 url = base_url + "air/now?location=" + location_id + "&key=" + self._param.web_apikey + "&lang=" + self._param.lang
                 response = requests.get(url=url).json()
+                if self.check_if_canceled("Qweather processing"):
+                    return
                 if response["code"] == "200":
                     return QWeather.be_output(str(response["now"]))
                 else:
                     return QWeather.be_output("**Error**" + self._param.error_code[response["code"]])
         except Exception as e:
+            if self.check_if_canceled("Qweather processing"):
+                return
             return QWeather.be_output("**Error**" + str(e))

agent/tools/retrieval.py

@@ -13,17 +13,21 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+from functools import partial
+import json
 import os
 import re
 from abc import ABC
 from agent.tools.base import ToolParamBase, ToolBase, ToolMeta
-from api.db import LLMType
+from common.constants import LLMType
+from api.db.services.document_service import DocumentService
+from api.db.services.dialog_service import meta_filter
 from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.db.services.llm_service import LLMBundle
-from api import settings
+from common import settings
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 from rag.app.tag import label_question
-from rag.prompts.generator import cross_languages, kb_prompt
+from rag.prompts.generator import cross_languages, kb_prompt, gen_meta_filter
 
 
 class RetrievalParam(ToolParamBase):
@@ -58,6 +62,7 @@ class RetrievalParam(ToolParamBase):
         self.use_kg = False
         self.cross_languages = []
         self.toc_enhance = False
+        self.meta_data_filter={}
 
     def check(self):
         self.check_decimal_float(self.similarity_threshold, "[Retrieval] Similarity threshold")
@@ -77,8 +82,12 @@ class Retrieval(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 12)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("Retrieval processing"):
+            return
+
         if not kwargs.get("query"):
             self.set_output("formalized_content", self._param.empty_response)
+            return
 
         kb_ids: list[str] = []
         for id in self._param.kb_ids:
@@ -117,6 +126,49 @@ class Retrieval(ToolBase, ABC):
         vars = self.get_input_elements_from_text(kwargs["query"])
         vars = {k:o["value"] for k,o in vars.items()}
         query = self.string_format(kwargs["query"], vars)
+
+        doc_ids=[]
+        if self._param.meta_data_filter!={}:
+            metas = DocumentService.get_meta_by_kbs(kb_ids)
+            if self._param.meta_data_filter.get("method") == "auto":
+                chat_mdl = LLMBundle(self._canvas.get_tenant_id(), LLMType.CHAT)
+                filters: dict = gen_meta_filter(chat_mdl, metas, query)
+                doc_ids.extend(meta_filter(metas, filters["conditions"], filters.get("logic", "and")))
+                if not doc_ids:
+                    doc_ids = None
+            elif self._param.meta_data_filter.get("method") == "manual":
+                filters = self._param.meta_data_filter["manual"]
+                for flt in filters:
+                    pat = re.compile(self.variable_ref_patt)
+                    s = flt["value"]
+                    out_parts = []
+                    last = 0
+
+                    for m in pat.finditer(s):
+                        out_parts.append(s[last:m.start()])
+                        key = m.group(1)
+                        v = self._canvas.get_variable_value(key)
+                        if v is None:
+                            rep = ""
+                        elif isinstance(v, partial):
+                            buf = []
+                            for chunk in v():
+                                buf.append(chunk)
+                            rep = "".join(buf)
+                        elif isinstance(v, str):
+                            rep = v
+                        else:
+                            rep = json.dumps(v, ensure_ascii=False)
+
+                        out_parts.append(rep)
+                        last = m.end()
+
+                    out_parts.append(s[last:])
+                    flt["value"] = "".join(out_parts)
+                doc_ids.extend(meta_filter(metas, filters, self._param.meta_data_filter.get("logic", "and")))
+                if filters and not doc_ids:
+                    doc_ids = ["-999"]
+
         if self._param.cross_languages:
             query = cross_languages(kbs[0].tenant_id, None, query, self._param.cross_languages)
 
@@ -131,13 +183,19 @@ class Retrieval(ToolBase, ABC):
                 self._param.top_n,
                 self._param.similarity_threshold,
                 1 - self._param.keywords_similarity_weight,
+                doc_ids=doc_ids,
                 aggs=False,
                 rerank_mdl=rerank_mdl,
                 rank_feature=label_question(query, kbs),
             )
+            if self.check_if_canceled("Retrieval processing"):
+                return
+
             if self._param.toc_enhance:
                 chat_mdl = LLMBundle(self._canvas._tenant_id, LLMType.CHAT)
                 cks = settings.retriever.retrieval_by_toc(query, kbinfos["chunks"], [kb.tenant_id for kb in kbs], chat_mdl, self._param.top_n)
+                if self.check_if_canceled("Retrieval processing"):
+                    return
                 if cks:
                     kbinfos["chunks"] = cks
             if self._param.use_kg:
@@ -146,6 +204,8 @@ class Retrieval(ToolBase, ABC):
                                                        kb_ids,
                                                        embd_mdl,
                                                        LLMBundle(self._canvas.get_tenant_id(), LLMType.CHAT))
+                if self.check_if_canceled("Retrieval processing"):
+                    return
                 if ck["content_with_weight"]:
                     kbinfos["chunks"].insert(0, ck)
         else:
@@ -153,6 +213,8 @@ class Retrieval(ToolBase, ABC):
 
         if self._param.use_kg and kbs:
             ck = settings.kg_retriever.retrieval(query, [kb.tenant_id for kb in kbs], filtered_kb_ids, embd_mdl, LLMBundle(kbs[0].tenant_id, LLMType.CHAT))
+            if self.check_if_canceled("Retrieval processing"):
+                return
             if ck["content_with_weight"]:
                 ck["content"] = ck["content_with_weight"]
                 del ck["content_with_weight"]

agent/tools/searxng.py

@@ -19,7 +19,7 @@ import time
 from abc import ABC
 import requests
 from agent.tools.base import ToolMeta, ToolParamBase, ToolBase
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 class SearXNGParam(ToolParamBase):
@@ -79,6 +79,9 @@ class SearXNG(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 12)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("SearXNG processing"):
+            return
+
         # Gracefully handle try-run without inputs
         query = kwargs.get("query")
         if not query or not isinstance(query, str) or not query.strip():
@@ -93,6 +96,9 @@ class SearXNG(ToolBase, ABC):
 
         last_e = ""
         for _ in range(self._param.max_retries+1):
+            if self.check_if_canceled("SearXNG processing"):
+                return
+
             try:
                 search_params = {
                     'q': query,
@@ -110,6 +116,9 @@ class SearXNG(ToolBase, ABC):
                 )
                 response.raise_for_status()
 
+                if self.check_if_canceled("SearXNG processing"):
+                    return
+
                 data = response.json()
 
                 if not data or not isinstance(data, dict):
@@ -121,6 +130,9 @@ class SearXNG(ToolBase, ABC):
 
                 results = results[:self._param.top_n]
 
+                if self.check_if_canceled("SearXNG processing"):
+                    return
+
                 self._retrieve_chunks(results,
                                       get_title=lambda r: r.get("title", ""),
                                       get_url=lambda r: r.get("url", ""),
@@ -130,10 +142,16 @@ class SearXNG(ToolBase, ABC):
                 return self.output("formalized_content")
 
             except requests.RequestException as e:
+                if self.check_if_canceled("SearXNG processing"):
+                    return
+
                 last_e = f"Network error: {e}"
                 logging.exception(f"SearXNG network error: {e}")
                 time.sleep(self._param.delay_after_error)
             except Exception as e:
+                if self.check_if_canceled("SearXNG processing"):
+                    return
+
                 last_e = str(e)
                 logging.exception(f"SearXNG error: {e}")
                 time.sleep(self._param.delay_after_error)

agent/tools/tavily.py

@@ -19,7 +19,7 @@ import time
 from abc import ABC
 from tavily import TavilyClient
 from agent.tools.base import ToolParamBase, ToolBase, ToolMeta
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 class TavilySearchParam(ToolParamBase):
@@ -103,6 +103,9 @@ class TavilySearch(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 12)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("TavilySearch processing"):
+            return
+
         if not kwargs.get("query"):
             self.set_output("formalized_content", "")
             return ""
@@ -113,10 +116,16 @@ class TavilySearch(ToolBase, ABC):
             if fld not in kwargs:
                 kwargs[fld] = getattr(self._param, fld)
         for _ in range(self._param.max_retries+1):
+            if self.check_if_canceled("TavilySearch processing"):
+                return
+
             try:
                 kwargs["include_images"] = False
                 kwargs["include_raw_content"] = False
                 res = self.tavily_client.search(**kwargs)
+                if self.check_if_canceled("TavilySearch processing"):
+                    return
+
                 self._retrieve_chunks(res["results"],
                                       get_title=lambda r: r["title"],
                                       get_url=lambda r: r["url"],
@@ -125,6 +134,9 @@ class TavilySearch(ToolBase, ABC):
                 self.set_output("json", res["results"])
                 return self.output("formalized_content")
             except Exception as e:
+                if self.check_if_canceled("TavilySearch processing"):
+                    return
+
                 last_e = e
                 logging.exception(f"Tavily error: {e}")
                 time.sleep(self._param.delay_after_error)
@@ -201,6 +213,9 @@ class TavilyExtract(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("TavilyExtract processing"):
+            return
+
         self.tavily_client = TavilyClient(api_key=self._param.api_key)
         last_e = None
         for fld in ["urls", "extract_depth", "format"]:
@@ -209,12 +224,21 @@ class TavilyExtract(ToolBase, ABC):
         if kwargs.get("urls") and isinstance(kwargs["urls"], str):
             kwargs["urls"] = kwargs["urls"].split(",")
         for _ in range(self._param.max_retries+1):
+            if self.check_if_canceled("TavilyExtract processing"):
+                return
+
             try:
                 kwargs["include_images"] = False
                 res = self.tavily_client.extract(**kwargs)
+                if self.check_if_canceled("TavilyExtract processing"):
+                    return
+
                 self.set_output("json", res["results"])
                 return self.output("json")
             except Exception as e:
+                if self.check_if_canceled("TavilyExtract processing"):
+                    return
+
                 last_e = e
                 logging.exception(f"Tavily error: {e}")
         if last_e:

agent/tools/tushare.py

@@ -43,12 +43,18 @@ class TuShare(ComponentBase, ABC):
     component_name = "TuShare"
 
     def _run(self, history, **kwargs):
+        if self.check_if_canceled("TuShare processing"):
+            return
+
         ans = self.get_input()
         ans = ",".join(ans["content"]) if "content" in ans else ""
         if not ans:
             return TuShare.be_output("")
 
         try:
+            if self.check_if_canceled("TuShare processing"):
+                return
+
             tus_res = []
             params = {
                 "api_name": "news",
@@ -58,12 +64,18 @@ class TuShare(ComponentBase, ABC):
             }
             response = requests.post(url="http://api.tushare.pro", data=json.dumps(params).encode('utf-8'))
             response = response.json()
+            if self.check_if_canceled("TuShare processing"):
+                return
             if response['code'] != 0:
                 return TuShare.be_output(response['msg'])
             df = pd.DataFrame(response['data']['items'])
             df.columns = response['data']['fields']
+            if self.check_if_canceled("TuShare processing"):
+                return
             tus_res.append({"content": (df[df['content'].str.contains(self._param.keyword, case=False)]).to_markdown()})
         except Exception as e:
+            if self.check_if_canceled("TuShare processing"):
+                return
             return TuShare.be_output("**ERROR**: " + str(e))
 
         if not tus_res:

agent/tools/wencai.py

@@ -21,7 +21,7 @@ import pandas as pd
 import pywencai
 
 from agent.tools.base import ToolParamBase, ToolMeta, ToolBase
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 class WenCaiParam(ToolParamBase):
@@ -70,19 +70,31 @@ class WenCai(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 12)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("WenCai processing"):
+            return
+
         if not kwargs.get("query"):
             self.set_output("report", "")
             return ""
 
         last_e = ""
         for _ in range(self._param.max_retries+1):
+            if self.check_if_canceled("WenCai processing"):
+                return
+
             try:
                 wencai_res = []
                 res = pywencai.get(query=kwargs["query"], query_type=self._param.query_type, perpage=self._param.top_n)
+                if self.check_if_canceled("WenCai processing"):
+                    return
+
                 if isinstance(res, pd.DataFrame):
                     wencai_res.append(res.to_markdown())
                 elif isinstance(res, dict):
                     for item in res.items():
+                        if self.check_if_canceled("WenCai processing"):
+                            return
+
                         if isinstance(item[1], list):
                             wencai_res.append(item[0] + "\n" + pd.DataFrame(item[1]).to_markdown())
                         elif isinstance(item[1], str):
@@ -100,6 +112,9 @@ class WenCai(ToolBase, ABC):
                 self.set_output("report", "\n\n".join(wencai_res))
                 return self.output("report")
             except Exception as e:
+                if self.check_if_canceled("WenCai processing"):
+                    return
+
                 last_e = e
                 logging.exception(f"WenCai error: {e}")
                 time.sleep(self._param.delay_after_error)

agent/tools/wikipedia.py

@@ -19,7 +19,7 @@ import time
 from abc import ABC
 import wikipedia
 from agent.tools.base import ToolMeta, ToolParamBase, ToolBase
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 class WikipediaParam(ToolParamBase):
@@ -66,17 +66,26 @@ class Wikipedia(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 60)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("Wikipedia processing"):
+            return
+
         if not kwargs.get("query"):
             self.set_output("formalized_content", "")
             return ""
 
         last_e = ""
         for _ in range(self._param.max_retries+1):
+            if self.check_if_canceled("Wikipedia processing"):
+                return
+
             try:
                 wikipedia.set_lang(self._param.language)
                 wiki_engine = wikipedia
                 pages = []
                 for p in wiki_engine.search(kwargs["query"], results=self._param.top_n):
+                    if self.check_if_canceled("Wikipedia processing"):
+                        return
+
                     try:
                         pages.append(wikipedia.page(p))
                     except Exception:
@@ -87,6 +96,9 @@ class Wikipedia(ToolBase, ABC):
                                       get_content=lambda r: r.summary)
                 return self.output("formalized_content")
             except Exception as e:
+                if self.check_if_canceled("Wikipedia processing"):
+                    return
+
                 last_e = e
                 logging.exception(f"Wikipedia error: {e}")
                 time.sleep(self._param.delay_after_error)

agent/tools/yahoofinance.py

@@ -20,7 +20,7 @@ from abc import ABC
 import pandas as pd
 import yfinance as yf
 from agent.tools.base import ToolMeta, ToolParamBase, ToolBase
-from api.utils.api_utils import timeout
+from common.connection_utils import timeout
 
 
 class YahooFinanceParam(ToolParamBase):
@@ -74,15 +74,24 @@ class YahooFinance(ToolBase, ABC):
 
     @timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 60)))
     def _invoke(self, **kwargs):
+        if self.check_if_canceled("YahooFinance processing"):
+            return
+
         if not kwargs.get("stock_code"):
             self.set_output("report", "")
             return ""
 
         last_e = ""
         for _ in range(self._param.max_retries+1):
+            if self.check_if_canceled("YahooFinance processing"):
+                return
+
             yohoo_res = []
             try:
                 msft = yf.Ticker(kwargs["stock_code"])
+                if self.check_if_canceled("YahooFinance processing"):
+                    return
+
                 if self._param.info:
                     yohoo_res.append("# Information:\n" + pd.Series(msft.info).to_markdown() + "\n")
                 if self._param.history:
@@ -100,6 +109,9 @@ class YahooFinance(ToolBase, ABC):
                 self.set_output("report", "\n\n".join(yohoo_res))
                 return self.output("report")
             except Exception as e:
+                if self.check_if_canceled("YahooFinance processing"):
+                    return
+
                 last_e = e
                 logging.exception(f"YahooFinance error: {e}")
                 time.sleep(self._param.delay_after_error)

api/apps/__init__.py

@@ -18,30 +18,32 @@ import sys
 import logging
 from importlib.util import module_from_spec, spec_from_file_location
 from pathlib import Path
-from flask import Blueprint, Flask
+from quart import Blueprint, Quart, request, g, current_app, session
 from werkzeug.wrappers.request import Request
-from flask_cors import CORS
 from flasgger import Swagger
 from itsdangerous.url_safe import URLSafeTimedSerializer as Serializer
-
+from quart_cors import cors
-from api.db import StatusEnum
+from common.constants import StatusEnum
-from api.db.db_models import close_connection
+from api.db.db_models import close_connection, APIToken
 from api.db.services import UserService
-from api.utils.json import CustomJSONEncoder
+from api.utils.json_encode import CustomJSONEncoder
 from api.utils import commands
 
 from flask_mail import Mail
-from flask_session import Session
+from quart_auth import Unauthorized
-from flask_login import LoginManager
+from common import settings
-from api import settings
 from api.utils.api_utils import server_error_response
 from api.constants import API_VERSION
+from common.misc_utils import get_uuid
+
+settings.init_settings()
 
 __all__ = ["app"]
 
 Request.json = property(lambda self: self.get_json(force=True, silent=True))
 
-app = Flask(__name__)
+app = Quart(__name__)
+app = cors(app, allow_origin="*")
 smtp_mail_server = Mail()
 
 # Add this at the beginning of your file to configure Swagger UI
@@ -76,7 +78,6 @@ swagger = Swagger(
     },
 )
 
-CORS(app, supports_credentials=True, max_age=2592000)
 app.url_map.strict_slashes = False
 app.json_encoder = CustomJSONEncoder
 app.errorhandler(Exception)(server_error_response)
@@ -84,24 +85,154 @@ app.errorhandler(Exception)(server_error_response)
 ## convince for dev and debug
 # app.config["LOGIN_DISABLED"] = True
 app.config["SESSION_PERMANENT"] = False
-app.config["SESSION_TYPE"] = "filesystem"
+app.config["SESSION_TYPE"] = "redis"
+app.config["SESSION_REDIS"] = settings.decrypt_database_config(name="redis")
 app.config["MAX_CONTENT_LENGTH"] = int(
     os.environ.get("MAX_CONTENT_LENGTH", 1024 * 1024 * 1024)
 )
-
+app.config['SECRET_KEY'] = settings.SECRET_KEY
-Session(app)
+app.secret_key = settings.SECRET_KEY
-login_manager = LoginManager()
-login_manager.init_app(app)
-
 commands.register_commands(app)
 
+from functools import wraps
+from typing import ParamSpec, TypeVar
+from collections.abc import Awaitable, Callable
+from werkzeug.local import LocalProxy
 
-def search_pages_path(pages_dir):
+T = TypeVar("T")
+P = ParamSpec("P")
+
+def _load_user():
+    jwt = Serializer(secret_key=settings.SECRET_KEY)
+    authorization = request.headers.get("Authorization")
+    g.user = None
+    if not authorization:
+        return
+
+    try:
+        access_token = str(jwt.loads(authorization))
+
+        if not access_token or not access_token.strip():
+            logging.warning("Authentication attempt with empty access token")
+            return None
+
+        # Access tokens should be UUIDs (32 hex characters)
+        if len(access_token.strip()) < 32:
+            logging.warning(f"Authentication attempt with invalid token format: {len(access_token)} chars")
+            return None
+
+        user = UserService.query(
+            access_token=access_token, status=StatusEnum.VALID.value
+        )
+        if not user and len(authorization.split()) == 2:
+            objs = APIToken.query(token=authorization.split()[1])
+            if objs:
+                user = UserService.query(id=objs[0].tenant_id, status=StatusEnum.VALID.value)
+        if user:
+            if not user[0].access_token or not user[0].access_token.strip():
+                logging.warning(f"User {user[0].email} has empty access_token in database")
+                return None
+            g.user = user[0]
+            return user[0]
+    except Exception as e:
+        logging.warning(f"load_user got exception {e}")
+
+
+current_user = LocalProxy(_load_user)
+
+
+def login_required(func: Callable[P, Awaitable[T]]) -> Callable[P, Awaitable[T]]:
+    """A decorator to restrict route access to authenticated users.
+
+    This should be used to wrap a route handler (or view function) to
+    enforce that only authenticated requests can access it. Note that
+    it is important that this decorator be wrapped by the route
+    decorator and not vice, versa, as below.
+
+    .. code-block:: python
+
+        @app.route('/')
+        @login_required
+        async def index():
+            ...
+
+    If the request is not authenticated a
+    `quart.exceptions.Unauthorized` exception will be raised.
+
+    """
+
+    @wraps(func)
+    async def wrapper(*args: P.args, **kwargs: P.kwargs) -> T:
+        if not current_user:# or not session.get("_user_id"):
+            raise Unauthorized()
+        else:
+            return await current_app.ensure_async(func)(*args, **kwargs)
+
+    return wrapper
+
+
+def login_user(user, remember=False, duration=None, force=False, fresh=True):
+    """
+    Logs a user in. You should pass the actual user object to this. If the
+    user's `is_active` property is ``False``, they will not be logged in
+    unless `force` is ``True``.
+
+    This will return ``True`` if the log in attempt succeeds, and ``False`` if
+    it fails (i.e. because the user is inactive).
+
+    :param user: The user object to log in.
+    :type user: object
+    :param remember: Whether to remember the user after their session expires.
+        Defaults to ``False``.
+    :type remember: bool
+    :param duration: The amount of time before the remember cookie expires. If
+        ``None`` the value set in the settings is used. Defaults to ``None``.
+    :type duration: :class:`datetime.timedelta`
+    :param force: If the user is inactive, setting this to ``True`` will log
+        them in regardless. Defaults to ``False``.
+    :type force: bool
+    :param fresh: setting this to ``False`` will log in the user with a session
+        marked as not "fresh". Defaults to ``True``.
+    :type fresh: bool
+    """
+    if not force and not user.is_active:
+        return False
+
+    session["_user_id"] = user.id
+    session["_fresh"] = fresh
+    session["_id"] = get_uuid()
+    return True
+
+
+def logout_user():
+    """
+    Logs a user out. (You do not need to pass the actual user.) This will
+    also clean up the remember me cookie if it exists.
+    """
+    if "_user_id" in session:
+        session.pop("_user_id")
+
+    if "_fresh" in session:
+        session.pop("_fresh")
+
+    if "_id" in session:
+        session.pop("_id")
+
+    COOKIE_NAME = "remember_token"
+    cookie_name = current_app.config.get("REMEMBER_COOKIE_NAME", COOKIE_NAME)
+    if cookie_name in request.cookies:
+        session["_remember"] = "clear"
+        if "_remember_seconds" in session:
+            session.pop("_remember_seconds")
+
+    return True
+
+def search_pages_path(page_path):
     app_path_list = [
-        path for path in pages_dir.glob("*_app.py") if not path.name.startswith(".")
+        path for path in page_path.glob("*_app.py") if not path.name.startswith(".")
     ]
     api_path_list = [
-        path for path in pages_dir.glob("*sdk/*.py") if not path.name.startswith(".")
+        path for path in page_path.glob("*sdk/*.py") if not path.name.startswith(".")
     ]
     app_path_list.extend(api_path_list)
     return app_path_list
@@ -138,44 +269,12 @@ pages_dir = [
 ]
 
 client_urls_prefix = [
-    register_page(path) for dir in pages_dir for path in search_pages_path(dir)
+    register_page(path) for directory in pages_dir for path in search_pages_path(directory)
 ]
 
 
-@login_manager.request_loader
-def load_user(web_request):
-    jwt = Serializer(secret_key=settings.SECRET_KEY)
-    authorization = web_request.headers.get("Authorization")
-    if authorization:
-        try:
-            access_token = str(jwt.loads(authorization))
-
-            if not access_token or not access_token.strip():
-                logging.warning("Authentication attempt with empty access token")
-                return None
-
-            # Access tokens should be UUIDs (32 hex characters)
-            if len(access_token.strip()) < 32:
-                logging.warning(f"Authentication attempt with invalid token format: {len(access_token)} chars")
-                return None
-
-            user = UserService.query(
-                access_token=access_token, status=StatusEnum.VALID.value
-            )
-            if user:
-                if not user[0].access_token or not user[0].access_token.strip():
-                    logging.warning(f"User {user[0].email} has empty access_token in database")
-                    return None
-                return user[0]
-            else:
-                return None
-        except Exception as e:
-            logging.warning(f"load_user got exception {e}")
-            return None
-    else:
-        return None
-
-
 @app.teardown_request
-def _db_close(exc):
+def _db_close(exception):
+    if exception:
+        logging.exception(f"Request failed: {exception}")
     close_connection()

api/apps/api_app.py

@@ -13,52 +13,28 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-import json
-import os
-import re
 from datetime import datetime, timedelta
-from flask import request, Response
+from quart import request
-from api.db.services.llm_service import LLMBundle
+from api.db.db_models import APIToken
-from flask_login import login_required, current_user
-
-from api.db import VALID_FILE_TYPES, VALID_TASK_STATUS, FileType, LLMType, ParserType, FileSource
-from api.db.db_models import APIToken, Task, File
-from api.db.services import duplicate_name
 from api.db.services.api_service import APITokenService, API4ConversationService
-from api.db.services.dialog_service import DialogService, chat
-from api.db.services.document_service import DocumentService, doc_upload_and_parse
-from api.db.services.file2document_service import File2DocumentService
-from api.db.services.file_service import FileService
-from api.db.services.knowledgebase_service import KnowledgebaseService
-from api.db.services.task_service import queue_tasks, TaskService
 from api.db.services.user_service import UserTenantService
-from api import settings
-from api.utils import get_uuid, current_timestamp, datetime_format
 from api.utils.api_utils import server_error_response, get_data_error_result, get_json_result, validate_request, \
     generate_confirmation_token
-
+from common.time_utils import current_timestamp, datetime_format
-from api.utils.file_utils import filename_type, thumbnail
+from api.apps import login_required, current_user
-from rag.app.tag import label_question
-from rag.prompts.generator import keyword_extraction
-from rag.utils.storage_factory import STORAGE_IMPL
-
-from api.db.services.canvas_service import UserCanvasService
-from agent.canvas import Canvas
-from functools import partial
-from pathlib import Path
 
 
 @manager.route('/new_token', methods=['POST'])  # noqa: F821
 @login_required
-def new_token():
+async def new_token():
-    req = request.json
+    req = await request.json
     try:
         tenants = UserTenantService.query(user_id=current_user.id)
         if not tenants:
             return get_data_error_result(message="Tenant not found!")
 
         tenant_id = tenants[0].tenant_id
-        obj = {"tenant_id": tenant_id, "token": generate_confirmation_token(tenant_id),
+        obj = {"tenant_id": tenant_id, "token": generate_confirmation_token(),
                "create_time": current_timestamp(),
                "create_date": datetime_format(datetime.now()),
                "update_time": None,
@@ -96,8 +72,8 @@ def token_list():
 @manager.route('/rm', methods=['POST'])  # noqa: F821
 @validate_request("tokens", "tenant_id")
 @login_required
-def rm():
+async def rm():
-    req = request.json
+    req = await request.json
     try:
         for token in req["tokens"]:
             APITokenService.filter_delete(
@@ -125,774 +101,19 @@ def stats():
                 "to_date",
                 datetime.now().strftime("%Y-%m-%d %H:%M:%S")),
             "agent" if "canvas_id" in request.args else None)
-        res = {
+
-            "pv": [(o["dt"], o["pv"]) for o in objs],
+        res = {"pv": [], "uv": [], "speed": [], "tokens": [], "round": [], "thumb_up": []}
-            "uv": [(o["dt"], o["uv"]) for o in objs],
+
-            "speed": [(o["dt"], float(o["tokens"]) / (float(o["duration"] + 0.1))) for o in objs],
+        for obj in objs:
-            "tokens": [(o["dt"], float(o["tokens"]) / 1000.) for o in objs],
+            dt = obj["dt"]
-            "round": [(o["dt"], o["round"]) for o in objs],
+            res["pv"].append((dt, obj["pv"]))
-            "thumb_up": [(o["dt"], o["thumb_up"]) for o in objs]
+            res["uv"].append((dt, obj["uv"]))
-        }
+            res["speed"].append((dt, float(obj["tokens"]) / (float(obj["duration"]) + 0.1))) # +0.1 to avoid division by zero
+            res["tokens"].append((dt, float(obj["tokens"]) / 1000.0)) # convert to thousands
+            res["round"].append((dt, obj["round"]))
+            res["thumb_up"].append((dt, obj["thumb_up"]))
+
         return get_json_result(data=res)
     except Exception as e:
         return server_error_response(e)
 
-
-@manager.route('/new_conversation', methods=['GET'])  # noqa: F821
-def set_conversation():
-    token = request.headers.get('Authorization').split()[1]
-    objs = APIToken.query(token=token)
-    if not objs:
-        return get_json_result(
-            data=False, message='Authentication error: API key is invalid!"', code=settings.RetCode.AUTHENTICATION_ERROR)
-    try:
-        if objs[0].source == "agent":
-            e, cvs = UserCanvasService.get_by_id(objs[0].dialog_id)
-            if not e:
-                return server_error_response("canvas not found.")
-            if not isinstance(cvs.dsl, str):
-                cvs.dsl = json.dumps(cvs.dsl, ensure_ascii=False)
-            canvas = Canvas(cvs.dsl, objs[0].tenant_id)
-            conv = {
-                "id": get_uuid(),
-                "dialog_id": cvs.id,
-                "user_id": request.args.get("user_id", ""),
-                "message": [{"role": "assistant", "content": canvas.get_prologue()}],
-                "source": "agent"
-            }
-            API4ConversationService.save(**conv)
-            return get_json_result(data=conv)
-        else:
-            e, dia = DialogService.get_by_id(objs[0].dialog_id)
-            if not e:
-                return get_data_error_result(message="Dialog not found")
-            conv = {
-                "id": get_uuid(),
-                "dialog_id": dia.id,
-                "user_id": request.args.get("user_id", ""),
-                "message": [{"role": "assistant", "content": dia.prompt_config["prologue"]}]
-            }
-            API4ConversationService.save(**conv)
-            return get_json_result(data=conv)
-    except Exception as e:
-        return server_error_response(e)
-
-
-@manager.route('/completion', methods=['POST'])  # noqa: F821
-@validate_request("conversation_id", "messages")
-def completion():
-    token = request.headers.get('Authorization').split()[1]
-    objs = APIToken.query(token=token)
-    if not objs:
-        return get_json_result(
-            data=False, message='Authentication error: API key is invalid!"', code=settings.RetCode.AUTHENTICATION_ERROR)
-    req = request.json
-    e, conv = API4ConversationService.get_by_id(req["conversation_id"])
-    if not e:
-        return get_data_error_result(message="Conversation not found!")
-    if "quote" not in req:
-        req["quote"] = False
-
-    msg = []
-    for m in req["messages"]:
-        if m["role"] == "system":
-            continue
-        if m["role"] == "assistant" and not msg:
-            continue
-        msg.append(m)
-    if not msg[-1].get("id"):
-        msg[-1]["id"] = get_uuid()
-    message_id = msg[-1]["id"]
-
-    def fillin_conv(ans):
-        nonlocal conv, message_id
-        if not conv.reference:
-            conv.reference.append(ans["reference"])
-        else:
-            conv.reference[-1] = ans["reference"]
-        conv.message[-1] = {"role": "assistant", "content": ans["answer"], "id": message_id}
-        ans["id"] = message_id
-
-    def rename_field(ans):
-        reference = ans['reference']
-        if not isinstance(reference, dict):
-            return
-        for chunk_i in reference.get('chunks', []):
-            if 'docnm_kwd' in chunk_i:
-                chunk_i['doc_name'] = chunk_i['docnm_kwd']
-                chunk_i.pop('docnm_kwd')
-
-    try:
-        if conv.source == "agent":
-            stream = req.get("stream", True)
-            conv.message.append(msg[-1])
-            e, cvs = UserCanvasService.get_by_id(conv.dialog_id)
-            if not e:
-                return server_error_response("canvas not found.")
-            del req["conversation_id"]
-            del req["messages"]
-
-            if not isinstance(cvs.dsl, str):
-                cvs.dsl = json.dumps(cvs.dsl, ensure_ascii=False)
-
-            if not conv.reference:
-                conv.reference = []
-            conv.message.append({"role": "assistant", "content": "", "id": message_id})
-            conv.reference.append({"chunks": [], "doc_aggs": []})
-
-            final_ans = {"reference": [], "content": ""}
-            canvas = Canvas(cvs.dsl, objs[0].tenant_id)
-
-            canvas.messages.append(msg[-1])
-            canvas.add_user_input(msg[-1]["content"])
-            answer = canvas.run(stream=stream)
-
-            assert answer is not None, "Nothing. Is it over?"
-
-            if stream:
-                assert isinstance(answer, partial), "Nothing. Is it over?"
-
-                def sse():
-                    nonlocal answer, cvs, conv
-                    try:
-                        for ans in answer():
-                            for k in ans.keys():
-                                final_ans[k] = ans[k]
-                            ans = {"answer": ans["content"], "reference": ans.get("reference", [])}
-                            fillin_conv(ans)
-                            rename_field(ans)
-                            yield "data:" + json.dumps({"code": 0, "message": "", "data": ans},
-                                                       ensure_ascii=False) + "\n\n"
-
-                        canvas.messages.append({"role": "assistant", "content": final_ans["content"], "id": message_id})
-                        canvas.history.append(("assistant", final_ans["content"]))
-                        if final_ans.get("reference"):
-                            canvas.reference.append(final_ans["reference"])
-                        cvs.dsl = json.loads(str(canvas))
-                        API4ConversationService.append_message(conv.id, conv.to_dict())
-                    except Exception as e:
-                        yield "data:" + json.dumps({"code": 500, "message": str(e),
-                                                    "data": {"answer": "**ERROR**: " + str(e), "reference": []}},
-                                                   ensure_ascii=False) + "\n\n"
-                    yield "data:" + json.dumps({"code": 0, "message": "", "data": True}, ensure_ascii=False) + "\n\n"
-
-                resp = Response(sse(), mimetype="text/event-stream")
-                resp.headers.add_header("Cache-control", "no-cache")
-                resp.headers.add_header("Connection", "keep-alive")
-                resp.headers.add_header("X-Accel-Buffering", "no")
-                resp.headers.add_header("Content-Type", "text/event-stream; charset=utf-8")
-                return resp
-
-            final_ans["content"] = "\n".join(answer["content"]) if "content" in answer else ""
-            canvas.messages.append({"role": "assistant", "content": final_ans["content"], "id": message_id})
-            if final_ans.get("reference"):
-                canvas.reference.append(final_ans["reference"])
-            cvs.dsl = json.loads(str(canvas))
-
-            result = {"answer": final_ans["content"], "reference": final_ans.get("reference", [])}
-            fillin_conv(result)
-            API4ConversationService.append_message(conv.id, conv.to_dict())
-            rename_field(result)
-            return get_json_result(data=result)
-
-        # ******************For dialog******************
-        conv.message.append(msg[-1])
-        e, dia = DialogService.get_by_id(conv.dialog_id)
-        if not e:
-            return get_data_error_result(message="Dialog not found!")
-        del req["conversation_id"]
-        del req["messages"]
-
-        if not conv.reference:
-            conv.reference = []
-        conv.message.append({"role": "assistant", "content": "", "id": message_id})
-        conv.reference.append({"chunks": [], "doc_aggs": []})
-
-        def stream():
-            nonlocal dia, msg, req, conv
-            try:
-                for ans in chat(dia, msg, True, **req):
-                    fillin_conv(ans)
-                    rename_field(ans)
-                    yield "data:" + json.dumps({"code": 0, "message": "", "data": ans},
-                                               ensure_ascii=False) + "\n\n"
-                API4ConversationService.append_message(conv.id, conv.to_dict())
-            except Exception as e:
-                yield "data:" + json.dumps({"code": 500, "message": str(e),
-                                            "data": {"answer": "**ERROR**: " + str(e), "reference": []}},
-                                           ensure_ascii=False) + "\n\n"
-            yield "data:" + json.dumps({"code": 0, "message": "", "data": True}, ensure_ascii=False) + "\n\n"
-
-        if req.get("stream", True):
-            resp = Response(stream(), mimetype="text/event-stream")
-            resp.headers.add_header("Cache-control", "no-cache")
-            resp.headers.add_header("Connection", "keep-alive")
-            resp.headers.add_header("X-Accel-Buffering", "no")
-            resp.headers.add_header("Content-Type", "text/event-stream; charset=utf-8")
-            return resp
-
-        answer = None
-        for ans in chat(dia, msg, **req):
-            answer = ans
-            fillin_conv(ans)
-            API4ConversationService.append_message(conv.id, conv.to_dict())
-            break
-        rename_field(answer)
-        return get_json_result(data=answer)
-
-    except Exception as e:
-        return server_error_response(e)
-
-
-@manager.route('/conversation/<conversation_id>', methods=['GET'])  # noqa: F821
-# @login_required
-def get_conversation(conversation_id):
-    token = request.headers.get('Authorization').split()[1]
-    objs = APIToken.query(token=token)
-    if not objs:
-        return get_json_result(
-            data=False, message='Authentication error: API key is invalid!"', code=settings.RetCode.AUTHENTICATION_ERROR)
-
-    try:
-        e, conv = API4ConversationService.get_by_id(conversation_id)
-        if not e:
-            return get_data_error_result(message="Conversation not found!")
-
-        conv = conv.to_dict()
-        if token != APIToken.query(dialog_id=conv['dialog_id'])[0].token:
-            return get_json_result(data=False, message='Authentication error: API key is invalid for this conversation_id!"',
-                                   code=settings.RetCode.AUTHENTICATION_ERROR)
-
-        for referenct_i in conv['reference']:
-            if referenct_i is None or len(referenct_i) == 0:
-                continue
-            for chunk_i in referenct_i['chunks']:
-                if 'docnm_kwd' in chunk_i.keys():
-                    chunk_i['doc_name'] = chunk_i['docnm_kwd']
-                    chunk_i.pop('docnm_kwd')
-        return get_json_result(data=conv)
-    except Exception as e:
-        return server_error_response(e)
-
-
-@manager.route('/document/upload', methods=['POST'])  # noqa: F821
-@validate_request("kb_name")
-def upload():
-    token = request.headers.get('Authorization').split()[1]
-    objs = APIToken.query(token=token)
-    if not objs:
-        return get_json_result(
-            data=False, message='Authentication error: API key is invalid!"', code=settings.RetCode.AUTHENTICATION_ERROR)
-
-    kb_name = request.form.get("kb_name").strip()
-    tenant_id = objs[0].tenant_id
-
-    try:
-        e, kb = KnowledgebaseService.get_by_name(kb_name, tenant_id)
-        if not e:
-            return get_data_error_result(
-                message="Can't find this knowledgebase!")
-        kb_id = kb.id
-    except Exception as e:
-        return server_error_response(e)
-
-    if 'file' not in request.files:
-        return get_json_result(
-            data=False, message='No file part!', code=settings.RetCode.ARGUMENT_ERROR)
-
-    file = request.files['file']
-    if file.filename == '':
-        return get_json_result(
-            data=False, message='No file selected!', code=settings.RetCode.ARGUMENT_ERROR)
-
-    root_folder = FileService.get_root_folder(tenant_id)
-    pf_id = root_folder["id"]
-    FileService.init_knowledgebase_docs(pf_id, tenant_id)
-    kb_root_folder = FileService.get_kb_folder(tenant_id)
-    kb_folder = FileService.new_a_file_from_kb(kb.tenant_id, kb.name, kb_root_folder["id"])
-
-    try:
-        if DocumentService.get_doc_count(kb.tenant_id) >= int(os.environ.get('MAX_FILE_NUM_PER_USER', 8192)):
-            return get_data_error_result(
-                message="Exceed the maximum file number of a free user!")
-
-        filename = duplicate_name(
-            DocumentService.query,
-            name=file.filename,
-            kb_id=kb_id)
-        filetype = filename_type(filename)
-        if not filetype:
-            return get_data_error_result(
-                message="This type of file has not been supported yet!")
-
-        location = filename
-        while STORAGE_IMPL.obj_exist(kb_id, location):
-            location += "_"
-        blob = request.files['file'].read()
-        STORAGE_IMPL.put(kb_id, location, blob)
-        doc = {
-            "id": get_uuid(),
-            "kb_id": kb.id,
-            "parser_id": kb.parser_id,
-            "parser_config": kb.parser_config,
-            "created_by": kb.tenant_id,
-            "type": filetype,
-            "name": filename,
-            "location": location,
-            "size": len(blob),
-            "thumbnail": thumbnail(filename, blob),
-            "suffix": Path(filename).suffix.lstrip("."),
-        }
-
-        form_data = request.form
-        if "parser_id" in form_data.keys():
-            if request.form.get("parser_id").strip() in list(vars(ParserType).values())[1:-3]:
-                doc["parser_id"] = request.form.get("parser_id").strip()
-        if doc["type"] == FileType.VISUAL:
-            doc["parser_id"] = ParserType.PICTURE.value
-        if doc["type"] == FileType.AURAL:
-            doc["parser_id"] = ParserType.AUDIO.value
-        if re.search(r"\.(ppt|pptx|pages)$", filename):
-            doc["parser_id"] = ParserType.PRESENTATION.value
-        if re.search(r"\.(eml)$", filename):
-            doc["parser_id"] = ParserType.EMAIL.value
-
-        doc_result = DocumentService.insert(doc)
-        FileService.add_file_from_kb(doc, kb_folder["id"], kb.tenant_id)
-    except Exception as e:
-        return server_error_response(e)
-
-    if "run" in form_data.keys():
-        if request.form.get("run").strip() == "1":
-            try:
-                info = {"run": 1, "progress": 0}
-                info["progress_msg"] = ""
-                info["chunk_num"] = 0
-                info["token_num"] = 0
-                DocumentService.update_by_id(doc["id"], info)
-                # if str(req["run"]) == TaskStatus.CANCEL.value:
-                tenant_id = DocumentService.get_tenant_id(doc["id"])
-                if not tenant_id:
-                    return get_data_error_result(message="Tenant not found!")
-
-                # e, doc = DocumentService.get_by_id(doc["id"])
-                TaskService.filter_delete([Task.doc_id == doc["id"]])
-                e, doc = DocumentService.get_by_id(doc["id"])
-                doc = doc.to_dict()
-                doc["tenant_id"] = tenant_id
-                bucket, name = File2DocumentService.get_storage_address(doc_id=doc["id"])
-                queue_tasks(doc, bucket, name, 0)
-            except Exception as e:
-                return server_error_response(e)
-
-    return get_json_result(data=doc_result.to_json())
-
-
-@manager.route('/document/upload_and_parse', methods=['POST'])  # noqa: F821
-@validate_request("conversation_id")
-def upload_parse():
-    token = request.headers.get('Authorization').split()[1]
-    objs = APIToken.query(token=token)
-    if not objs:
-        return get_json_result(
-            data=False, message='Authentication error: API key is invalid!"', code=settings.RetCode.AUTHENTICATION_ERROR)
-
-    if 'file' not in request.files:
-        return get_json_result(
-            data=False, message='No file part!', code=settings.RetCode.ARGUMENT_ERROR)
-
-    file_objs = request.files.getlist('file')
-    for file_obj in file_objs:
-        if file_obj.filename == '':
-            return get_json_result(
-                data=False, message='No file selected!', code=settings.RetCode.ARGUMENT_ERROR)
-
-    doc_ids = doc_upload_and_parse(request.form.get("conversation_id"), file_objs, objs[0].tenant_id)
-    return get_json_result(data=doc_ids)
-
-
-@manager.route('/list_chunks', methods=['POST'])  # noqa: F821
-# @login_required
-def list_chunks():
-    token = request.headers.get('Authorization').split()[1]
-    objs = APIToken.query(token=token)
-    if not objs:
-        return get_json_result(
-            data=False, message='Authentication error: API key is invalid!"', code=settings.RetCode.AUTHENTICATION_ERROR)
-
-    req = request.json
-
-    try:
-        if "doc_name" in req.keys():
-            tenant_id = DocumentService.get_tenant_id_by_name(req['doc_name'])
-            doc_id = DocumentService.get_doc_id_by_doc_name(req['doc_name'])
-
-        elif "doc_id" in req.keys():
-            tenant_id = DocumentService.get_tenant_id(req['doc_id'])
-            doc_id = req['doc_id']
-        else:
-            return get_json_result(
-                data=False, message="Can't find doc_name or doc_id"
-            )
-        kb_ids = KnowledgebaseService.get_kb_ids(tenant_id)
-
-        res = settings.retriever.chunk_list(doc_id, tenant_id, kb_ids)
-        res = [
-            {
-                "content": res_item["content_with_weight"],
-                "doc_name": res_item["docnm_kwd"],
-                "image_id": res_item["img_id"]
-            } for res_item in res
-        ]
-
-    except Exception as e:
-        return server_error_response(e)
-
-    return get_json_result(data=res)
-
-@manager.route('/get_chunk/<chunk_id>', methods=['GET'])  # noqa: F821
-# @login_required
-def get_chunk(chunk_id):
-    from rag.nlp import search
-    token = request.headers.get('Authorization').split()[1]
-    objs = APIToken.query(token=token)
-    if not objs:
-        return get_json_result(
-            data=False, message='Authentication error: API key is invalid!"', code=settings.RetCode.AUTHENTICATION_ERROR)
-    try:
-        tenant_id = objs[0].tenant_id
-        kb_ids = KnowledgebaseService.get_kb_ids(tenant_id)
-        chunk = settings.docStoreConn.get(chunk_id, search.index_name(tenant_id), kb_ids)
-        if chunk is None:
-            return server_error_response(Exception("Chunk not found"))
-        k = []
-        for n in chunk.keys():
-            if re.search(r"(_vec$|_sm_|_tks|_ltks)", n):
-                k.append(n)
-        for n in k:
-            del chunk[n]
-
-        return get_json_result(data=chunk)
-    except Exception as e:
-        return server_error_response(e)
-
-@manager.route('/list_kb_docs', methods=['POST'])  # noqa: F821
-# @login_required
-def list_kb_docs():
-    token = request.headers.get('Authorization').split()[1]
-    objs = APIToken.query(token=token)
-    if not objs:
-        return get_json_result(
-            data=False, message='Authentication error: API key is invalid!"', code=settings.RetCode.AUTHENTICATION_ERROR)
-
-    req = request.json
-    tenant_id = objs[0].tenant_id
-    kb_name = req.get("kb_name", "").strip()
-
-    try:
-        e, kb = KnowledgebaseService.get_by_name(kb_name, tenant_id)
-        if not e:
-            return get_data_error_result(
-                message="Can't find this knowledgebase!")
-        kb_id = kb.id
-
-    except Exception as e:
-        return server_error_response(e)
-
-    page_number = int(req.get("page", 1))
-    items_per_page = int(req.get("page_size", 15))
-    orderby = req.get("orderby", "create_time")
-    desc = req.get("desc", True)
-    keywords = req.get("keywords", "")
-    status = req.get("status", [])
-    if status:
-        invalid_status = {s for s in status if s not in VALID_TASK_STATUS}
-        if invalid_status:
-            return get_data_error_result(
-                message=f"Invalid filter status conditions: {', '.join(invalid_status)}"
-            )
-    types = req.get("types", [])
-    if types:
-        invalid_types = {t for t in types if t not in VALID_FILE_TYPES}
-        if invalid_types:
-            return get_data_error_result(
-                message=f"Invalid filter conditions: {', '.join(invalid_types)} type{'s' if len(invalid_types) > 1 else ''}"
-            )
-    try:
-        docs, tol = DocumentService.get_by_kb_id(
-            kb_id, page_number, items_per_page, orderby, desc, keywords, status, types)
-        docs = [{"doc_id": doc['id'], "doc_name": doc['name']} for doc in docs]
-
-        return get_json_result(data={"total": tol, "docs": docs})
-
-    except Exception as e:
-        return server_error_response(e)
-
-
-@manager.route('/document/infos', methods=['POST'])  # noqa: F821
-@validate_request("doc_ids")
-def docinfos():
-    token = request.headers.get('Authorization').split()[1]
-    objs = APIToken.query(token=token)
-    if not objs:
-        return get_json_result(
-            data=False, message='Authentication error: API key is invalid!"', code=settings.RetCode.AUTHENTICATION_ERROR)
-    req = request.json
-    doc_ids = req["doc_ids"]
-    docs = DocumentService.get_by_ids(doc_ids)
-    return get_json_result(data=list(docs.dicts()))
-
-
-@manager.route('/document', methods=['DELETE'])  # noqa: F821
-# @login_required
-def document_rm():
-    token = request.headers.get('Authorization').split()[1]
-    objs = APIToken.query(token=token)
-    if not objs:
-        return get_json_result(
-            data=False, message='Authentication error: API key is invalid!"', code=settings.RetCode.AUTHENTICATION_ERROR)
-
-    tenant_id = objs[0].tenant_id
-    req = request.json
-    try:
-        doc_ids = DocumentService.get_doc_ids_by_doc_names(req.get("doc_names", []))
-        for doc_id in req.get("doc_ids", []):
-            if doc_id not in doc_ids:
-                doc_ids.append(doc_id)
-
-        if not doc_ids:
-            return get_json_result(
-                data=False, message="Can't find doc_names or doc_ids"
-            )
-
-    except Exception as e:
-        return server_error_response(e)
-
-    root_folder = FileService.get_root_folder(tenant_id)
-    pf_id = root_folder["id"]
-    FileService.init_knowledgebase_docs(pf_id, tenant_id)
-
-    errors = ""
-    docs = DocumentService.get_by_ids(doc_ids)
-    doc_dic = {}
-    for doc in docs:
-        doc_dic[doc.id] = doc
-
-    for doc_id in doc_ids:
-        try:
-            if doc_id not in doc_dic:
-                return get_data_error_result(message="Document not found!")
-            doc = doc_dic[doc_id]
-            tenant_id = DocumentService.get_tenant_id(doc_id)
-            if not tenant_id:
-                return get_data_error_result(message="Tenant not found!")
-
-            b, n = File2DocumentService.get_storage_address(doc_id=doc_id)
-
-            if not DocumentService.remove_document(doc, tenant_id):
-                return get_data_error_result(
-                    message="Database error (Document removal)!")
-
-            f2d = File2DocumentService.get_by_document_id(doc_id)
-            FileService.filter_delete([File.source_type == FileSource.KNOWLEDGEBASE, File.id == f2d[0].file_id])
-            File2DocumentService.delete_by_document_id(doc_id)
-
-            STORAGE_IMPL.rm(b, n)
-        except Exception as e:
-            errors += str(e)
-
-    if errors:
-        return get_json_result(data=False, message=errors, code=settings.RetCode.SERVER_ERROR)
-
-    return get_json_result(data=True)
-
-
-@manager.route('/completion_aibotk', methods=['POST'])  # noqa: F821
-@validate_request("Authorization", "conversation_id", "word")
-def completion_faq():
-    import base64
-    req = request.json
-
-    token = req["Authorization"]
-    objs = APIToken.query(token=token)
-    if not objs:
-        return get_json_result(
-            data=False, message='Authentication error: API key is invalid!"', code=settings.RetCode.AUTHENTICATION_ERROR)
-
-    e, conv = API4ConversationService.get_by_id(req["conversation_id"])
-    if not e:
-        return get_data_error_result(message="Conversation not found!")
-    if "quote" not in req:
-        req["quote"] = True
-
-    msg = []
-    msg.append({"role": "user", "content": req["word"]})
-    if not msg[-1].get("id"):
-        msg[-1]["id"] = get_uuid()
-    message_id = msg[-1]["id"]
-
-    def fillin_conv(ans):
-        nonlocal conv, message_id
-        if not conv.reference:
-            conv.reference.append(ans["reference"])
-        else:
-            conv.reference[-1] = ans["reference"]
-        conv.message[-1] = {"role": "assistant", "content": ans["answer"], "id": message_id}
-        ans["id"] = message_id
-
-    try:
-        if conv.source == "agent":
-            conv.message.append(msg[-1])
-            e, cvs = UserCanvasService.get_by_id(conv.dialog_id)
-            if not e:
-                return server_error_response("canvas not found.")
-
-            if not isinstance(cvs.dsl, str):
-                cvs.dsl = json.dumps(cvs.dsl, ensure_ascii=False)
-
-            if not conv.reference:
-                conv.reference = []
-            conv.message.append({"role": "assistant", "content": "", "id": message_id})
-            conv.reference.append({"chunks": [], "doc_aggs": []})
-
-            final_ans = {"reference": [], "doc_aggs": []}
-            canvas = Canvas(cvs.dsl, objs[0].tenant_id)
-
-            canvas.messages.append(msg[-1])
-            canvas.add_user_input(msg[-1]["content"])
-            answer = canvas.run(stream=False)
-
-            assert answer is not None, "Nothing. Is it over?"
-
-            data_type_picture = {
-                "type": 3,
-                "url": "base64 content"
-            }
-            data = [
-                {
-                    "type": 1,
-                    "content": ""
-                }
-            ]
-            final_ans["content"] = "\n".join(answer["content"]) if "content" in answer else ""
-            canvas.messages.append({"role": "assistant", "content": final_ans["content"], "id": message_id})
-            if final_ans.get("reference"):
-                canvas.reference.append(final_ans["reference"])
-            cvs.dsl = json.loads(str(canvas))
-
-            ans = {"answer": final_ans["content"], "reference": final_ans.get("reference", [])}
-            data[0]["content"] += re.sub(r'##\d\$\$', '', ans["answer"])
-            fillin_conv(ans)
-            API4ConversationService.append_message(conv.id, conv.to_dict())
-
-            chunk_idxs = [int(match[2]) for match in re.findall(r'##\d\$\$', ans["answer"])]
-            for chunk_idx in chunk_idxs[:1]:
-                if ans["reference"]["chunks"][chunk_idx]["img_id"]:
-                    try:
-                        bkt, nm = ans["reference"]["chunks"][chunk_idx]["img_id"].split("-")
-                        response = STORAGE_IMPL.get(bkt, nm)
-                        data_type_picture["url"] = base64.b64encode(response).decode('utf-8')
-                        data.append(data_type_picture)
-                        break
-                    except Exception as e:
-                        return server_error_response(e)
-
-            response = {"code": 200, "msg": "success", "data": data}
-            return response
-
-        # ******************For dialog******************
-        conv.message.append(msg[-1])
-        e, dia = DialogService.get_by_id(conv.dialog_id)
-        if not e:
-            return get_data_error_result(message="Dialog not found!")
-        del req["conversation_id"]
-
-        if not conv.reference:
-            conv.reference = []
-        conv.message.append({"role": "assistant", "content": "", "id": message_id})
-        conv.reference.append({"chunks": [], "doc_aggs": []})
-
-        data_type_picture = {
-            "type": 3,
-            "url": "base64 content"
-        }
-        data = [
-            {
-                "type": 1,
-                "content": ""
-            }
-        ]
-        ans = ""
-        for a in chat(dia, msg, stream=False, **req):
-            ans = a
-            break
-        data[0]["content"] += re.sub(r'##\d\$\$', '', ans["answer"])
-        fillin_conv(ans)
-        API4ConversationService.append_message(conv.id, conv.to_dict())
-
-        chunk_idxs = [int(match[2]) for match in re.findall(r'##\d\$\$', ans["answer"])]
-        for chunk_idx in chunk_idxs[:1]:
-            if ans["reference"]["chunks"][chunk_idx]["img_id"]:
-                try:
-                    bkt, nm = ans["reference"]["chunks"][chunk_idx]["img_id"].split("-")
-                    response = STORAGE_IMPL.get(bkt, nm)
-                    data_type_picture["url"] = base64.b64encode(response).decode('utf-8')
-                    data.append(data_type_picture)
-                    break
-                except Exception as e:
-                    return server_error_response(e)
-
-        response = {"code": 200, "msg": "success", "data": data}
-        return response
-
-    except Exception as e:
-        return server_error_response(e)
-
-
-@manager.route('/retrieval', methods=['POST'])  # noqa: F821
-@validate_request("kb_id", "question")
-def retrieval():
-    token = request.headers.get('Authorization').split()[1]
-    objs = APIToken.query(token=token)
-    if not objs:
-        return get_json_result(
-            data=False, message='Authentication error: API key is invalid!"', code=settings.RetCode.AUTHENTICATION_ERROR)
-
-    req = request.json
-    kb_ids = req.get("kb_id", [])
-    doc_ids = req.get("doc_ids", [])
-    question = req.get("question")
-    page = int(req.get("page", 1))
-    size = int(req.get("page_size", 30))
-    similarity_threshold = float(req.get("similarity_threshold", 0.2))
-    vector_similarity_weight = float(req.get("vector_similarity_weight", 0.3))
-    top = int(req.get("top_k", 1024))
-    highlight = bool(req.get("highlight", False)) 
-
-    try:
-        kbs = KnowledgebaseService.get_by_ids(kb_ids)
-        embd_nms = list(set([kb.embd_id for kb in kbs]))
-        if len(embd_nms) != 1:
-            return get_json_result(
-                data=False, message='Knowledge bases use different embedding models or does not exist."',
-                code=settings.RetCode.AUTHENTICATION_ERROR)
-
-        embd_mdl = LLMBundle(kbs[0].tenant_id, LLMType.EMBEDDING, llm_name=kbs[0].embd_id)
-        rerank_mdl = None
-        if req.get("rerank_id"):
-            rerank_mdl = LLMBundle(kbs[0].tenant_id, LLMType.RERANK, llm_name=req["rerank_id"])
-        if req.get("keyword", False):
-            chat_mdl = LLMBundle(kbs[0].tenant_id, LLMType.CHAT)
-            question += keyword_extraction(chat_mdl, question)
-        ranks = settings.retriever.retrieval(question, embd_mdl, kbs[0].tenant_id, kb_ids, page, size,
-                                               similarity_threshold, vector_similarity_weight, top,
-                                               doc_ids, rerank_mdl=rerank_mdl, highlight= highlight,
-                                               rank_feature=label_question(question, kbs))
-        for c in ranks["chunks"]:
-            c.pop("vector", None)
-        return get_json_result(data=ranks)
-    except Exception as e:
-        if str(e).find("not_found") > 0:
-            return get_json_result(data=False, message='No chunk found! Check the chunk status please!',
-                                   code=settings.RetCode.DATA_ERROR)
-        return server_error_response(e)

api/apps/auth/github.py

@@ -34,7 +34,7 @@ class GithubOAuthClient(OAuthClient):
 
     def fetch_user_info(self, access_token, **kwargs):
         """
-        Fetch github user info.
+        Fetch GitHub user info.
         """
         user_info = {}
         try:

api/apps/auth/oidc.py

@@ -43,7 +43,8 @@ class OIDCClient(OAuthClient):
         self.jwks_uri = config['jwks_uri']
 
 
-    def _load_oidc_metadata(self, issuer):
+    @staticmethod
+    def _load_oidc_metadata(issuer):
         """
         Load OIDC metadata from `/.well-known/openid-configuration`.
         """

api/apps/canvas_app.py

@@ -18,14 +18,9 @@ import logging
 import re
 import sys
 from functools import partial
-
-import flask
 import trio
-from flask import request, Response
+from quart import request, Response, make_response
-from flask_login import login_required, current_user
-
 from agent.component import LLM
-from api import settings
 from api.db import CanvasCategory, FileType
 from api.db.services.canvas_service import CanvasTemplateService, UserCanvasService, API4ConversationService
 from api.db.services.document_service import DocumentService
@@ -34,9 +29,10 @@ from api.db.services.pipeline_operation_log_service import PipelineOperationLogS
 from api.db.services.task_service import queue_dataflow, CANVAS_DEBUG_DOC_ID, TaskService
 from api.db.services.user_service import TenantService
 from api.db.services.user_canvas_version import UserCanvasVersionService
-from api.settings import RetCode
+from common.constants import RetCode
-from api.utils import get_uuid
+from common.misc_utils import get_uuid
-from api.utils.api_utils import get_json_result, server_error_response, validate_request, get_data_error_result
+from api.utils.api_utils import get_json_result, server_error_response, validate_request, get_data_error_result, \
+    request_json
 from agent.canvas import Canvas
 from peewee import MySQLDatabase, PostgresqlDatabase
 from api.db.db_models import APIToken, Task
@@ -46,6 +42,8 @@ from api.utils.file_utils import filename_type, read_potential_broken_pdf
 from rag.flow.pipeline import Pipeline
 from rag.nlp import search
 from rag.utils.redis_conn import REDIS_CONN
+from common import settings
+from api.apps import login_required, current_user
 
 
 @manager.route('/templates', methods=['GET'])  # noqa: F821
@@ -57,8 +55,9 @@ def templates():
 @manager.route('/rm', methods=['POST'])  # noqa: F821
 @validate_request("canvas_ids")
 @login_required
-def rm():
+async def rm():
-    for i in request.json["canvas_ids"]:
+    req = await request_json()
+    for i in req["canvas_ids"]:
         if not UserCanvasService.accessible(i, current_user.id):
             return get_json_result(
                 data=False, message='Only owner of canvas authorized for this operation.',
@@ -70,8 +69,8 @@ def rm():
 @manager.route('/set', methods=['POST'])  # noqa: F821
 @validate_request("dsl", "title")
 @login_required
-def save():
+async def save():
-    req = request.json
+    req = await request_json()
     if not isinstance(req["dsl"], str):
         req["dsl"] = json.dumps(req["dsl"], ensure_ascii=False)
     req["dsl"] = json.loads(req["dsl"])
@@ -129,8 +128,8 @@ def getsse(canvas_id):
 @manager.route('/completion', methods=['POST'])  # noqa: F821
 @validate_request("id")
 @login_required
-def run():
+async def run():
-    req = request.json
+    req = await request_json()
     query = req.get("query", "")
     files = req.get("files", [])
     inputs = req.get("inputs", {})
@@ -156,20 +155,22 @@ def run():
         return get_json_result(data={"message_id": task_id})
 
     try:
-        canvas = Canvas(cvs.dsl, current_user.id, req["id"])
+        canvas = Canvas(cvs.dsl, current_user.id)
     except Exception as e:
         return server_error_response(e)
 
-    def sse():
+    async def sse():
         nonlocal canvas, user_id
         try:
-            for ans in canvas.run(query=query, files=files, user_id=user_id, inputs=inputs):
+            async for ans in canvas.run(query=query, files=files, user_id=user_id, inputs=inputs):
                 yield "data:" + json.dumps(ans, ensure_ascii=False) + "\n\n"
 
             cvs.dsl = json.loads(str(canvas))
             UserCanvasService.update_by_id(req["id"], cvs.to_dict())
+
         except Exception as e:
             logging.exception(e)
+            canvas.cancel_task()
             yield "data:" + json.dumps({"code": 500, "message": str(e), "data": False}, ensure_ascii=False) + "\n\n"
 
     resp = Response(sse(), mimetype="text/event-stream")
@@ -177,14 +178,15 @@ def run():
     resp.headers.add_header("Connection", "keep-alive")
     resp.headers.add_header("X-Accel-Buffering", "no")
     resp.headers.add_header("Content-Type", "text/event-stream; charset=utf-8")
+    #resp.call_on_close(lambda: canvas.cancel_task())
     return resp
 
 
 @manager.route('/rerun', methods=['POST'])  # noqa: F821
 @validate_request("id", "dsl", "component_id")
 @login_required
-def rerun():
+async def rerun():
-    req = request.json
+    req = await request_json()
     doc = PipelineOperationLogService.get_documents_info(req["id"])
     if not doc:
         return get_data_error_result(message="Document not found.")
@@ -221,8 +223,8 @@ def cancel(task_id):
 @manager.route('/reset', methods=['POST'])  # noqa: F821
 @validate_request("id")
 @login_required
-def reset():
+async def reset():
-    req = request.json
+    req = await request_json()
     if not UserCanvasService.accessible(req["id"], current_user.id):
         return get_json_result(
             data=False, message='Only owner of canvas authorized for this operation.',
@@ -242,7 +244,7 @@ def reset():
 
 
 @manager.route("/upload/<canvas_id>", methods=["POST"])  # noqa: F821
-def upload(canvas_id):
+async def upload(canvas_id):
     e, cvs = UserCanvasService.get_by_canvas_id(canvas_id)
     if not e:
         return get_data_error_result(message="canvas not found.")
@@ -308,7 +310,8 @@ def upload(canvas_id):
         except Exception as e:
             return  server_error_response(e)
 
-    file = request.files['file']
+    files = await request.files
+    file = files['file']
     try:
         DocumentService.check_doc_health(user_id, file.filename)
         return get_json_result(data=structured(file.filename, filename_type(file.filename), file.read(), file.content_type))
@@ -339,8 +342,8 @@ def input_form():
 @manager.route('/debug', methods=['POST'])  # noqa: F821
 @validate_request("id", "component_id", "params")
 @login_required
-def debug():
+async def debug():
-    req = request.json
+    req = await request_json()
     if not UserCanvasService.accessible(req["id"], current_user.id):
         return get_json_result(
             data=False, message='Only owner of canvas authorized for this operation.',
@@ -371,8 +374,8 @@ def debug():
 @manager.route('/test_db_connect', methods=['POST'])  # noqa: F821
 @validate_request("db_type", "database", "username", "host", "port", "password")
 @login_required
-def test_db_connect():
+async def test_db_connect():
-    req = request.json
+    req = await request_json()
     try:
         if req["db_type"] in ["mysql", "mariadb"]:
             db = MySQLDatabase(req["database"], user=req["username"], host=req["host"], port=req["port"],
@@ -410,22 +413,21 @@ def test_db_connect():
             ibm_db.close(conn)
             return get_json_result(data="Database Connection Successful!")
         elif req["db_type"] == 'trino':
-            def _parse_catalog_schema(db: str):
+            def _parse_catalog_schema(db_name: str):
-                if not db:
+                if not db_name:
                     return None, None
-                if "." in db:
+                if "." in db_name:
-                    c, s = db.split(".", 1)
+                    catalog_name, schema_name = db_name.split(".", 1)
-                elif "/" in db:
+                elif "/" in db_name:
-                    c, s = db.split("/", 1)
+                    catalog_name, schema_name = db_name.split("/", 1)
                 else:
-                    c, s = db, "default"
+                    catalog_name, schema_name = db_name, "default"
-                return c, s
+                return catalog_name, schema_name
             try:
                 import trino
                 import os
-                from trino.auth import BasicAuthentication
+            except Exception as e:
-            except Exception:
+                return server_error_response(f"Missing dependency 'trino'. Please install: pip install trino, detail: {e}")
-                return server_error_response("Missing dependency 'trino'. Please install: pip install trino")
 
             catalog, schema = _parse_catalog_schema(req["database"])
             if not catalog:
@@ -435,7 +437,7 @@ def test_db_connect():
 
             auth = None
             if http_scheme == "https" and req.get("password"):
-                auth = BasicAuthentication(req.get("username") or "ragflow", req["password"])
+                auth = trino.BasicAuthentication(req.get("username") or "ragflow", req["password"])
 
             conn = trino.dbapi.connect(
                 host=req["host"],
@@ -468,8 +470,8 @@ def test_db_connect():
 @login_required
 def getlistversion(canvas_id):
     try:
-        list =sorted([c.to_dict() for c in UserCanvasVersionService.list_by_canvas_id(canvas_id)], key=lambda x: x["update_time"]*-1)
+        versions =sorted([c.to_dict() for c in UserCanvasVersionService.list_by_canvas_id(canvas_id)], key=lambda x: x["update_time"]*-1)
-        return get_json_result(data=list)
+        return get_json_result(data=versions)
     except Exception as e:
         return get_data_error_result(message=f"Error getting history files: {e}")
 
@@ -479,7 +481,6 @@ def getlistversion(canvas_id):
 @login_required
 def getversion( version_id):
     try:
-
         e, version = UserCanvasVersionService.get_by_id(version_id)
         if version:
             return get_json_result(data=version.to_dict())
@@ -518,8 +519,8 @@ def list_canvas():
 @manager.route('/setting', methods=['POST'])  # noqa: F821
 @validate_request("id", "title", "permission")
 @login_required
-def setting():
+async def setting():
-    req = request.json
+    req = await request_json()
     req["user_id"] = current_user.id
 
     if not UserCanvasService.accessible(req["id"], current_user.id):
@@ -546,11 +547,11 @@ def trace():
     cvs_id = request.args.get("canvas_id")
     msg_id = request.args.get("message_id")
     try:
-        bin = REDIS_CONN.get(f"{cvs_id}-{msg_id}-logs")
+        binary = REDIS_CONN.get(f"{cvs_id}-{msg_id}-logs")
-        if not bin:
+        if not binary:
             return get_json_result(data={})
 
-        return get_json_result(data=json.loads(bin.encode("utf-8")))
+        return get_json_result(data=json.loads(binary.encode("utf-8")))
     except Exception as e:
         logging.exception(e)
 
@@ -600,8 +601,8 @@ def prompts():
 
 
 @manager.route('/download', methods=['GET'])  # noqa: F821
-def download():
+async def download():
     id = request.args.get("id")
     created_by = request.args.get("created_by")
     blob = FileService.get_blob(created_by, id)
-    return flask.make_response(blob)
+    return await make_response(blob)

api/apps/chunk_app.py

@@ -18,31 +18,31 @@ import json
 import re
 
 import xxhash
-from flask import request
+from quart import request
-from flask_login import current_user, login_required
 
-from api import settings
-from api.db import LLMType, ParserType
 from api.db.services.dialog_service import meta_filter
 from api.db.services.document_service import DocumentService
 from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.db.services.llm_service import LLMBundle
 from api.db.services.search_service import SearchService
 from api.db.services.user_service import UserTenantService
-from api.utils.api_utils import get_data_error_result, get_json_result, server_error_response, validate_request
+from api.utils.api_utils import get_data_error_result, get_json_result, server_error_response, validate_request, \
+    request_json
 from rag.app.qa import beAdoc, rmPrefix
 from rag.app.tag import label_question
 from rag.nlp import rag_tokenizer, search
 from rag.prompts.generator import gen_meta_filter, cross_languages, keyword_extraction
-from rag.settings import PAGERANK_FLD
+from common.string_utils import remove_redundant_spaces
-from rag.utils import rmSpace
+from common.constants import RetCode, LLMType, ParserType, PAGERANK_FLD
+from common import settings
+from api.apps import login_required, current_user
 
 
 @manager.route('/list', methods=['POST'])  # noqa: F821
 @login_required
 @validate_request("doc_id")
-def list_chunk():
+async def list_chunk():
-    req = request.json
+    req = await request_json()
     doc_id = req["doc_id"]
     page = int(req.get("page", 1))
     size = int(req.get("size", 30))
@@ -60,12 +60,12 @@ def list_chunk():
         }
         if "available_int" in req:
             query["available_int"] = int(req["available_int"])
-        sres = settings.retriever.search(query, search.index_name(tenant_id), kb_ids, highlight=True)
+        sres = settings.retriever.search(query, search.index_name(tenant_id), kb_ids, highlight=["content_ltks"])
         res = {"total": sres.total, "chunks": [], "doc": doc.to_dict()}
         for id in sres.ids:
             d = {
                 "chunk_id": id,
-                "content_with_weight": rmSpace(sres.highlight[id]) if question and id in sres.highlight else sres.field[
+                "content_with_weight": remove_redundant_spaces(sres.highlight[id]) if question and id in sres.highlight else sres.field[
                     id].get(
                     "content_with_weight", ""),
                 "doc_id": sres.field[id]["doc_id"],
@@ -83,7 +83,7 @@ def list_chunk():
     except Exception as e:
         if str(e).find("not_found") > 0:
             return get_json_result(data=False, message='No chunk found!',
-                                   code=settings.RetCode.DATA_ERROR)
+                                   code=RetCode.DATA_ERROR)
         return server_error_response(e)
 
 
@@ -115,15 +115,15 @@ def get():
     except Exception as e:
         if str(e).find("NotFoundError") >= 0:
             return get_json_result(data=False, message='Chunk not found!',
-                                   code=settings.RetCode.DATA_ERROR)
+                                   code=RetCode.DATA_ERROR)
         return server_error_response(e)
 
 
 @manager.route('/set', methods=['POST'])  # noqa: F821
 @login_required
 @validate_request("doc_id", "chunk_id", "content_with_weight")
-def set():
+async def set():
-    req = request.json
+    req = await request_json()
     d = {
         "id": req["chunk_id"],
         "content_with_weight": req["content_with_weight"]}
@@ -179,8 +179,8 @@ def set():
 @manager.route('/switch', methods=['POST'])  # noqa: F821
 @login_required
 @validate_request("chunk_ids", "available_int", "doc_id")
-def switch():
+async def switch():
-    req = request.json
+    req = await request_json()
     try:
         e, doc = DocumentService.get_by_id(req["doc_id"])
         if not e:
@@ -199,9 +199,8 @@ def switch():
 @manager.route('/rm', methods=['POST'])  # noqa: F821
 @login_required
 @validate_request("chunk_ids", "doc_id")
-def rm():
+async def rm():
-    from rag.utils.storage_factory import STORAGE_IMPL
+    req = await request_json()
-    req = request.json
     try:
         e, doc = DocumentService.get_by_id(req["doc_id"])
         if not e:
@@ -214,8 +213,8 @@ def rm():
         chunk_number = len(deleted_chunk_ids)
         DocumentService.decrement_chunk_num(doc.id, doc.kb_id, 1, chunk_number, 0)
         for cid in deleted_chunk_ids:
-            if STORAGE_IMPL.obj_exist(doc.kb_id, cid):
+            if settings.STORAGE_IMPL.obj_exist(doc.kb_id, cid):
-                STORAGE_IMPL.rm(doc.kb_id, cid)
+                settings.STORAGE_IMPL.rm(doc.kb_id, cid)
         return get_json_result(data=True)
     except Exception as e:
         return server_error_response(e)
@@ -224,8 +223,8 @@ def rm():
 @manager.route('/create', methods=['POST'])  # noqa: F821
 @login_required
 @validate_request("doc_id", "content_with_weight")
-def create():
+async def create():
-    req = request.json
+    req = await request_json()
     chunck_id = xxhash.xxh64((req["content_with_weight"] + req["doc_id"]).encode("utf-8")).hexdigest()
     d = {"id": chunck_id, "content_ltks": rag_tokenizer.tokenize(req["content_with_weight"]),
          "content_with_weight": req["content_with_weight"]}
@@ -282,8 +281,8 @@ def create():
 @manager.route('/retrieval_test', methods=['POST'])  # noqa: F821
 @login_required
 @validate_request("kb_id", "question")
-def retrieval_test():
+async def retrieval_test():
-    req = request.json
+    req = await request_json()
     page = int(req.get("page", 1))
     size = int(req.get("size", 30))
     question = req["question"]
@@ -292,7 +291,7 @@ def retrieval_test():
         kb_ids = [kb_ids]
     if not kb_ids:
         return get_json_result(data=False, message='Please specify dataset firstly.',
-                               code=settings.RetCode.DATA_ERROR)
+                               code=RetCode.DATA_ERROR)
 
     doc_ids = req.get("doc_ids", [])
     use_kg = req.get("use_kg", False)
@@ -306,14 +305,14 @@ def retrieval_test():
         metas = DocumentService.get_meta_by_kbs(kb_ids)
         if meta_data_filter.get("method") == "auto":
             chat_mdl = LLMBundle(current_user.id, LLMType.CHAT, llm_name=search_config.get("chat_id", ""))
-            filters = gen_meta_filter(chat_mdl, metas, question)
+            filters: dict = gen_meta_filter(chat_mdl, metas, question)
-            doc_ids.extend(meta_filter(metas, filters))
+            doc_ids.extend(meta_filter(metas, filters["conditions"], filters.get("logic", "and")))
             if not doc_ids:
                 doc_ids = None
         elif meta_data_filter.get("method") == "manual":
-            doc_ids.extend(meta_filter(metas, meta_data_filter["manual"]))
+            doc_ids.extend(meta_filter(metas, meta_data_filter["manual"], meta_data_filter.get("logic", "and")))
-            if not doc_ids:
+            if meta_data_filter["manual"] and not doc_ids:
-                doc_ids = None
+                doc_ids = ["-999"]
 
     try:
         tenants = UserTenantService.query(user_id=current_user.id)
@@ -326,7 +325,7 @@ def retrieval_test():
             else:
                 return get_json_result(
                     data=False, message='Only owner of knowledgebase authorized for this operation.',
-                    code=settings.RetCode.OPERATING_ERROR)
+                    code=RetCode.OPERATING_ERROR)
 
         e, kb = KnowledgebaseService.get_by_id(kb_ids[0])
         if not e:
@@ -350,7 +349,8 @@ def retrieval_test():
                                float(req.get("similarity_threshold", 0.0)),
                                float(req.get("vector_similarity_weight", 0.3)),
                                top,
-                               doc_ids, rerank_mdl=rerank_mdl, highlight=req.get("highlight"),
+                               doc_ids, rerank_mdl=rerank_mdl,
+                                             highlight=req.get("highlight", False),
                                rank_feature=labels
                                )
         if use_kg:
@@ -370,7 +370,7 @@ def retrieval_test():
     except Exception as e:
         if str(e).find("not_found") > 0:
             return get_json_result(data=False, message='No chunk found! Check the chunk status please!',
-                                   code=settings.RetCode.DATA_ERROR)
+                                   code=RetCode.DATA_ERROR)
         return server_error_response(e)
 
 

api/apps/connector_app.py

@@ -0,0 +1,295 @@
+#
+#  Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+import asyncio
+import json
+import logging
+import time
+import uuid
+from html import escape
+from typing import Any
+
+from quart import request, make_response
+from google_auth_oauthlib.flow import Flow
+
+from api.db import InputType
+from api.db.services.connector_service import ConnectorService, SyncLogsService
+from api.utils.api_utils import get_data_error_result, get_json_result, validate_request
+from common.constants import RetCode, TaskStatus
+from common.data_source.config import GOOGLE_DRIVE_WEB_OAUTH_REDIRECT_URI, DocumentSource
+from common.data_source.google_util.constant import GOOGLE_DRIVE_WEB_OAUTH_POPUP_TEMPLATE, GOOGLE_SCOPES
+from common.misc_utils import get_uuid
+from rag.utils.redis_conn import REDIS_CONN
+from api.apps import login_required, current_user
+
+
+@manager.route("/set", methods=["POST"])  # noqa: F821
+@login_required
+async def set_connector():
+    req = await request.json
+    if req.get("id"):
+        conn = {fld: req[fld] for fld in ["prune_freq", "refresh_freq", "config", "timeout_secs"] if fld in req}
+        ConnectorService.update_by_id(req["id"], conn)
+    else:
+        req["id"] = get_uuid()
+        conn = {
+            "id": req["id"],
+            "tenant_id": current_user.id,
+            "name": req["name"],
+            "source": req["source"],
+            "input_type": InputType.POLL,
+            "config": req["config"],
+            "refresh_freq": int(req.get("refresh_freq", 30)),
+            "prune_freq": int(req.get("prune_freq", 720)),
+            "timeout_secs": int(req.get("timeout_secs", 60 * 29)),
+            "status": TaskStatus.SCHEDULE,
+        }
+        ConnectorService.save(**conn)
+
+    await asyncio.sleep(1)
+    e, conn = ConnectorService.get_by_id(req["id"])
+
+    return get_json_result(data=conn.to_dict())
+
+
+@manager.route("/list", methods=["GET"])  # noqa: F821
+@login_required
+def list_connector():
+    return get_json_result(data=ConnectorService.list(current_user.id))
+
+
+@manager.route("/<connector_id>", methods=["GET"])  # noqa: F821
+@login_required
+def get_connector(connector_id):
+    e, conn = ConnectorService.get_by_id(connector_id)
+    if not e:
+        return get_data_error_result(message="Can't find this Connector!")
+    return get_json_result(data=conn.to_dict())
+
+
+@manager.route("/<connector_id>/logs", methods=["GET"])  # noqa: F821
+@login_required
+def list_logs(connector_id):
+    req = request.args.to_dict(flat=True)
+    arr, total = SyncLogsService.list_sync_tasks(connector_id, int(req.get("page", 1)), int(req.get("page_size", 15)))
+    return get_json_result(data={"total": total, "logs": arr})
+
+
+@manager.route("/<connector_id>/resume", methods=["PUT"])  # noqa: F821
+@login_required
+async def resume(connector_id):
+    req = await request.json
+    if req.get("resume"):
+        ConnectorService.resume(connector_id, TaskStatus.SCHEDULE)
+    else:
+        ConnectorService.resume(connector_id, TaskStatus.CANCEL)
+    return get_json_result(data=True)
+
+
+@manager.route("/<connector_id>/rebuild", methods=["PUT"])  # noqa: F821
+@login_required
+@validate_request("kb_id")
+async def rebuild(connector_id):
+    req = await request.json
+    err = ConnectorService.rebuild(req["kb_id"], connector_id, current_user.id)
+    if err:
+        return get_json_result(data=False, message=err, code=RetCode.SERVER_ERROR)
+    return get_json_result(data=True)
+
+
+@manager.route("/<connector_id>/rm", methods=["POST"])  # noqa: F821
+@login_required
+def rm_connector(connector_id):
+    ConnectorService.resume(connector_id, TaskStatus.CANCEL)
+    ConnectorService.delete_by_id(connector_id)
+    return get_json_result(data=True)
+
+
+GOOGLE_WEB_FLOW_STATE_PREFIX = "google_drive_web_flow_state"
+GOOGLE_WEB_FLOW_RESULT_PREFIX = "google_drive_web_flow_result"
+WEB_FLOW_TTL_SECS = 15 * 60
+
+
+def _web_state_cache_key(flow_id: str) -> str:
+    return f"{GOOGLE_WEB_FLOW_STATE_PREFIX}:{flow_id}"
+
+
+def _web_result_cache_key(flow_id: str) -> str:
+    return f"{GOOGLE_WEB_FLOW_RESULT_PREFIX}:{flow_id}"
+
+
+def _load_credentials(payload: str | dict[str, Any]) -> dict[str, Any]:
+    if isinstance(payload, dict):
+        return payload
+    try:
+        return json.loads(payload)
+    except json.JSONDecodeError as exc:  # pragma: no cover - defensive
+        raise ValueError("Invalid Google credentials JSON.") from exc
+
+
+def _get_web_client_config(credentials: dict[str, Any]) -> dict[str, Any]:
+    web_section = credentials.get("web")
+    if not isinstance(web_section, dict):
+        raise ValueError("Google OAuth JSON must include a 'web' client configuration to use browser-based authorization.")
+    return {"web": web_section}
+
+
+async def _render_web_oauth_popup(flow_id: str, success: bool, message: str):
+    status = "success" if success else "error"
+    auto_close = "window.close();" if success else ""
+    escaped_message = escape(message)
+    payload_json = json.dumps(
+        {
+            "type": "ragflow-google-drive-oauth",
+            "status": status,
+            "flowId": flow_id or "",
+            "message": message,
+        }
+    )
+    html = GOOGLE_DRIVE_WEB_OAUTH_POPUP_TEMPLATE.format(
+        heading="Authorization complete" if success else "Authorization failed",
+        message=escaped_message,
+        payload_json=payload_json,
+        auto_close=auto_close,
+    )
+    response = await make_response(html, 200)
+    response.headers["Content-Type"] = "text/html; charset=utf-8"
+    return response
+
+
+@manager.route("/google-drive/oauth/web/start", methods=["POST"])  # noqa: F821
+@login_required
+@validate_request("credentials")
+async def start_google_drive_web_oauth():
+    if not GOOGLE_DRIVE_WEB_OAUTH_REDIRECT_URI:
+        return get_json_result(
+            code=RetCode.SERVER_ERROR,
+            message="Google Drive OAuth redirect URI is not configured on the server.",
+        )
+
+    req = await request.json or {}
+    raw_credentials = req.get("credentials", "")
+    try:
+        credentials = _load_credentials(raw_credentials)
+    except ValueError as exc:
+        return get_json_result(code=RetCode.ARGUMENT_ERROR, message=str(exc))
+
+    if credentials.get("refresh_token"):
+        return get_json_result(
+            code=RetCode.ARGUMENT_ERROR,
+            message="Uploaded credentials already include a refresh token.",
+        )
+
+    try:
+        client_config = _get_web_client_config(credentials)
+    except ValueError as exc:
+        return get_json_result(code=RetCode.ARGUMENT_ERROR, message=str(exc))
+
+    flow_id = str(uuid.uuid4())
+    try:
+        flow = Flow.from_client_config(client_config, scopes=GOOGLE_SCOPES[DocumentSource.GOOGLE_DRIVE])
+        flow.redirect_uri = GOOGLE_DRIVE_WEB_OAUTH_REDIRECT_URI
+        authorization_url, _ = flow.authorization_url(
+            access_type="offline",
+            include_granted_scopes="true",
+            prompt="consent",
+            state=flow_id,
+        )
+    except Exception as exc:  # pragma: no cover - defensive
+        logging.exception("Failed to create Google OAuth flow: %s", exc)
+        return get_json_result(
+            code=RetCode.SERVER_ERROR,
+            message="Failed to initialize Google OAuth flow. Please verify the uploaded client configuration.",
+        )
+
+    cache_payload = {
+        "user_id": current_user.id,
+        "client_config": client_config,
+        "created_at": int(time.time()),
+    }
+    REDIS_CONN.set_obj(_web_state_cache_key(flow_id), cache_payload, WEB_FLOW_TTL_SECS)
+
+    return get_json_result(
+        data={
+            "flow_id": flow_id,
+            "authorization_url": authorization_url,
+            "expires_in": WEB_FLOW_TTL_SECS,
+        }
+    )
+
+
+@manager.route("/google-drive/oauth/web/callback", methods=["GET"])  # noqa: F821
+async def google_drive_web_oauth_callback():
+    state_id = request.args.get("state")
+    error = request.args.get("error")
+    error_description = request.args.get("error_description") or error
+
+    if not state_id:
+        return await _render_web_oauth_popup("", False, "Missing OAuth state parameter.")
+
+    state_cache = REDIS_CONN.get(_web_state_cache_key(state_id))
+    if not state_cache:
+        return await _render_web_oauth_popup(state_id, False, "Authorization session expired. Please restart from the main window.")
+
+    state_obj = json.loads(state_cache)
+    client_config = state_obj.get("client_config")
+    if not client_config:
+        REDIS_CONN.delete(_web_state_cache_key(state_id))
+        return await _render_web_oauth_popup(state_id, False, "Authorization session was invalid. Please retry.")
+
+    if error:
+        REDIS_CONN.delete(_web_state_cache_key(state_id))
+        return await _render_web_oauth_popup(state_id, False, error_description or "Authorization was cancelled.")
+
+    code = request.args.get("code")
+    if not code:
+        return await _render_web_oauth_popup(state_id, False, "Missing authorization code from Google.")
+
+    try:
+        flow = Flow.from_client_config(client_config, scopes=GOOGLE_SCOPES[DocumentSource.GOOGLE_DRIVE])
+        flow.redirect_uri = GOOGLE_DRIVE_WEB_OAUTH_REDIRECT_URI
+        flow.fetch_token(code=code)
+    except Exception as exc:  # pragma: no cover - defensive
+        logging.exception("Failed to exchange Google OAuth code: %s", exc)
+        REDIS_CONN.delete(_web_state_cache_key(state_id))
+        return await _render_web_oauth_popup(state_id, False, "Failed to exchange tokens with Google. Please retry.")
+
+    creds_json = flow.credentials.to_json()
+    result_payload = {
+        "user_id": state_obj.get("user_id"),
+        "credentials": creds_json,
+    }
+    REDIS_CONN.set_obj(_web_result_cache_key(state_id), result_payload, WEB_FLOW_TTL_SECS)
+    REDIS_CONN.delete(_web_state_cache_key(state_id))
+
+    return await _render_web_oauth_popup(state_id, True, "Authorization completed successfully.")
+
+
+@manager.route("/google-drive/oauth/web/result", methods=["POST"])  # noqa: F821
+@login_required
+@validate_request("flow_id")
+async def poll_google_drive_web_result():
+    req = await request.json or {}
+    flow_id = req.get("flow_id")
+    cache_raw = REDIS_CONN.get(_web_result_cache_key(flow_id))
+    if not cache_raw:
+        return get_json_result(code=RetCode.RUNNING, message="Authorization is still pending.")
+
+    result = json.loads(cache_raw)
+    if result.get("user_id") != current_user.id:
+        return get_json_result(code=RetCode.PERMISSION_ERROR, message="You are not allowed to access this authorization result.")
+
+    REDIS_CONN.delete(_web_result_cache_key(flow_id))
+    return get_json_result(data={"credentials": result.get("credentials")})

api/apps/conversation_app.py

@@ -17,10 +17,8 @@ import json
 import re
 import logging
 from copy import deepcopy
-from flask import Response, request
+from quart import Response, request
-from flask_login import current_user, login_required
+from api.apps import current_user, login_required
-from api import settings
-from api.db import LLMType
 from api.db.db_models import APIToken
 from api.db.services.conversation_service import ConversationService, structure_answer
 from api.db.services.dialog_service import DialogService, ask, chat, gen_mindmap
@@ -31,12 +29,13 @@ from api.db.services.user_service import TenantService, UserTenantService
 from api.utils.api_utils import get_data_error_result, get_json_result, server_error_response, validate_request
 from rag.prompts.template import load_prompt
 from rag.prompts.generator import chunks_format
+from common.constants import RetCode, LLMType
 
 
 @manager.route("/set", methods=["POST"])  # noqa: F821
 @login_required
-def set_conversation():
+async def set_conversation():
-    req = request.json
+    req = await request.json
     conv_id = req.get("conversation_id")
     is_new = req.get("is_new")
     name = req.get("name", "New conversation")
@@ -86,14 +85,13 @@ def get():
         if not e:
             return get_data_error_result(message="Conversation not found!")
         tenants = UserTenantService.query(user_id=current_user.id)
-        avatar = None
         for tenant in tenants:
             dialog = DialogService.query(tenant_id=tenant.tenant_id, id=conv.dialog_id)
             if dialog and len(dialog) > 0:
                 avatar = dialog[0].icon
                 break
         else:
-            return get_json_result(data=False, message="Only owner of conversation authorized for this operation.", code=settings.RetCode.OPERATING_ERROR)
+            return get_json_result(data=False, message="Only owner of conversation authorized for this operation.", code=RetCode.OPERATING_ERROR)
 
         for ref in conv.reference:
             if isinstance(ref, list):
@@ -130,8 +128,9 @@ def getsse(dialog_id):
 
 @manager.route("/rm", methods=["POST"])  # noqa: F821
 @login_required
-def rm():
+async def rm():
-    conv_ids = request.json["conversation_ids"]
+    req = await request.json
+    conv_ids = req["conversation_ids"]
     try:
         for cid in conv_ids:
             exist, conv = ConversationService.get_by_id(cid)
@@ -142,7 +141,7 @@ def rm():
                 if DialogService.query(tenant_id=tenant.tenant_id, id=conv.dialog_id):
                     break
             else:
-                return get_json_result(data=False, message="Only owner of conversation authorized for this operation.", code=settings.RetCode.OPERATING_ERROR)
+                return get_json_result(data=False, message="Only owner of conversation authorized for this operation.", code=RetCode.OPERATING_ERROR)
             ConversationService.delete_by_id(cid)
         return get_json_result(data=True)
     except Exception as e:
@@ -155,7 +154,7 @@ def list_conversation():
     dialog_id = request.args["dialog_id"]
     try:
         if not DialogService.query(tenant_id=current_user.id, id=dialog_id):
-            return get_json_result(data=False, message="Only owner of dialog authorized for this operation.", code=settings.RetCode.OPERATING_ERROR)
+            return get_json_result(data=False, message="Only owner of dialog authorized for this operation.", code=RetCode.OPERATING_ERROR)
         convs = ConversationService.query(dialog_id=dialog_id, order_by=ConversationService.model.create_time, reverse=True)
 
         convs = [d.to_dict() for d in convs]
@@ -167,8 +166,8 @@ def list_conversation():
 @manager.route("/completion", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("conversation_id", "messages")
-def completion():
+async def completion():
-    req = request.json
+    req = await request.json
     msg = []
     for m in req["messages"]:
         if m["role"] == "system":
@@ -252,8 +251,8 @@ def completion():
 
 @manager.route("/tts", methods=["POST"])  # noqa: F821
 @login_required
-def tts():
+async def tts():
-    req = request.json
+    req = await request.json
     text = req["text"]
 
     tenants = TenantService.get_info_by(current_user.id)
@@ -285,8 +284,8 @@ def tts():
 @manager.route("/delete_msg", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("conversation_id", "message_id")
-def delete_msg():
+async def delete_msg():
-    req = request.json
+    req = await request.json
     e, conv = ConversationService.get_by_id(req["conversation_id"])
     if not e:
         return get_data_error_result(message="Conversation not found!")
@@ -308,8 +307,8 @@ def delete_msg():
 @manager.route("/thumbup", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("conversation_id", "message_id")
-def thumbup():
+async def thumbup():
-    req = request.json
+    req = await request.json
     e, conv = ConversationService.get_by_id(req["conversation_id"])
     if not e:
         return get_data_error_result(message="Conversation not found!")
@@ -335,8 +334,8 @@ def thumbup():
 @manager.route("/ask", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("question", "kb_ids")
-def ask_about():
+async def ask_about():
-    req = request.json
+    req = await request.json
     uid = current_user.id
 
     search_id = req.get("search_id", "")
@@ -367,8 +366,8 @@ def ask_about():
 @manager.route("/mindmap", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("question", "kb_ids")
-def mindmap():
+async def mindmap():
-    req = request.json
+    req = await request.json
     search_id = req.get("search_id", "")
     search_app = SearchService.get_detail(search_id) if search_id else {}
     search_config = search_app.get("search_config", {}) if search_app else {}
@@ -385,8 +384,8 @@ def mindmap():
 @manager.route("/related_questions", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("question")
-def related_questions():
+async def related_questions():
-    req = request.json
+    req = await request.json
 
     search_id = req.get("search_id", "")
     search_config = {}

api/apps/dialog_app.py

@@ -14,25 +14,25 @@
 #  limitations under the License.
 #
 
-from flask import request
+from quart import request
-from flask_login import login_required, current_user
 from api.db.services import duplicate_name
 from api.db.services.dialog_service import DialogService
-from api.db import StatusEnum
+from common.constants import StatusEnum
 from api.db.services.tenant_llm_service import TenantLLMService
 from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.db.services.user_service import TenantService, UserTenantService
-from api import settings
 from api.utils.api_utils import server_error_response, get_data_error_result, validate_request
-from api.utils import get_uuid
+from common.misc_utils import get_uuid
+from common.constants import RetCode
 from api.utils.api_utils import get_json_result
+from api.apps import login_required, current_user
 
 
 @manager.route('/set', methods=['POST'])  # noqa: F821
 @validate_request("prompt_config")
 @login_required
-def set_dialog():
+async def set_dialog():
-    req = request.json
+    req = await request.json
     dialog_id = req.get("dialog_id", "")
     is_create = not dialog_id
     name = req.get("name", "New Dialog")
@@ -154,33 +154,34 @@ def get_kb_names(kb_ids):
 @login_required
 def list_dialogs():
     try:
-        diags = DialogService.query(
+        conversations = DialogService.query(
             tenant_id=current_user.id,
             status=StatusEnum.VALID.value,
             reverse=True,
             order_by=DialogService.model.create_time)
-        diags = [d.to_dict() for d in diags]
+        conversations = [d.to_dict() for d in conversations]
-        for d in diags:
+        for conversation in conversations:
-            d["kb_ids"], d["kb_names"] = get_kb_names(d["kb_ids"])
+            conversation["kb_ids"], conversation["kb_names"] = get_kb_names(conversation["kb_ids"])
-        return get_json_result(data=diags)
+        return get_json_result(data=conversations)
     except Exception as e:
         return server_error_response(e)
 
 
 @manager.route('/next', methods=['POST'])  # noqa: F821
 @login_required
-def list_dialogs_next():
+async def list_dialogs_next():
-    keywords = request.args.get("keywords", "")
+    args = request.args
-    page_number = int(request.args.get("page", 0))
+    keywords = args.get("keywords", "")
-    items_per_page = int(request.args.get("page_size", 0))
+    page_number = int(args.get("page", 0))
-    parser_id = request.args.get("parser_id")
+    items_per_page = int(args.get("page_size", 0))
-    orderby = request.args.get("orderby", "create_time")
+    parser_id = args.get("parser_id")
-    if request.args.get("desc", "true").lower() == "false":
+    orderby = args.get("orderby", "create_time")
+    if args.get("desc", "true").lower() == "false":
         desc = False
     else:
         desc = True
 
-    req = request.get_json()
+    req = await request.get_json()
     owner_ids = req.get("owner_ids", [])
     try:
         if not owner_ids:
@@ -207,8 +208,8 @@ def list_dialogs_next():
 @manager.route('/rm', methods=['POST'])  # noqa: F821
 @login_required
 @validate_request("dialog_ids")
-def rm():
+async def rm():
-    req = request.json
+    req = await request.json
     dialog_list=[]
     tenants = UserTenantService.query(user_id=current_user.id)
     try:
@@ -219,7 +220,7 @@ def rm():
             else:
                 return get_json_result(
                     data=False, message='Only owner of dialog authorized for this operation.',
-                    code=settings.RetCode.OPERATING_ERROR)
+                    code=RetCode.OPERATING_ERROR)
             dialog_list.append({"id": id,"status":StatusEnum.INVALID.value})
         DialogService.update_many_by_id(dialog_list)
         return get_json_result(data=True)

api/apps/document_app.py

@@ -18,66 +18,66 @@ import os.path
 import pathlib
 import re
 from pathlib import Path
-
+from quart import request, make_response
-import flask
+from api.apps import current_user, login_required
-from flask import request
-from flask_login import current_user, login_required
-
-from api import settings
 from api.common.check_team_permission import check_kb_team_permission
 from api.constants import FILE_NAME_LEN_LIMIT, IMG_BASE64_PREFIX
-from api.db import VALID_FILE_TYPES, VALID_TASK_STATUS, FileSource, FileType, ParserType, TaskStatus
+from api.db import VALID_FILE_TYPES, FileType
-from api.db.db_models import File, Task
+from api.db.db_models import Task
 from api.db.services import duplicate_name
 from api.db.services.document_service import DocumentService, doc_upload_and_parse
 from api.db.services.file2document_service import File2DocumentService
 from api.db.services.file_service import FileService
 from api.db.services.knowledgebase_service import KnowledgebaseService
-from api.db.services.task_service import TaskService, cancel_all_task_of, queue_tasks, queue_dataflow
+from api.db.services.task_service import TaskService, cancel_all_task_of
 from api.db.services.user_service import UserTenantService
-from api.utils import get_uuid
+from common.misc_utils import get_uuid
 from api.utils.api_utils import (
     get_data_error_result,
     get_json_result,
     server_error_response,
-    validate_request,
+    validate_request, request_json,
 )
-from api.utils.file_utils import filename_type, get_project_base_directory, thumbnail
+from api.utils.file_utils import filename_type, thumbnail
+from common.file_utils import get_project_base_directory
+from common.constants import RetCode, VALID_TASK_STATUS, ParserType, TaskStatus
 from api.utils.web_utils import CONTENT_TYPE_MAP, html2pdf, is_valid_url
 from deepdoc.parser.html_parser import RAGFlowHtmlParser
-from rag.nlp import search
+from rag.nlp import search, rag_tokenizer
-from rag.utils.storage_factory import STORAGE_IMPL
+from common import settings
 
 
 @manager.route("/upload", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("kb_id")
-def upload():
+async def upload():
-    kb_id = request.form.get("kb_id")
+    form = await request.form
+    kb_id = form.get("kb_id")
     if not kb_id:
-        return get_json_result(data=False, message='Lack of "KB ID"', code=settings.RetCode.ARGUMENT_ERROR)
+        return get_json_result(data=False, message='Lack of "KB ID"', code=RetCode.ARGUMENT_ERROR)
-    if "file" not in request.files:
+    files = await request.files
-        return get_json_result(data=False, message="No file part!", code=settings.RetCode.ARGUMENT_ERROR)
+    if "file" not in files:
+        return get_json_result(data=False, message="No file part!", code=RetCode.ARGUMENT_ERROR)
 
-    file_objs = request.files.getlist("file")
+    file_objs = files.getlist("file")
     for file_obj in file_objs:
         if file_obj.filename == "":
-            return get_json_result(data=False, message="No file selected!", code=settings.RetCode.ARGUMENT_ERROR)
+            return get_json_result(data=False, message="No file selected!", code=RetCode.ARGUMENT_ERROR)
         if len(file_obj.filename.encode("utf-8")) > FILE_NAME_LEN_LIMIT:
-            return get_json_result(data=False, message=f"File name must be {FILE_NAME_LEN_LIMIT} bytes or less.", code=settings.RetCode.ARGUMENT_ERROR)
+            return get_json_result(data=False, message=f"File name must be {FILE_NAME_LEN_LIMIT} bytes or less.", code=RetCode.ARGUMENT_ERROR)
 
     e, kb = KnowledgebaseService.get_by_id(kb_id)
     if not e:
         raise LookupError("Can't find this knowledgebase!")
     if not check_kb_team_permission(kb, current_user.id):
-        return get_json_result(data=False, message="No authorization.", code=settings.RetCode.AUTHENTICATION_ERROR)
+        return get_json_result(data=False, message="No authorization.", code=RetCode.AUTHENTICATION_ERROR)
 
     err, files = FileService.upload_document(kb, file_objs, current_user.id)
     if err:
-        return get_json_result(data=files, message="\n".join(err), code=settings.RetCode.SERVER_ERROR)
+        return get_json_result(data=files, message="\n".join(err), code=RetCode.SERVER_ERROR)
 
     if not files:
-        return get_json_result(data=files, message="There seems to be an issue with your file format. Please verify it is correct and not corrupted.", code=settings.RetCode.DATA_ERROR)
+        return get_json_result(data=files, message="There seems to be an issue with your file format. Please verify it is correct and not corrupted.", code=RetCode.DATA_ERROR)
     files = [f[0] for f in files]  # remove the blob
 
     return get_json_result(data=files)
@@ -86,19 +86,20 @@ def upload():
 @manager.route("/web_crawl", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("kb_id", "name", "url")
-def web_crawl():
+async def web_crawl():
-    kb_id = request.form.get("kb_id")
+    form = await request.form
+    kb_id = form.get("kb_id")
     if not kb_id:
-        return get_json_result(data=False, message='Lack of "KB ID"', code=settings.RetCode.ARGUMENT_ERROR)
+        return get_json_result(data=False, message='Lack of "KB ID"', code=RetCode.ARGUMENT_ERROR)
-    name = request.form.get("name")
+    name = form.get("name")
-    url = request.form.get("url")
+    url = form.get("url")
     if not is_valid_url(url):
-        return get_json_result(data=False, message="The URL format is invalid", code=settings.RetCode.ARGUMENT_ERROR)
+        return get_json_result(data=False, message="The URL format is invalid", code=RetCode.ARGUMENT_ERROR)
     e, kb = KnowledgebaseService.get_by_id(kb_id)
     if not e:
         raise LookupError("Can't find this knowledgebase!")
     if check_kb_team_permission(kb, current_user.id):
-        return get_json_result(data=False, message="No authorization.", code=settings.RetCode.AUTHENTICATION_ERROR)
+        return get_json_result(data=False, message="No authorization.", code=RetCode.AUTHENTICATION_ERROR)
 
     blob = html2pdf(url)
     if not blob:
@@ -117,9 +118,9 @@ def web_crawl():
             raise RuntimeError("This type of file has not been supported yet!")
 
         location = filename
-        while STORAGE_IMPL.obj_exist(kb_id, location):
+        while settings.STORAGE_IMPL.obj_exist(kb_id, location):
             location += "_"
-        STORAGE_IMPL.put(kb_id, location, blob)
+        settings.STORAGE_IMPL.put(kb_id, location, blob)
         doc = {
             "id": get_uuid(),
             "kb_id": kb.id,
@@ -151,16 +152,16 @@ def web_crawl():
 @manager.route("/create", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("name", "kb_id")
-def create():
+async def create():
-    req = request.json
+    req = await request_json()
     kb_id = req["kb_id"]
     if not kb_id:
-        return get_json_result(data=False, message='Lack of "KB ID"', code=settings.RetCode.ARGUMENT_ERROR)
+        return get_json_result(data=False, message='Lack of "KB ID"', code=RetCode.ARGUMENT_ERROR)
     if len(req["name"].encode("utf-8")) > FILE_NAME_LEN_LIMIT:
-        return get_json_result(data=False, message=f"File name must be {FILE_NAME_LEN_LIMIT} bytes or less.", code=settings.RetCode.ARGUMENT_ERROR)
+        return get_json_result(data=False, message=f"File name must be {FILE_NAME_LEN_LIMIT} bytes or less.", code=RetCode.ARGUMENT_ERROR)
 
     if req["name"].strip() == "":
-        return get_json_result(data=False, message="File name can't be empty.", code=settings.RetCode.ARGUMENT_ERROR)
+        return get_json_result(data=False, message="File name can't be empty.", code=RetCode.ARGUMENT_ERROR)
     req["name"] = req["name"].strip()
 
     try:
@@ -207,16 +208,16 @@ def create():
 
 @manager.route("/list", methods=["POST"])  # noqa: F821
 @login_required
-def list_docs():
+async def list_docs():
     kb_id = request.args.get("kb_id")
     if not kb_id:
-        return get_json_result(data=False, message='Lack of "KB ID"', code=settings.RetCode.ARGUMENT_ERROR)
+        return get_json_result(data=False, message='Lack of "KB ID"', code=RetCode.ARGUMENT_ERROR)
     tenants = UserTenantService.query(user_id=current_user.id)
     for tenant in tenants:
         if KnowledgebaseService.query(tenant_id=tenant.tenant_id, id=kb_id):
             break
     else:
-        return get_json_result(data=False, message="Only owner of knowledgebase authorized for this operation.", code=settings.RetCode.OPERATING_ERROR)
+        return get_json_result(data=False, message="Only owner of knowledgebase authorized for this operation.", code=RetCode.OPERATING_ERROR)
     keywords = request.args.get("keywords", "")
 
     page_number = int(request.args.get("page", 0))
@@ -229,7 +230,7 @@ def list_docs():
     create_time_from = int(request.args.get("create_time_from", 0))
     create_time_to = int(request.args.get("create_time_to", 0))
 
-    req = request.get_json()
+    req = await request.get_json()
 
     run_status = req.get("run_status", [])
     if run_status:
@@ -259,6 +260,8 @@ def list_docs():
         for doc_item in docs:
             if doc_item["thumbnail"] and not doc_item["thumbnail"].startswith(IMG_BASE64_PREFIX):
                 doc_item["thumbnail"] = f"/v1/document/image/{kb_id}-{doc_item['thumbnail']}"
+            if doc_item.get("source_type"):
+                doc_item["source_type"] = doc_item["source_type"].split("/")[0]
 
         return get_json_result(data={"total": tol, "docs": docs})
     except Exception as e:
@@ -267,18 +270,18 @@ def list_docs():
 
 @manager.route("/filter", methods=["POST"])  # noqa: F821
 @login_required
-def get_filter():
+async def get_filter():
-    req = request.get_json()
+    req = await request.get_json()
 
     kb_id = req.get("kb_id")
     if not kb_id:
-        return get_json_result(data=False, message='Lack of "KB ID"', code=settings.RetCode.ARGUMENT_ERROR)
+        return get_json_result(data=False, message='Lack of "KB ID"', code=RetCode.ARGUMENT_ERROR)
     tenants = UserTenantService.query(user_id=current_user.id)
     for tenant in tenants:
         if KnowledgebaseService.query(tenant_id=tenant.tenant_id, id=kb_id):
             break
     else:
-        return get_json_result(data=False, message="Only owner of knowledgebase authorized for this operation.", code=settings.RetCode.OPERATING_ERROR)
+        return get_json_result(data=False, message="Only owner of knowledgebase authorized for this operation.", code=RetCode.OPERATING_ERROR)
 
     keywords = req.get("keywords", "")
 
@@ -305,12 +308,12 @@ def get_filter():
 
 @manager.route("/infos", methods=["POST"])  # noqa: F821
 @login_required
-def docinfos():
+async def doc_infos():
-    req = request.json
+    req = await request_json()
     doc_ids = req["doc_ids"]
     for doc_id in doc_ids:
         if not DocumentService.accessible(doc_id, current_user.id):
-            return get_json_result(data=False, message="No authorization.", code=settings.RetCode.AUTHENTICATION_ERROR)
+            return get_json_result(data=False, message="No authorization.", code=RetCode.AUTHENTICATION_ERROR)
     docs = DocumentService.get_by_ids(doc_ids)
     return get_json_result(data=list(docs.dicts()))
 
@@ -320,7 +323,7 @@ def docinfos():
 def thumbnails():
     doc_ids = request.args.getlist("doc_ids")
     if not doc_ids:
-        return get_json_result(data=False, message='Lack of "Document ID"', code=settings.RetCode.ARGUMENT_ERROR)
+        return get_json_result(data=False, message='Lack of "Document ID"', code=RetCode.ARGUMENT_ERROR)
 
     try:
         docs = DocumentService.get_thumbnails(doc_ids)
@@ -337,13 +340,13 @@ def thumbnails():
 @manager.route("/change_status", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("doc_ids", "status")
-def change_status():
+async def change_status():
-    req = request.get_json()
+    req = await request.get_json()
     doc_ids = req.get("doc_ids", [])
     status = str(req.get("status", ""))
 
     if status not in ["0", "1"]:
-        return get_json_result(data=False, message='"Status" must be either 0 or 1!', code=settings.RetCode.ARGUMENT_ERROR)
+        return get_json_result(data=False, message='"Status" must be either 0 or 1!', code=RetCode.ARGUMENT_ERROR)
 
     result = {}
     for doc_id in doc_ids:
@@ -377,58 +380,20 @@ def change_status():
 @manager.route("/rm", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("doc_id")
-def rm():
+async def rm():
-    req = request.json
+    req = await request_json()
     doc_ids = req["doc_id"]
     if isinstance(doc_ids, str):
         doc_ids = [doc_ids]
 
     for doc_id in doc_ids:
         if not DocumentService.accessible4deletion(doc_id, current_user.id):
-            return get_json_result(data=False, message="No authorization.", code=settings.RetCode.AUTHENTICATION_ERROR)
+            return get_json_result(data=False, message="No authorization.", code=RetCode.AUTHENTICATION_ERROR)
 
-    root_folder = FileService.get_root_folder(current_user.id)
+    errors = FileService.delete_docs(doc_ids, current_user.id)
-    pf_id = root_folder["id"]
-    FileService.init_knowledgebase_docs(pf_id, current_user.id)
-    errors = ""
-    kb_table_num_map = {}
-    for doc_id in doc_ids:
-        try:
-            e, doc = DocumentService.get_by_id(doc_id)
-            if not e:
-                return get_data_error_result(message="Document not found!")
-            tenant_id = DocumentService.get_tenant_id(doc_id)
-            if not tenant_id:
-                return get_data_error_result(message="Tenant not found!")
-
-            b, n = File2DocumentService.get_storage_address(doc_id=doc_id)
-
-            TaskService.filter_delete([Task.doc_id == doc_id])
-            if not DocumentService.remove_document(doc, tenant_id):
-                return get_data_error_result(message="Database error (Document removal)!")
-
-            f2d = File2DocumentService.get_by_document_id(doc_id)
-            deleted_file_count = 0
-            if f2d:
-                deleted_file_count = FileService.filter_delete([File.source_type == FileSource.KNOWLEDGEBASE, File.id == f2d[0].file_id])
-            File2DocumentService.delete_by_document_id(doc_id)
-            if deleted_file_count > 0:
-                STORAGE_IMPL.rm(b, n)
-
-            doc_parser = doc.parser_id
-            if doc_parser == ParserType.TABLE:
-                kb_id = doc.kb_id
-                if kb_id not in kb_table_num_map:
-                    counts = DocumentService.count_by_kb_id(kb_id=kb_id, keywords="", run_status=[TaskStatus.DONE], types=[])
-                    kb_table_num_map[kb_id] = counts
-                kb_table_num_map[kb_id] -= 1
-                if kb_table_num_map[kb_id] <= 0:
-                    KnowledgebaseService.delete_field_map(kb_id)
-        except Exception as e:
-            errors += str(e)
 
     if errors:
-        return get_json_result(data=False, message=errors, code=settings.RetCode.SERVER_ERROR)
+        return get_json_result(data=False, message=errors, code=RetCode.SERVER_ERROR)
 
     return get_json_result(data=True)
 
@@ -436,11 +401,11 @@ def rm():
 @manager.route("/run", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("doc_ids", "run")
-def run():
+async def run():
-    req = request.json
+    req = await request_json()
     for doc_id in req["doc_ids"]:
         if not DocumentService.accessible(doc_id, current_user.id):
-            return get_json_result(data=False, message="No authorization.", code=settings.RetCode.AUTHENTICATION_ERROR)
+            return get_json_result(data=False, message="No authorization.", code=RetCode.AUTHENTICATION_ERROR)
     try:
         kb_table_num_map = {}
         for id in req["doc_ids"]:
@@ -473,23 +438,7 @@ def run():
 
             if str(req["run"]) == TaskStatus.RUNNING.value:
                 doc = doc.to_dict()
-                doc["tenant_id"] = tenant_id
+                DocumentService.run(tenant_id, doc, kb_table_num_map)
-
-                doc_parser = doc.get("parser_id", ParserType.NAIVE)
-                if doc_parser == ParserType.TABLE:
-                    kb_id = doc.get("kb_id")
-                    if not kb_id:
-                        continue
-                    if kb_id not in kb_table_num_map:
-                        count = DocumentService.count_by_kb_id(kb_id=kb_id, keywords="", run_status=[TaskStatus.DONE], types=[])
-                        kb_table_num_map[kb_id] = count
-                        if kb_table_num_map[kb_id] <= 0:
-                            KnowledgebaseService.delete_field_map(kb_id)
-                if doc.get("pipeline_id", ""):
-                    queue_dataflow(tenant_id, flow_id=doc["pipeline_id"], task_id=get_uuid(), doc_id=id)
-                else:
-                    bucket, name = File2DocumentService.get_storage_address(doc_id=doc["id"])
-                    queue_tasks(doc, bucket, name, 0)
 
         return get_json_result(data=True)
     except Exception as e:
@@ -499,18 +448,18 @@ def run():
 @manager.route("/rename", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("doc_id", "name")
-def rename():
+async def rename():
-    req = request.json
+    req = await request_json()
     if not DocumentService.accessible(req["doc_id"], current_user.id):
-        return get_json_result(data=False, message="No authorization.", code=settings.RetCode.AUTHENTICATION_ERROR)
+        return get_json_result(data=False, message="No authorization.", code=RetCode.AUTHENTICATION_ERROR)
     try:
         e, doc = DocumentService.get_by_id(req["doc_id"])
         if not e:
             return get_data_error_result(message="Document not found!")
         if pathlib.Path(req["name"].lower()).suffix != pathlib.Path(doc.name.lower()).suffix:
-            return get_json_result(data=False, message="The extension of file can't be changed", code=settings.RetCode.ARGUMENT_ERROR)
+            return get_json_result(data=False, message="The extension of file can't be changed", code=RetCode.ARGUMENT_ERROR)
         if len(req["name"].encode("utf-8")) > FILE_NAME_LEN_LIMIT:
-            return get_json_result(data=False, message=f"File name must be {FILE_NAME_LEN_LIMIT} bytes or less.", code=settings.RetCode.ARGUMENT_ERROR)
+            return get_json_result(data=False, message=f"File name must be {FILE_NAME_LEN_LIMIT} bytes or less.", code=RetCode.ARGUMENT_ERROR)
 
         for d in DocumentService.query(name=req["name"], kb_id=doc.kb_id):
             if d.name == req["name"]:
@@ -524,6 +473,21 @@ def rename():
             e, file = FileService.get_by_id(informs[0].file_id)
             FileService.update_by_id(file.id, {"name": req["name"]})
 
+        tenant_id = DocumentService.get_tenant_id(req["doc_id"])
+        title_tks = rag_tokenizer.tokenize(req["name"])
+        es_body = {
+            "docnm_kwd": req["name"],
+            "title_tks": title_tks,
+            "title_sm_tks": rag_tokenizer.fine_grained_tokenize(title_tks),
+        }
+        if settings.docStoreConn.indexExist(search.index_name(tenant_id), doc.kb_id):
+            settings.docStoreConn.update(
+                {"doc_id": req["doc_id"]},
+                es_body,
+                search.index_name(tenant_id),
+                doc.kb_id,
+            )
+
         return get_json_result(data=True)
     except Exception as e:
         return server_error_response(e)
@@ -531,19 +495,20 @@ def rename():
 
 @manager.route("/get/<doc_id>", methods=["GET"])  # noqa: F821
 # @login_required
-def get(doc_id):
+async def get(doc_id):
     try:
         e, doc = DocumentService.get_by_id(doc_id)
         if not e:
             return get_data_error_result(message="Document not found!")
 
         b, n = File2DocumentService.get_storage_address(doc_id=doc_id)
-        response = flask.make_response(STORAGE_IMPL.get(b, n))
+        response = await make_response(settings.STORAGE_IMPL.get(b, n))
 
         ext = re.search(r"\.([^.]+)$", doc.name.lower())
         ext = ext.group(1) if ext else None
         if ext:
             if doc.type == FileType.VISUAL.value:
+
                 content_type = CONTENT_TYPE_MAP.get(ext, f"image/{ext}")
             else:
                 content_type = CONTENT_TYPE_MAP.get(ext, f"application/{ext}")
@@ -553,14 +518,30 @@ def get(doc_id):
         return server_error_response(e)
 
 
+@manager.route("/download/<attachment_id>", methods=["GET"])  # noqa: F821
+@login_required
+async def download_attachment(attachment_id):
+    try:
+        ext = request.args.get("ext", "markdown")
+        data = settings.STORAGE_IMPL.get(current_user.id, attachment_id)
+        # data = settings.STORAGE_IMPL.get("eb500d50bb0411f0907561d2782adda5", attachment_id)
+        response = await make_response(data)
+        response.headers.set("Content-Type", CONTENT_TYPE_MAP.get(ext, f"application/{ext}"))
+
+        return response
+
+    except Exception as e:
+        return server_error_response(e)
+
+
 @manager.route("/change_parser", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("doc_id")
-def change_parser():
+async def change_parser():
 
-    req = request.json
+    req = await request_json()
     if not DocumentService.accessible(req["doc_id"], current_user.id):
-        return get_json_result(data=False, message="No authorization.", code=settings.RetCode.AUTHENTICATION_ERROR)
+        return get_json_result(data=False, message="No authorization.", code=RetCode.AUTHENTICATION_ERROR)
 
     e, doc = DocumentService.get_by_id(req["doc_id"])
     if not e:
@@ -580,6 +561,7 @@ def change_parser():
                 return get_data_error_result(message="Tenant not found!")
             if settings.docStoreConn.indexExist(search.index_name(tenant_id), doc.kb_id):
                 settings.docStoreConn.delete({"doc_id": doc.id}, search.index_name(tenant_id), doc.kb_id)
+        return None
 
     try:
         if "pipeline_id" in req and req["pipeline_id"] != "":
@@ -608,13 +590,13 @@ def change_parser():
 
 @manager.route("/image/<image_id>", methods=["GET"])  # noqa: F821
 # @login_required
-def get_image(image_id):
+async def get_image(image_id):
     try:
         arr = image_id.split("-")
         if len(arr) != 2:
             return get_data_error_result(message="Image not found.")
         bkt, nm = image_id.split("-")
-        response = flask.make_response(STORAGE_IMPL.get(bkt, nm))
+        response = await make_response(settings.STORAGE_IMPL.get(bkt, nm))
         response.headers.set("Content-Type", "image/JPEG")
         return response
     except Exception as e:
@@ -624,27 +606,28 @@ def get_image(image_id):
 @manager.route("/upload_and_parse", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("conversation_id")
-def upload_and_parse():
+async def upload_and_parse():
-    if "file" not in request.files:
+    files = await request.file
-        return get_json_result(data=False, message="No file part!", code=settings.RetCode.ARGUMENT_ERROR)
+    if "file" not in files:
+        return get_json_result(data=False, message="No file part!", code=RetCode.ARGUMENT_ERROR)
 
-    file_objs = request.files.getlist("file")
+    file_objs = files.getlist("file")
     for file_obj in file_objs:
         if file_obj.filename == "":
-            return get_json_result(data=False, message="No file selected!", code=settings.RetCode.ARGUMENT_ERROR)
+            return get_json_result(data=False, message="No file selected!", code=RetCode.ARGUMENT_ERROR)
-
-    doc_ids = doc_upload_and_parse(request.form.get("conversation_id"), file_objs, current_user.id)
 
+    form = await request.form
+    doc_ids = doc_upload_and_parse(form.get("conversation_id"), file_objs, current_user.id)
     return get_json_result(data=doc_ids)
 
 
 @manager.route("/parse", methods=["POST"])  # noqa: F821
 @login_required
-def parse():
+async def parse():
-    url = request.json.get("url") if request.json else ""
+    url = await request.json.get("url") if await request.json else ""
     if url:
         if not is_valid_url(url):
-            return get_json_result(data=False, message="The URL format is invalid", code=settings.RetCode.ARGUMENT_ERROR)
+            return get_json_result(data=False, message="The URL format is invalid", code=RetCode.ARGUMENT_ERROR)
         download_path = os.path.join(get_project_base_directory(), "logs/downloads")
         os.makedirs(download_path, exist_ok=True)
         from seleniumwire.webdriver import Chrome, ChromeOptions
@@ -677,15 +660,16 @@ def parse():
 
         r = re.search(r"filename=\"([^\"]+)\"", str(res_headers))
         if not r or not r.group(1):
-            return get_json_result(data=False, message="Can't not identify downloaded file", code=settings.RetCode.ARGUMENT_ERROR)
+            return get_json_result(data=False, message="Can't not identify downloaded file", code=RetCode.ARGUMENT_ERROR)
         f = File(r.group(1), os.path.join(download_path, r.group(1)))
         txt = FileService.parse_docs([f], current_user.id)
         return get_json_result(data=txt)
 
-    if "file" not in request.files:
+    files = await request.files
-        return get_json_result(data=False, message="No file part!", code=settings.RetCode.ARGUMENT_ERROR)
+    if "file" not in files:
+        return get_json_result(data=False, message="No file part!", code=RetCode.ARGUMENT_ERROR)
 
-    file_objs = request.files.getlist("file")
+    file_objs = files.getlist("file")
     txt = FileService.parse_docs(file_objs, current_user.id)
 
     return get_json_result(data=txt)
@@ -694,21 +678,21 @@ def parse():
 @manager.route("/set_meta", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("doc_id", "meta")
-def set_meta():
+async def set_meta():
-    req = request.json
+    req = await request_json()
     if not DocumentService.accessible(req["doc_id"], current_user.id):
-        return get_json_result(data=False, message="No authorization.", code=settings.RetCode.AUTHENTICATION_ERROR)
+        return get_json_result(data=False, message="No authorization.", code=RetCode.AUTHENTICATION_ERROR)
     try:
         meta = json.loads(req["meta"])
         if not isinstance(meta, dict):
-            return get_json_result(data=False, message="Only dictionary type supported.", code=settings.RetCode.ARGUMENT_ERROR)
+            return get_json_result(data=False, message="Only dictionary type supported.", code=RetCode.ARGUMENT_ERROR)
         for k, v in meta.items():
             if not isinstance(v, str) and not isinstance(v, int) and not isinstance(v, float):
-                return get_json_result(data=False, message=f"The type is not supported: {v}", code=settings.RetCode.ARGUMENT_ERROR)
+                return get_json_result(data=False, message=f"The type is not supported: {v}", code=RetCode.ARGUMENT_ERROR)
     except Exception as e:
-        return get_json_result(data=False, message=f"Json syntax error: {e}", code=settings.RetCode.ARGUMENT_ERROR)
+        return get_json_result(data=False, message=f"Json syntax error: {e}", code=RetCode.ARGUMENT_ERROR)
     if not isinstance(meta, dict):
-        return get_json_result(data=False, message='Meta data should be in Json map format, like {"key": "value"}', code=settings.RetCode.ARGUMENT_ERROR)
+        return get_json_result(data=False, message='Meta data should be in Json map format, like {"key": "value"}', code=RetCode.ARGUMENT_ERROR)
 
     try:
         e, doc = DocumentService.get_by_id(req["doc_id"])

api/apps/file2document_app.py

@@ -19,22 +19,22 @@ from pathlib import Path
 from api.db.services.file2document_service import File2DocumentService
 from api.db.services.file_service import FileService
 
-from flask import request
+from quart import request
-from flask_login import login_required, current_user
+from api.apps import login_required, current_user
 from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.utils.api_utils import server_error_response, get_data_error_result, validate_request
-from api.utils import get_uuid
+from common.misc_utils import get_uuid
+from common.constants import RetCode
 from api.db import FileType
 from api.db.services.document_service import DocumentService
-from api import settings
 from api.utils.api_utils import get_json_result
 
 
 @manager.route('/convert', methods=['POST'])  # noqa: F821
 @login_required
 @validate_request("file_ids", "kb_ids")
-def convert():
+async def convert():
-    req = request.json
+    req = await request.json
     kb_ids = req["kb_ids"]
     file_ids = req["file_ids"]
     file2documents = []
@@ -103,12 +103,12 @@ def convert():
 @manager.route('/rm', methods=['POST'])  # noqa: F821
 @login_required
 @validate_request("file_ids")
-def rm():
+async def rm():
-    req = request.json
+    req = await request.json
     file_ids = req["file_ids"]
     if not file_ids:
         return get_json_result(
-            data=False, message='Lack of "Files ID"', code=settings.RetCode.ARGUMENT_ERROR)
+            data=False, message='Lack of "Files ID"', code=RetCode.ARGUMENT_ERROR)
     try:
         for file_id in file_ids:
             informs = File2DocumentService.get_by_file_id(file_id)