Fix: Unified terminology to "Pipeline" and optimized related component logic. #9869 (#10394)

### What problem does this PR solve?

Fix: Unified terminology to "Pipeline" and optimized related component
logic. #9869

- Added logic to clear pipeline_id when parseType changes in the chunk
method dialog.
- Fixed an issue in the Tooltip form component that prevented clicks
from triggering saves.
### Type of change

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

.github/workflows/release.yml

@@ -16,7 +16,7 @@ concurrency:
 
 jobs:
   release:
-    runs-on: [ "self-hosted", "ragflow-test" ]
+    runs-on: [ "self-hosted", "overseas" ]
     steps:
       - name: Ensure workspace ownership
         run: echo "chown -R $USER $GITHUB_WORKSPACE" && sudo chown -R $USER $GITHUB_WORKSPACE
@@ -25,7 +25,7 @@ jobs:
       - name: Check out code
         uses: actions/checkout@v4
         with:
-          token: ${{ secrets.GITHUB_TOKEN }}  # Use the secret as an environment variable
+          token: ${{ secrets.MY_GITHUB_TOKEN }}  # Use the secret as an environment variable
           fetch-depth: 0
           fetch-tags: true
 
@@ -69,28 +69,54 @@ jobs:
         # https://github.com/actions/upload-release-asset has been replaced by https://github.com/softprops/action-gh-release
         uses: softprops/action-gh-release@v2
         with:
-          token: ${{ secrets.GITHUB_TOKEN }}  # Use the secret as an environment variable
+          token: ${{ secrets.MY_GITHUB_TOKEN }}  # Use the secret as an environment variable
           prerelease: ${{ env.PRERELEASE }}
           tag_name: ${{ env.RELEASE_TAG }}
           # The body field does not support environment variable substitution directly.
           body_path: release_body.md
 
-      - name: Build and push ragflow-sdk
+      # https://github.com/marketplace/actions/docker-login
+      - 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 && uv build
-          twine upload sdk/python/dist/* -u __token__ -p ${{ secrets.PYPI_API_TOKEN }}
+          cd sdk/python && \
+          uv build
 
-      - name: Build and push ragflow-cli
+      - name: Publish package distributions to PyPI
         if: startsWith(github.ref, 'refs/tags/v')
-        run: |
-          cd admin/client && uv build
-          twine upload admin/client/dist/* -u __token__ -p ${{ secrets.PYPI_API_TOKEN }}
-
-      - name: Build and push image
-        run: |
-          echo ${{ secrets.DOCKERHUB_TOKEN }} | sudo docker login --username infiniflow --password-stdin
-          sudo docker build --build-arg NEED_MIRROR=1 -t infiniflow/ragflow:${RELEASE_TAG} -f Dockerfile .
-          sudo docker tag infiniflow/ragflow:${RELEASE_TAG} infiniflow/ragflow:latest
-          sudo docker push infiniflow/ragflow:${RELEASE_TAG}
-          sudo docker push infiniflow/ragflow:latest
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: sdk/python/dist/
+          password: ${{ secrets.PYPI_API_TOKEN }}
+          verbose: true

.github/workflows/tests.yml

@@ -10,7 +10,7 @@ on:
       - '*.md'
       - '*.mdx'
   pull_request:
-    types: [ labeled, synchronize, reopened ]
+    types: [ opened, synchronize, reopened, labeled ]
     paths-ignore:
       - 'docs/**'
       - '*.md'
@@ -29,15 +29,17 @@ jobs:
     # 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') }}
-    runs-on: [ "self-hosted", "ragflow-test" ]
+    runs-on: [ "self-hosted", "debug" ]
     steps:
       # https://github.com/hmarr/debug-action
       #- uses: hmarr/debug-action@v2
 
-      - name: Ensure workspace ownership
+      - name: Show who triggered this workflow
         run: |
           echo "Workflow triggered by ${{ github.event_name }}"
-          echo "chown -R $USER $GITHUB_WORKSPACE" && sudo chown -R $USER $GITHUB_WORKSPACE
+
+      - name: Ensure workspace ownership
+        run: echo "chown -R $USER $GITHUB_WORKSPACE" && sudo chown -R $USER $GITHUB_WORKSPACE
 
       # https://github.com/actions/checkout/issues/1781
       - name: Check out code
@@ -46,44 +48,6 @@ jobs:
           fetch-depth: 0
           fetch-tags: true
 
-      - name: Check workflow duplication
-        if: ${{ !cancelled() && !failure() && (github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'ci')) }}
-        run: |
-          if [[ "$GITHUB_EVENT_NAME" != "pull_request" && "$GITHUB_EVENT_NAME" != "schedule" ]]; then
-            HEAD=$(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
-              PR_SHA_FP=${RUNNER_WORKSPACE_PREFIX}/artifacts/${GITHUB_REPOSITORY}/PR_${PR_NUMBER}
-              if [[ -f "${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
-                  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
-                    sleep 5
-                  done
-                  exit 1
-                fi
-              fi
-            fi
-          else
-            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
-            PR_SHA=$(git rev-parse HEAD^{tree})
-            echo "PR #${PR_NUMBER} workspace content hash: ${PR_SHA}"
-            mkdir -p ${RUNNER_WORKSPACE_PREFIX}/artifacts/${GITHUB_REPOSITORY}
-            echo "${PR_SHA} ${GITHUB_RUN_ID}" > ${PR_SHA_FP}
-          fi
-
       # https://github.com/astral-sh/ruff-action
       - name: Static check with Ruff
         uses: astral-sh/ruff-action@v3
@@ -91,140 +55,122 @@ jobs:
           version: ">=0.11.x"
           args: "check"
 
-      - name: Build ragflow:nightly
+      - name: Build ragflow:nightly-slim
         run: |
           RUNNER_WORKSPACE_PREFIX=${RUNNER_WORKSPACE_PREFIX:-$HOME}
-          RAGFLOW_IMAGE=infiniflow/ragflow:${GITHUB_RUN_ID}
-          echo "RAGFLOW_IMAGE=${RAGFLOW_IMAGE}" >> $GITHUB_ENV
           sudo docker pull ubuntu:22.04
-          sudo DOCKER_BUILDKIT=1 docker build --build-arg NEED_MIRROR=1 -f Dockerfile -t ${RAGFLOW_IMAGE} .
-          if [[ "$GITHUB_EVENT_NAME" == "schedule" ]]; then
-            export HTTP_API_TEST_LEVEL=p3
-          else
-            export HTTP_API_TEST_LEVEL=p2
-          fi
-          echo "HTTP_API_TEST_LEVEL=${HTTP_API_TEST_LEVEL}" >> $GITHUB_ENV
-          echo "RAGFLOW_CONTAINER=${GITHUB_RUN_ID}-ragflow-cpu-1" >> $GITHUB_ENV
+          sudo docker build --progress=plain --build-arg LIGHTEN=1 --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
+
+      - name: Build ragflow:nightly
+        run: |
+          sudo docker build --progress=plain --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly .
+
+      - name: Start ragflow:nightly-slim
+        run: |
+          sudo docker compose -f docker/docker-compose.yml down --volumes --remove-orphans
+          echo -e "\nRAGFLOW_IMAGE=infiniflow/ragflow:nightly-slim" >> docker/.env
+          sudo docker compose -f docker/docker-compose.yml up -d
+
+      - name: Stop ragflow:nightly-slim
+        if: always()  # always run this step even if previous steps failed
+        run: |
+          sudo docker compose -f docker/docker-compose.yml down -v
 
       - name: Start ragflow:nightly
         run: |
-          # Determine runner number (default to 1 if not found)
-          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
+          echo -e "\nRAGFLOW_IMAGE=infiniflow/ragflow:nightly" >> docker/.env
+          sudo docker compose -f docker/docker-compose.yml up -d
 
       - 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=""
-          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
+          export HOST_ADDRESS=http://host.docker.internal:9380
+          until sudo docker exec ragflow-server curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
             echo "Waiting for service to be available..."
             sleep 5
           done
-          source .venv/bin/activate && pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_sdk_api
+          if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then
+            export HTTP_API_TEST_LEVEL=p3
+          else
+            export HTTP_API_TEST_LEVEL=p2
+          fi
+          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && uv pip install sdk/python && uv run --only-group test --no-default-groups pytest -s --tb=short --level=${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=""
-          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
+          export HOST_ADDRESS=http://host.docker.internal:9380
+          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
-          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
+          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
           
       - 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=""
-          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
+          export HOST_ADDRESS=http://host.docker.internal:9380
+          until sudo docker exec ragflow-server curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
             echo "Waiting for service to be available..."
             sleep 5
           done
-          source .venv/bin/activate && pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_http_api
+          if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then
+            export HTTP_API_TEST_LEVEL=p3
+          else
+            export HTTP_API_TEST_LEVEL=p2
+          fi
+          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && uv run --only-group test --no-default-groups pytest -s --tb=short --level=${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 -p ${GITHUB_RUN_ID} down -v
+          sudo docker compose -f docker/docker-compose.yml down -v
 
       - name: Start ragflow:nightly
         run: |
-          sed -i '1i DOC_ENGINE=infinity' docker/.env
-          sudo docker compose -f docker/docker-compose.yml -p ${GITHUB_RUN_ID} up -d
+          sudo DOC_ENGINE=infinity docker compose -f docker/docker-compose.yml 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=""
-          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
+          export HOST_ADDRESS=http://host.docker.internal:9380
+          until sudo docker exec ragflow-server curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
             echo "Waiting for service to be available..."
             sleep 5
           done
-          source .venv/bin/activate && DOC_ENGINE=infinity pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_sdk_api
+          if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then
+            export HTTP_API_TEST_LEVEL=p3
+          else
+            export HTTP_API_TEST_LEVEL=p2
+          fi
+          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && uv pip install sdk/python && DOC_ENGINE=infinity uv run --only-group test --no-default-groups pytest -s --tb=short --level=${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=""
-          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
+          export HOST_ADDRESS=http://host.docker.internal:9380
+          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
-          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
+          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
 
       - 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=""
-          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
+          export HOST_ADDRESS=http://host.docker.internal:9380
+          until sudo docker exec ragflow-server curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
             echo "Waiting for service to be available..."
             sleep 5
           done
-          source .venv/bin/activate && DOC_ENGINE=infinity pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_http_api
+          if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then
+            export HTTP_API_TEST_LEVEL=p3
+          else
+            export HTTP_API_TEST_LEVEL=p2
+          fi
+          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && DOC_ENGINE=infinity uv run --only-group test --no-default-groups pytest -s --tb=short --level=${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 docker compose -f docker/docker-compose.yml -p ${GITHUB_RUN_ID} down -v
-          sudo docker rmi -f ${RAGFLOW_IMAGE}
+          sudo DOC_ENGINE=infinity docker compose -f docker/docker-compose.yml down -v

.gitignore

@@ -149,7 +149,7 @@ out
 # Nuxt.js build / generate output
 .nuxt
 dist
-ragflow_cli.egg-info
+
 # Gatsby files
 .cache/
 # Comment in the public line in if your project uses Gatsby and not Next.js

Dockerfile

@@ -4,6 +4,8 @@ USER root
 SHELL ["/bin/bash", "-c"]
 
 ARG NEED_MIRROR=0
+ARG LIGHTEN=0
+ENV LIGHTEN=${LIGHTEN}
 
 WORKDIR /ragflow
 
@@ -15,6 +17,13 @@ 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.
@@ -54,11 +63,11 @@ RUN --mount=type=cache,id=ragflow_apt,target=/var/cache/apt,sharing=locked \
     apt install -y ghostscript
 
 RUN if [ "$NEED_MIRROR" == "1" ]; then \
-        pip3 config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple && \
-        pip3 config set global.trusted-host pypi.tuna.tsinghua.edu.cn; \
+        pip3 config set global.index-url https://mirrors.aliyun.com/pypi/simple && \
+        pip3 config set global.trusted-host mirrors.aliyun.com; \
         mkdir -p /etc/uv && \
         echo "[[index]]" > /etc/uv/uv.toml && \
-        echo 'url = "https://pypi.tuna.tsinghua.edu.cn/simple"' >> /etc/uv/uv.toml && \
+        echo 'url = "https://mirrors.aliyun.com/pypi/simple"' >> /etc/uv/uv.toml && \
         echo "default = true" >> /etc/uv/uv.toml; \
     fi; \
     pipx install uv
@@ -142,11 +151,15 @@ COPY pyproject.toml uv.lock ./
 # uv records index url into uv.lock but doesn't failover among multiple indexes
 RUN --mount=type=cache,id=ragflow_uv,target=/root/.cache/uv,sharing=locked \
     if [ "$NEED_MIRROR" == "1" ]; then \
-        sed -i 's|pypi.org|pypi.tuna.tsinghua.edu.cn|g' uv.lock; \
+        sed -i 's|pypi.org|mirrors.aliyun.com/pypi|g' uv.lock; \
     else \
-        sed -i 's|pypi.tuna.tsinghua.edu.cn|pypi.org|g' uv.lock; \
+        sed -i 's|mirrors.aliyun.com/pypi|pypi.org|g' uv.lock; \
     fi; \
-    uv sync --python 3.10 --frozen
+    if [ "$LIGHTEN" == "1" ]; then \
+        uv sync --python 3.10 --frozen; \
+    else \
+        uv sync --python 3.10 --frozen --all-extras; \
+    fi
 
 COPY web web
 COPY docs docs
@@ -156,7 +169,11 @@ RUN --mount=type=cache,id=ragflow_npm,target=/root/.npm,sharing=locked \
 COPY .git /ragflow/.git
 
 RUN version_info=$(git describe --tags --match=v* --first-parent --always); \
-    version_info="$version_info"; \
+    if [ "$LIGHTEN" == "1" ]; then \
+        version_info="$version_info slim"; \
+    else \
+        version_info="$version_info full"; \
+    fi; \
     echo "RAGFlow version: $version_info"; \
     echo $version_info > /ragflow/VERSION
 
@@ -174,7 +191,6 @@ ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
 ENV PYTHONPATH=/ragflow/
 
 COPY web web
-COPY admin admin
 COPY api api
 COPY conf conf
 COPY deepdoc deepdoc
@@ -185,7 +201,6 @@ 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

@@ -1,14 +0,0 @@
-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

@@ -1,6 +1,6 @@
 <div align="center">
 <a href="https://demo.ragflow.io/">
-<img src="web/src/assets/logo-with-text.svg" width="520" alt="ragflow logo">
+<img src="web/src/assets/logo-with-text.png" width="520" alt="ragflow logo">
 </a>
 </div>
 
@@ -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:v0.21.1">
+        <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:v0.20.5">
     </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">
@@ -84,9 +84,8 @@ Try our demo at [https://demo.ragflow.io](https://demo.ragflow.io).
 
 ## 🔥 Latest Updates
 
-- 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.
+- 2025-08-04 Supports new models, including Kimi K2 and Grok 4.
 - 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.
@@ -136,7 +135,7 @@ releases! 🌟
 ## 🔎 System Architecture
 
 <div align="center" style="margin-top:20px;margin-bottom:20px;">
-<img src="https://github.com/user-attachments/assets/31b0dd6f-ca4f-445a-9457-70cb44a381b2" width="1000"/>
+<img src="https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485" width="1000"/>
 </div>
 
 ## 🎬 Get Started
@@ -188,7 +187,7 @@ releases! 🌟
 > 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 `v0.21.1-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.21.1-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server.
+   > The command below downloads the `v0.20.5-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.20.5-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:v0.20.5` for the full edition `v0.20.5`.
 
    ```bash
    $ cd ragflow/docker
@@ -196,23 +195,20 @@ releases! 🌟
    $ docker compose -f docker-compose.yml up -d
 
    # To use GPU to accelerate embedding and DeepDoc tasks:
-   # sed -i '1i DEVICE=gpu' .env
-   # docker compose -f docker-compose.yml up -d
+   # docker compose -f docker-compose-gpu.yml up -d
    ```
 
    | 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           |
-   | nightly           | &approx;2       | ❌                    | _Unstable_ nightly build |
-
-
-   > Note: Starting with `v0.22.0`, we ship only the slim edition and no longer append the **-slim** suffix to the image tag.
+   | v0.20.5           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.5-slim      | &approx;2       | ❌                   | Stable release            |
+   | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
+   | nightly-slim      | &approx;2       | ❌                   | _Unstable_ nightly build  |
 
 4. Check the server status after having the server up and running:
 
    ```bash
-   $ docker logs -f docker-ragflow-cpu-1
+   $ docker logs -f ragflow-server
    ```
 
    _The following output confirms a successful launch of the system:_
@@ -290,6 +286,16 @@ RAGFlow uses Elasticsearch by default for storing full text and vectors. To swit
 
 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/
@@ -309,7 +315,7 @@ 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 # install RAGFlow dependent python modules
+   uv sync --python 3.10 --all-extras # install RAGFlow dependent python modules
    uv run download_deps.py
    pre-commit install
    ```
@@ -335,13 +341,11 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
 5. If your operating system does not have jemalloc, please install it as follows:
 
    ```bash
-   # Ubuntu
+   # ubuntu
    sudo apt-get install libjemalloc-dev
-   # CentOS
+   # centos
    sudo yum install jemalloc
-   # OpenSUSE
-   sudo zypper install jemalloc
-   # macOS
+   # mac
    sudo brew install jemalloc
    ```
 

README_id.md

@@ -1,6 +1,6 @@
 <div align="center">
 <a href="https://demo.ragflow.io/">
-<img src="web/src/assets/logo-with-text.svg" width="520" alt="Logo ragflow">
+<img src="web/src/assets/logo-with-text.png" width="520" alt="Logo ragflow">
 </a>
 </div>
 
@@ -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:v0.21.1">
+        <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:v0.20.5">
     </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">
@@ -80,9 +80,8 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
 
 ## 🔥 Pembaruan Terbaru
 
-- 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.
+- 2025-08-04 Mendukung model baru, termasuk Kimi K2 dan Grok 4.
 - 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.
@@ -130,7 +129,7 @@ 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/user-attachments/assets/31b0dd6f-ca4f-445a-9457-70cb44a381b2" width="1000"/>
+<img src="https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485" width="1000"/>
 </div>
 
 ## 🎬 Mulai
@@ -182,30 +181,28 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
 > 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 v0.21.1 dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.21.1, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server.
+> Perintah di bawah ini mengunduh edisi v0.20.5-slim dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.20.5-slim, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server. Misalnya, atur RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.5 untuk edisi lengkap v0.20.5.
 
-   ```bash
-   $ cd ragflow/docker
-   # Use CPU for embedding and DeepDoc tasks:
-   $ docker compose -f docker-compose.yml up -d
+```bash
+$ 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:
-   # sed -i '1i DEVICE=gpu' .env
-   # docker compose -f docker-compose.yml up -d
-   ```
+# To use GPU to accelerate embedding and DeepDoc tasks:
+# docker compose -f docker-compose-gpu.yml up -d
+```
 
 | 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           |
-| nightly           | &approx;2       | ❌                    | _Unstable_ nightly build |
-
-> Catatan: Mulai dari `v0.22.0`, kami hanya menyediakan edisi slim dan tidak lagi menambahkan akhiran **-slim** pada tag image.
+| v0.20.5           | &approx;9       | :heavy_check_mark:    | Stable release           |
+| v0.20.5-slim      | &approx;2       | ❌                    | Stable release           |
+| nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
+| nightly-slim      | &approx;2       | ❌                    | _Unstable_ nightly build |
 
 1. Periksa status server setelah server aktif dan berjalan:
 
    ```bash
-   $ docker logs -f docker-ragflow-cpu-1
+   $ docker logs -f ragflow-server
    ```
 
    _Output berikut menandakan bahwa sistem berhasil diluncurkan:_
@@ -256,6 +253,16 @@ Pembaruan konfigurasi ini memerlukan reboot semua kontainer agar efektif:
 
 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/
@@ -275,7 +282,7 @@ 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 # install RAGFlow dependent python modules
+   uv sync --python 3.10 --all-extras # install RAGFlow dependent python modules
    uv run download_deps.py
    pre-commit install
    ```

README_ja.md

@@ -1,6 +1,6 @@
 <div align="center">
 <a href="https://demo.ragflow.io/">
-<img src="web/src/assets/logo-with-text.svg" width="350" alt="ragflow logo">
+<img src="web/src/assets/logo-with-text.png" width="350" alt="ragflow logo">
 </a>
 </div>
 
@@ -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:v0.21.1">
+        <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:v0.20.5">
     </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">
@@ -60,9 +60,8 @@
 
 ## 🔥 最新情報
 
-- 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。
+- 2025-08-04 新モデル、キミK2およびGrok 4をサポート。
 - 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。
@@ -110,7 +109,7 @@
 ## 🔎 システム構成
 
 <div align="center" style="margin-top:20px;margin-bottom:20px;">
-<img src="https://github.com/user-attachments/assets/31b0dd6f-ca4f-445a-9457-70cb44a381b2" width="1000"/>
+<img src="https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485" width="1000"/>
 </div>
 
 ## 🎬 初期設定
@@ -161,7 +160,7 @@
 > 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 v0.21.1 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。v0.21.1 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。
+   > 以下のコマンドは、RAGFlow Docker イメージの v0.20.5-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。v0.20.5-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 v0.20.5 をダウンロードするには、RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.5 と設定します。
 
    ```bash
    $ cd ragflow/docker
@@ -169,22 +168,20 @@
    $ docker compose -f docker-compose.yml up -d
 
    # To use GPU to accelerate embedding and DeepDoc tasks:
-   # sed -i '1i DEVICE=gpu' .env
-   # docker compose -f docker-compose.yml up -d
+   # docker compose -f docker-compose-gpu.yml up -d
    ```
 
    | 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           |
-   | nightly           | &approx;2       | ❌                    | _Unstable_ nightly build |
-
-   > 注意：`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。
+   | v0.20.5           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.5-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:
 
    ```bash
-   $ docker logs -f docker-ragflow-cpu-1
+   $ docker logs -f ragflow-server
    ```
 
    _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:_
@@ -251,6 +248,16 @@ RAGFlow はデフォルトで Elasticsearch を使用して全文とベクトル
 
 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/
@@ -270,7 +277,7 @@ 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 # install RAGFlow dependent python modules
+   uv sync --python 3.10 --all-extras # install RAGFlow dependent python modules
    uv run download_deps.py
    pre-commit install
    ```

README_ko.md

@@ -1,6 +1,6 @@
 <div align="center">
 <a href="https://demo.ragflow.io/">
-<img src="web/src/assets/logo-with-text.svg" width="520" alt="ragflow logo">
+<img src="web/src/assets/logo-with-text.png" width="520" alt="ragflow logo">
 </a>
 </div>
 
@@ -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:v0.21.1">
+        <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:v0.20.5">
     </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">
@@ -60,9 +60,8 @@
 
 ## 🔥 업데이트
 
-- 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.
+- 2025-08-04 새로운 모델인 Kimi K2와 Grok 4를 포함하여 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.
@@ -110,7 +109,7 @@
 ## 🔎 시스템 아키텍처
 
 <div align="center" style="margin-top:20px;margin-bottom:20px;">
-<img src="https://github.com/user-attachments/assets/31b0dd6f-ca4f-445a-9457-70cb44a381b2" width="1000"/>
+<img src="https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485" width="1000"/>
 </div>
 
 ## 🎬 시작하기
@@ -161,7 +160,7 @@
 > 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 v0.21.1 버전을 다운로드합니다. 다양한 RAGFlow 버전에 대한 설명은 다음 표를 참조하십시오. v0.21.1과 다른 RAGFlow 버전을 다운로드하려면, docker/.env 파일에서 RAGFLOW_IMAGE 변수를 적절히 업데이트한 후 docker compose를 사용하여 서버를 시작하십시오.
+   > 아래 명령어는 RAGFlow Docker 이미지의 v0.20.5-slim 버전을 다운로드합니다. 다양한 RAGFlow 버전에 대한 설명은 다음 표를 참조하십시오. v0.20.5-slim과 다른 RAGFlow 버전을 다운로드하려면, docker/.env 파일에서 RAGFLOW_IMAGE 변수를 적절히 업데이트한 후 docker compose를 사용하여 서버를 시작하십시오. 예를 들어, 전체 버전인 v0.20.5을 다운로드하려면 RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.5로 설정합니다.
 
    ```bash
    $ cd ragflow/docker
@@ -169,22 +168,20 @@
    $ docker compose -f docker-compose.yml up -d
 
    # To use GPU to accelerate embedding and DeepDoc tasks:
-   # sed -i '1i DEVICE=gpu' .env
-   # docker compose -f docker-compose.yml up -d
+   # docker compose -f docker-compose-gpu.yml up -d
    ```
 
    | 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           |
-   | nightly           | &approx;2       | ❌                    | _Unstable_ nightly build |
-
-   > 참고: `v0.22.0`부터는 slim 에디션만 배포하며 이미지 태그에 **-slim** 접미사를 더 이상 붙이지 않습니다.
+   | v0.20.5           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.5-slim      | &approx;2       | ❌                    | Stable release           |
+   | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
+   | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
 
 1. 서버가 시작된 후 서버 상태를 확인하세요:
 
    ```bash
-   $ docker logs -f docker-ragflow-cpu-1
+   $ docker logs -f ragflow-server
    ```
 
    _다음 출력 결과로 시스템이 성공적으로 시작되었음을 확인합니다:_
@@ -250,6 +247,16 @@ RAGFlow 는 기본적으로 Elasticsearch 를 사용하여 전체 텍스트 및
 
 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/
@@ -269,7 +276,7 @@ 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 # install RAGFlow dependent python modules
+   uv sync --python 3.10 --all-extras # install RAGFlow dependent python modules
    uv run download_deps.py
    pre-commit install
    ```

README_pt_br.md

@@ -1,6 +1,6 @@
 <div align="center">
 <a href="https://demo.ragflow.io/">
-<img src="web/src/assets/logo-with-text.svg" width="520" alt="ragflow logo">
+<img src="web/src/assets/logo-with-text.png" width="520" alt="ragflow logo">
 </a>
 </div>
 
@@ -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:v0.21.1">
+        <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:v0.20.5">
     </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">
@@ -80,9 +80,8 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).
 
 ## 🔥 Últimas Atualizações
 
-- 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.
+- 04-08-2025 Suporta novos modelos, incluindo Kimi K2 e Grok 4.
 - 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.
@@ -130,7 +129,7 @@ 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/user-attachments/assets/31b0dd6f-ca4f-445a-9457-70cb44a381b2" width="1000"/>
+<img src="https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485" width="1000"/>
 </div>
 
 ## 🎬 Primeiros Passos
@@ -181,30 +180,28 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).
 > 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 `v0.21.1` 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 `v0.21.1`, atualize a variável `RAGFLOW_IMAGE` conforme necessário no **docker/.env** antes de usar `docker compose` para iniciar o servidor.
+    > O comando abaixo baixa a edição `v0.20.5-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 `v0.20.5-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:v0.20.5` para a edição completa `v0.20.5`.
 
-   ```bash
-   $ cd ragflow/docker
-   # Use CPU for embedding and DeepDoc tasks:
-   $ docker compose -f docker-compose.yml up -d
+    ```bash
+    $ 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:
-   # sed -i '1i DEVICE=gpu' .env
-   # docker compose -f docker-compose.yml up -d
-   ```
+    # To use GPU to accelerate embedding and DeepDoc tasks:
+    # docker compose -f docker-compose-gpu.yml up -d
+    ```
 
-    | Tag da imagem RAGFlow | Tamanho da imagem (GB) | Possui modelos de incorporação? | Estável?                    |
-    | --------------------- | ---------------------- | ------------------------------- | --------------------------- |
-    | v0.21.1               | &approx;9              | ✔️                              | Lançamento estável          |
-    | v0.21.1-slim          | &approx;2              | ❌                              | Lançamento estável          |
-    | nightly               | &approx;2              | ❌                              | Construção noturna instável |
-
-    > Observação: A partir da `v0.22.0`, distribuímos apenas a edição slim e não adicionamos mais o sufixo **-slim** às tags das imagens.
+    | Tag da imagem RAGFlow | Tamanho da imagem (GB) | Possui modelos de incorporação? | Estável?                 |
+    | --------------------- | ---------------------- | ------------------------------- | ------------------------ |
+    | v0.20.5               | ~9                     | :heavy_check_mark:              | Lançamento estável       |
+    | v0.20.5-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:
 
     ```bash
-    $ docker logs -f docker-ragflow-cpu-1
+    $ docker logs -f ragflow-server
     ```
 
     _O seguinte resultado confirma o lançamento bem-sucedido do sistema:_
@@ -274,6 +271,16 @@ O RAGFlow usa o Elasticsearch por padrão para armazenar texto completo e vetore
 
 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/
@@ -293,7 +300,7 @@ 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 # instala os módulos Python dependentes do RAGFlow
+   uv sync --python 3.10 --all-extras # instala os módulos Python dependentes do RAGFlow
    uv run download_deps.py
    pre-commit install
    ```

README_tzh.md

@@ -1,6 +1,6 @@
 <div align="center">
 <a href="https://demo.ragflow.io/">
-<img src="web/src/assets/logo-with-text.svg" width="350" alt="ragflow logo">
+<img src="web/src/assets/logo-with-text.png" width="350" alt="ragflow logo">
 </a>
 </div>
 
@@ -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:v0.21.1">
+        <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:v0.20.5">
     </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">
@@ -83,9 +83,8 @@
 
 ## 🔥 近期更新
 
-- 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。
+- 2025-08-04 支援 Kimi K2 和 Grok 4 等模型.
 - 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。
@@ -133,7 +132,7 @@
 ## 🔎 系統架構
 
 <div align="center" style="margin-top:20px;margin-bottom:20px;">
-<img src="https://github.com/user-attachments/assets/31b0dd6f-ca4f-445a-9457-70cb44a381b2" width="1000"/>
+<img src="https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485" width="1000"/>
 </div>
 
 ## 🎬 快速開始
@@ -184,7 +183,7 @@
 > 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 `v0.21.1`。請參考下表查看不同 Docker 發行版的說明。如需下載不同於 `v0.21.1` 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。
+   > 執行以下指令會自動下載 RAGFlow slim Docker 映像 `v0.20.5-slim`。請參考下表查看不同 Docker 發行版的說明。如需下載不同於 `v0.20.5-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:v0.20.5` 來下載 RAGFlow 鏡像的 `v0.20.5` 完整發行版。
 
    ```bash
    $ cd ragflow/docker
@@ -192,17 +191,15 @@
    $ docker compose -f docker-compose.yml up -d
 
    # To use GPU to accelerate embedding and DeepDoc tasks:
-   # sed -i '1i DEVICE=gpu' .env
-   # docker compose -f docker-compose.yml up -d
+   # docker compose -f docker-compose-gpu.yml up -d
    ```
 
    | 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           |
-   | nightly           | &approx;2       | ❌                    | _Unstable_ nightly build |
-
-   > 注意：自 `v0.22.0` 起，我們僅發佈 slim 版本，並且不再在映像標籤後附加 **-slim** 後綴。
+   | v0.20.5           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.5-slim      | &approx;2       | ❌                    | Stable release           |
+   | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
+   | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
 
    > [!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。
@@ -213,7 +210,7 @@
 4. 伺服器啟動成功後再次確認伺服器狀態：
 
    ```bash
-   $ docker logs -f docker-ragflow-cpu-1
+   $ docker logs -f ragflow-server
    ```
 
    _出現以下介面提示說明伺服器啟動成功：_
@@ -289,7 +286,17 @@ RAGFlow 預設使用 Elasticsearch 儲存文字和向量資料. 如果要切換
 ```bash
 git clone https://github.com/infiniflow/ragflow.git
 cd ragflow/
-docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly .
+docker build --platform linux/amd64 --build-arg LIGHTEN=1 --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
+```
+
+## 🔧 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
@@ -306,7 +313,7 @@ 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 # install RAGFlow dependent python modules
+   uv sync --python 3.10 --all-extras # install RAGFlow dependent python modules
    uv run download_deps.py
    pre-commit install
    ```

README_zh.md

@@ -1,6 +1,6 @@
 <div align="center">
 <a href="https://demo.ragflow.io/">
-<img src="web/src/assets/logo-with-text.svg" width="350" alt="ragflow logo">
+<img src="web/src/assets/logo-with-text.png" width="350" alt="ragflow logo">
 </a>
 </div>
 
@@ -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:v0.21.1">
+        <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:v0.20.5">
     </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">
@@ -83,9 +83,8 @@
 
 ## 🔥 近期更新
 
-- 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。
+- 2025-08-08 支持 OpenAI 最新的 GPT-5 系列模型.
+- 2025-08-04 新增对 Kimi K2 和 Grok 4 等模型的支持.
 - 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。
@@ -133,7 +132,7 @@
 ## 🔎 系统架构
 
 <div align="center" style="margin-top:20px;margin-bottom:20px;">
-<img src="https://github.com/user-attachments/assets/31b0dd6f-ca4f-445a-9457-70cb44a381b2" width="1000"/>
+<img src="https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485" width="1000"/>
 </div>
 
 ## 🎬 快速开始
@@ -184,7 +183,7 @@
 > 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 `v0.21.1`。请参考下表查看不同 Docker 发行版的描述。如需下载不同于 `v0.21.1` 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。
+   > 运行以下命令会自动下载 RAGFlow slim Docker 镜像 `v0.20.5-slim`。请参考下表查看不同 Docker 发行版的描述。如需下载不同于 `v0.20.5-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:v0.20.5` 来下载 RAGFlow 镜像的 `v0.20.5` 完整发行版。
 
    ```bash
    $ cd ragflow/docker
@@ -192,17 +191,15 @@
    $ docker compose -f docker-compose.yml up -d
 
    # To use GPU to accelerate embedding and DeepDoc tasks:
-   # sed -i '1i DEVICE=gpu' .env
-   # docker compose -f docker-compose.yml up -d
+   # docker compose -f docker-compose-gpu.yml up -d
    ```
 
    | 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           |
-   | nightly           | &approx;2       | ❌                    | _Unstable_ nightly build |
-
-   > 注意：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。
+   | v0.20.5           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.5-slim      | &approx;2       | ❌                    | Stable release           |
+   | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
+   | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
 
    > [!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。
@@ -213,7 +210,7 @@
 4. 服务器启动成功后再次确认服务器状态：
 
    ```bash
-   $ docker logs -f docker-ragflow-cpu-1
+   $ docker logs -f ragflow-server
    ```
 
    _出现以下界面提示说明服务器启动成功：_
@@ -289,7 +286,17 @@ RAGFlow 默认使用 Elasticsearch 存储文本和向量数据. 如果要切换
 ```bash
 git clone https://github.com/infiniflow/ragflow.git
 cd ragflow/
-docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly .
+docker build --platform linux/amd64 --build-arg LIGHTEN=1 --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
+```
+
+## 🔧 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
@@ -306,7 +313,7 @@ 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 # install RAGFlow dependent python modules
+   uv sync --python 3.10 --all-extras # install RAGFlow dependent python modules
    uv run download_deps.py
    pre-commit install
    ```

admin/README.md

@@ -15,55 +15,22 @@ It consists of a server-side Service and a command-line client (CLI), both imple
 - **Admin Service**: A backend service that interfaces with the RAGFlow system to execute administrative operations and monitor its status.
 - **Admin CLI**: A command-line interface that allows users to connect to the Admin Service and issue commands for system management.
 
-
-
 ### Starting the Admin Service
 
-#### Launching from source code
-
-1. Before start Admin Service, please make sure RAGFlow system is already started.
-
-2. Launch from source code:
-
-   ```bash
-   python admin/server/admin_server.py
-   ```
-   The service will start and listen for incoming connections from the CLI on the configured port. 
-
-#### Using docker image
-
-1. Before startup, please configure the `docker_compose.yml`  file to enable admin server:
-
-   ```bash
-   command:
-     - --enable-adminserver
-   ```
-
-2. Start the containers, the service will start and listen for incoming connections from the CLI on the configured port.
-
+1.  Before start Admin Service, please make sure RAGFlow system is already started.
 
+2.  Run the service script:
+    ```bash
+    python admin/admin_server.py
+    ```
+    The service will start and listen for incoming connections from the CLI on the configured port.
 
 ### Using the Admin CLI
 
 1.  Ensure the Admin Service is running.
-2.  Install ragflow-cli.
+2.  Launch the CLI client:
     ```bash
-    pip install ragflow-cli==0.21.1
-    ```
-3.  Launch the CLI client:
-    ```bash
-    ragflow-cli -h 127.0.0.1 -p 9381
-    ```
-    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
-
-
+    python admin/admin_client.py -h 0.0.0.0 -p 9381
 
 ## Supported Commands
 
@@ -75,7 +42,12 @@ Commands are case-insensitive and must be terminated with a semicolon (`;`).
     -   Lists all available services within the RAGFlow system.
 -   `SHOW SERVICE <id>;`
     -   Shows detailed status information for the service identified by `<id>`.
-
+-   `STARTUP SERVICE <id>;`
+    -   Attempts to start the service identified by `<id>`.
+-   `SHUTDOWN SERVICE <id>;`
+    -   Attempts to gracefully shut down the service identified by `<id>`.
+-   `RESTART SERVICE <id>;`
+    -   Attempts to restart the service identified by `<id>`.
 
 ### User Management Commands
 
@@ -83,17 +55,10 @@ Commands are case-insensitive and must be terminated with a semicolon (`;`).
     -   Lists all users known to the system.
 -   `SHOW USER '<username>';`
     -   Shows details and permissions for the specified user. The username must be enclosed in single or double quotes.
-
-- `CREATE USER <username> <password>;`
-  - Create user by username and password. The username and password must be enclosed in single or double quotes.
-
 -   `DROP USER '<username>';`
     -   Removes the specified user from the system. Use with caution.
 -   `ALTER USER PASSWORD '<username>' '<new_password>';`
     -   Changes the password for the specified user.
--   `ALTER USER ACTIVE <username> <on/off>;`
-    -   Changes the user to active or inactive.
-
 
 ### Data and Agent Commands
 

admin/admin_client.py

@@ -0,0 +1,574 @@
+import argparse
+import base64
+
+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
+import requests
+from requests.auth import HTTPBasicAuth
+from api.common.base64 import encode_to_base64
+
+GRAMMAR = r"""
+start: command
+
+command: sql_command | meta_command
+
+sql_command: list_services
+           | show_service
+           | startup_service
+           | shutdown_service
+           | restart_service
+           | list_users
+           | show_user
+           | drop_user
+           | alter_user
+           | create_user
+           | activate_user
+           | list_datasets
+           | list_agents
+
+// meta command definition
+meta_command: "\\" meta_command_name [meta_args]
+
+meta_command_name: /[a-zA-Z?]+/
+meta_args: (meta_arg)+
+
+meta_arg: /[^\\s"']+/ | quoted_string
+
+// command definition
+
+LIST: "LIST"i
+SERVICES: "SERVICES"i
+SHOW: "SHOW"i
+CREATE: "CREATE"i
+SERVICE: "SERVICE"i
+SHUTDOWN: "SHUTDOWN"i
+STARTUP: "STARTUP"i
+RESTART: "RESTART"i
+USERS: "USERS"i
+DROP: "DROP"i
+USER: "USER"i
+ALTER: "ALTER"i
+ACTIVE: "ACTIVE"i
+PASSWORD: "PASSWORD"i
+DATASETS: "DATASETS"i
+OF: "OF"i
+AGENTS: "AGENTS"i
+
+list_services: LIST SERVICES ";"
+show_service: SHOW SERVICE NUMBER ";"
+startup_service: STARTUP SERVICE NUMBER ";"
+shutdown_service: SHUTDOWN SERVICE NUMBER ";"
+restart_service: RESTART SERVICE NUMBER ";"
+
+list_users: LIST USERS ";"
+drop_user: DROP USER quoted_string ";"
+alter_user: ALTER USER PASSWORD quoted_string quoted_string ";"
+show_user: SHOW USER quoted_string ";"
+create_user: CREATE USER quoted_string quoted_string ";"
+activate_user: ALTER USER ACTIVE quoted_string status ";"
+
+list_datasets: LIST DATASETS OF quoted_string ";"
+list_agents: LIST AGENTS OF quoted_string ";"
+
+identifier: WORD
+quoted_string: QUOTED_STRING
+status: WORD
+
+QUOTED_STRING: /'[^']+'/ | /"[^"]+"/
+WORD: /[a-zA-Z0-9_\-\.]+/
+NUMBER: /[0-9]+/
+
+%import common.WS
+%ignore WS
+"""
+
+
+class AdminTransformer(Transformer):
+
+    def start(self, items):
+        return items[0]
+
+    def command(self, items):
+        return items[0]
+
+    def list_services(self, items):
+        result = {'type': 'list_services'}
+        return result
+
+    def show_service(self, items):
+        service_id = int(items[2])
+        return {"type": "show_service", "number": service_id}
+
+    def startup_service(self, items):
+        service_id = int(items[2])
+        return {"type": "startup_service", "number": service_id}
+
+    def shutdown_service(self, items):
+        service_id = int(items[2])
+        return {"type": "shutdown_service", "number": service_id}
+
+    def restart_service(self, items):
+        service_id = int(items[2])
+        return {"type": "restart_service", "number": service_id}
+
+    def list_users(self, items):
+        return {"type": "list_users"}
+
+    def show_user(self, items):
+        user_name = items[2]
+        return {"type": "show_user", "username": user_name}
+
+    def drop_user(self, items):
+        user_name = items[2]
+        return {"type": "drop_user", "username": 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}
+
+    def create_user(self, items):
+        user_name = items[2]
+        password = items[3]
+        return {"type": "create_user", "username": 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}
+
+    def list_datasets(self, items):
+        user_name = items[3]
+        return {"type": "list_datasets", "username": user_name}
+
+    def list_agents(self, items):
+        user_name = items[3]
+        return {"type": "list_agents", "username": user_name}
+
+    def meta_command(self, items):
+        command_name = str(items[0]).lower()
+        args = items[1:] if len(items) > 1 else []
+
+        # handle quoted parameter
+        parsed_args = []
+        for arg in args:
+            if hasattr(arg, 'value'):
+                parsed_args.append(arg.value)
+            else:
+                parsed_args.append(str(arg))
+
+        return {'type': 'meta', 'command': command_name, 'args': parsed_args}
+
+    def meta_command_name(self, items):
+        return items[0]
+
+    def meta_args(self, items):
+        return items
+
+
+def encrypt(input_string):
+    pub = '-----BEGIN PUBLIC KEY-----\nMIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEArq9XTUSeYr2+N1h3Afl/z8Dse/2yD0ZGrKwx+EEEcdsBLca9Ynmx3nIB5obmLlSfmskLpBo0UACBmB5rEjBp2Q2f3AG3Hjd4B+gNCG6BDaawuDlgANIhGnaTLrIqWrrcm4EMzJOnAOI1fgzJRsOOUEfaS318Eq9OVO3apEyCCt0lOQK6PuksduOjVxtltDav+guVAA068NrPYmRNabVKRNLJpL8w4D44sfth5RvZ3q9t+6RTArpEtc5sh5ChzvqPOzKGMXW83C95TxmXqpbK6olN4RevSfVjEAgCydH6HN6OhtOQEcnrU97r9H0iZOWwbw3pVrZiUkuRD1R56Wzs2wIDAQAB\n-----END PUBLIC KEY-----'
+    pub_key = RSA.importKey(pub)
+    cipher = Cipher_pkcs1_v1_5.new(pub_key)
+    cipher_text = cipher.encrypt(base64.b64encode(input_string.encode('utf-8')))
+    return base64.b64encode(cipher_text).decode("utf-8")
+
+
+class AdminCommandParser:
+    def __init__(self):
+        self.parser = Lark(GRAMMAR, start='start', parser='lalr', transformer=AdminTransformer())
+        self.command_history = []
+
+    def parse_command(self, command_str: str) -> Dict[str, Any]:
+        if not command_str.strip():
+            return {'type': 'empty'}
+
+        self.command_history.append(command_str)
+
+        try:
+            result = self.parser.parse(command_str)
+            return result
+        except Exception as e:
+            return {'type': 'error', 'message': f'Parse error: {str(e)}'}
+
+
+class AdminCLI:
+    def __init__(self):
+        self.parser = AdminCommandParser()
+        self.is_interactive = False
+        self.admin_account = "admin@ragflow.io"
+        self.admin_password: str = "admin"
+        self.host: str = ""
+        self.port: int = 0
+
+    def verify_admin(self, args):
+
+        conn_info = self._parse_connection_args(args)
+        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'
+
+        try_count = 0
+        while True:
+            try_count += 1
+            if try_count > 3:
+                return False
+
+            admin_passwd = input(f"password for {self.admin_account}: ").strip()
+            try:
+                self.admin_password = encode_to_base64(admin_passwd)
+                response = requests.get(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password))
+                if response.status_code == 200:
+                    res_json = response.json()
+                    error_code = res_json.get('code', -1)
+                    if error_code == 0:
+                        print("Authentication successful.")
+                        return True
+                    else:
+                        error_message = res_json.get('message', 'Unknown error')
+                        print(f"Authentication failed: {error_message}, try again")
+                        continue
+                else:
+                    print(f"Bad response，status: {response.status_code}, try again")
+            except Exception:
+                print(f"Can't access {self.host}, port: {self.port}")
+
+    def _print_table_simple(self, data):
+        if not data:
+            print("No data to print")
+            return
+        if isinstance(data, dict):
+            # handle single row data
+            data = [data]
+
+        columns = list(data[0].keys())
+        col_widths = {}
+
+        for col in columns:
+            max_width = len(str(col))
+            for item in data:
+                value_len = len(str(item.get(col, '')))
+                if value_len > max_width:
+                    max_width = value_len
+            col_widths[col] = max(2, max_width)
+
+        # Generate delimiter
+        separator = "+" + "+".join(["-" * (col_widths[col] + 2) for col in columns]) + "+"
+
+        # Print header
+        print(separator)
+        header = "|" + "|".join([f" {col:<{col_widths[col]}} " for col in columns]) + "|"
+        print(header)
+        print(separator)
+
+        # Print data
+        for item in data:
+            row = "|"
+            for col in columns:
+                value = str(item.get(col, ''))
+                if len(value) > col_widths[col]:
+                    value = value[:col_widths[col] - 3] + "..."
+                row += f" {value:<{col_widths[col]}} |"
+            print(row)
+
+        print(separator)
+
+    def run_interactive(self):
+
+        self.is_interactive = True
+        print("RAGFlow Admin command line interface - Type '\\?' for help, '\\q' to quit")
+
+        while True:
+            try:
+                command = input("admin> ").strip()
+                if not command:
+                    continue
+
+                print(f"command: {command}")
+                result = self.parser.parse_command(command)
+                self.execute_command(result)
+
+                if isinstance(result, Tree):
+                    continue
+
+                if result.get('type') == 'meta' and result.get('command') in ['q', 'quit', 'exit']:
+                    break
+
+            except KeyboardInterrupt:
+                print("\nUse '\\q' to quit")
+            except EOFError:
+                print("\nGoodbye!")
+                break
+
+    def run_single_command(self, args):
+        conn_info = self._parse_connection_args(args)
+        if 'error' in conn_info:
+            print(f"Error: {conn_info['error']}")
+            return
+
+    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')
+
+        try:
+            parsed_args, remaining_args = parser.parse_known_args(args)
+            return {
+                'host': parsed_args.host,
+                'port': parsed_args.port,
+            }
+        except SystemExit:
+            return {'error': 'Invalid connection arguments'}
+
+    def execute_command(self, parsed_command: Dict[str, Any]):
+
+        command_dict: dict
+        if isinstance(parsed_command, Tree):
+            command_dict = parsed_command.children[0]
+        else:
+            if parsed_command['type'] == 'error':
+                print(f"Error: {parsed_command['message']}")
+                return
+            else:
+                command_dict = parsed_command
+
+        # print(f"Parsed command: {command_dict}")
+
+        command_type = command_dict['type']
+
+        match command_type:
+            case 'list_services':
+                self._handle_list_services(command_dict)
+            case 'show_service':
+                self._handle_show_service(command_dict)
+            case 'restart_service':
+                self._handle_restart_service(command_dict)
+            case 'shutdown_service':
+                self._handle_shutdown_service(command_dict)
+            case 'startup_service':
+                self._handle_startup_service(command_dict)
+            case 'list_users':
+                self._handle_list_users(command_dict)
+            case 'show_user':
+                self._handle_show_user(command_dict)
+            case 'drop_user':
+                self._handle_drop_user(command_dict)
+            case 'alter_user':
+                self._handle_alter_user(command_dict)
+            case 'create_user':
+                self._handle_create_user(command_dict)
+            case 'activate_user':
+                self._handle_activate_user(command_dict)
+            case 'list_datasets':
+                self._handle_list_datasets(command_dict)
+            case 'list_agents':
+                self._handle_list_agents(command_dict)
+            case 'meta':
+                self._handle_meta_command(command_dict)
+            case _:
+                print(f"Command '{command_type}' would be executed with API")
+
+    def _handle_list_services(self, command):
+        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))
+        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']}")
+
+    def _handle_show_service(self, command):
+        service_id: int = command['number']
+        print(f"Showing service: {service_id}")
+
+    def _handle_restart_service(self, command):
+        service_id: int = command['number']
+        print(f"Restart service {service_id}")
+
+    def _handle_shutdown_service(self, command):
+        service_id: int = command['number']
+        print(f"Shutdown service {service_id}")
+
+    def _handle_startup_service(self, command):
+        service_id: int = command['number']
+        print(f"Startup service {service_id}")
+
+    def _handle_list_users(self, command):
+        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))
+        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']}")
+
+    def _handle_show_user(self, command):
+        username_tree: Tree = command['username']
+        username: str = username_tree.children[0].strip("'\"")
+        print(f"Showing user: {username}")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{username}'
+        response = requests.get(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password))
+        res_json = response.json()
+        if response.status_code == 200:
+            self._print_table_simple(res_json['data'])
+        else:
+            print(f"Fail to get user {username}, code: {res_json['code']}, message: {res_json['message']}")
+
+    def _handle_drop_user(self, command):
+        username_tree: Tree = command['username']
+        username: str = username_tree.children[0].strip("'\"")
+        print(f"Drop user: {username}")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{username}'
+        response = requests.delete(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password))
+        res_json = response.json()
+        if response.status_code == 200:
+            print(res_json["message"])
+        else:
+            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']
+        username: str = username_tree.children[0].strip("'\"")
+        password_tree: Tree = command['password']
+        password: str = password_tree.children[0].strip("'\"")
+        print(f"Alter user: {username}, password: {password}")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{username}/password'
+        response = requests.put(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password),
+                                json={'new_password': encrypt(password)})
+        res_json = response.json()
+        if response.status_code == 200:
+            print(res_json["message"])
+        else:
+            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']
+        username: str = username_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}")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/users'
+        response = requests.post(
+            url,
+            auth=HTTPBasicAuth(self.admin_account, self.admin_password),
+            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']}")
+
+    def _handle_activate_user(self, command):
+        username_tree: Tree = command['username']
+        username: str = username_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()}.")
+            url = f'http://{self.host}:{self.port}/api/v1/admin/users/{username}/activate'
+            response = requests.put(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password),
+                                    json={'activate_status': activate_status})
+            res_json = response.json()
+            if response.status_code == 200:
+                print(res_json["message"])
+            else:
+                print(f"Fail to alter activate status, code: {res_json['code']}, message: {res_json['message']}")
+        else:
+            print(f"Unknown activate status: {activate_status}.")
+
+    def _handle_list_datasets(self, command):
+        username_tree: Tree = command['username']
+        username: str = username_tree.children[0].strip("'\"")
+        print(f"Listing all datasets of user: {username}")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{username}/datasets'
+        response = requests.get(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password))
+        res_json = response.json()
+        if response.status_code == 200:
+            self._print_table_simple(res_json['data'])
+        else:
+            print(f"Fail to get all datasets of {username}, code: {res_json['code']}, message: {res_json['message']}")
+
+    def _handle_list_agents(self, command):
+        username_tree: Tree = command['username']
+        username: str = username_tree.children[0].strip("'\"")
+        print(f"Listing all agents of user: {username}")
+        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{username}/agents'
+        response = requests.get(url, auth=HTTPBasicAuth(self.admin_account, self.admin_password))
+        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']}")
+
+    def _handle_meta_command(self, command):
+        meta_command = command['command']
+        args = command.get('args', [])
+
+        if meta_command in ['?', 'h', 'help']:
+            self.show_help()
+        elif meta_command in ['q', 'quit', 'exit']:
+            print("Goodbye!")
+        else:
+            print(f"Meta command '{meta_command}' with args {args}")
+
+    def show_help(self):
+        """Help info"""
+        help_text = """
+Commands:
+  LIST SERVICES
+  SHOW SERVICE <service>
+  STARTUP SERVICE <service>
+  SHUTDOWN SERVICE <service>
+  RESTART SERVICE <service>
+  LIST USERS
+  SHOW USER <user>
+  DROP USER <user>
+  CREATE USER <user> <password>
+  ALTER USER PASSWORD <user> <new_password>
+  ALTER USER ACTIVE <user> <on/off>
+  LIST DATASETS OF <user>
+  LIST AGENTS OF <user>
+
+Meta Commands:
+  \\?, \\h, \\help     Show this help
+  \\q, \\quit, \\exit   Quit the CLI
+        """
+        print(help_text)
+
+
+def main():
+    import sys
+
+    cli = AdminCLI()
+
+    if len(sys.argv) == 1 or (len(sys.argv) > 1 and sys.argv[1] == '-'):
+        print(r"""
+            ____  ___   ______________                 ___       __          _     
+           / __ \/   | / ____/ ____/ /___ _      __   /   | ____/ /___ ___  (_)___ 
+          / /_/ / /| |/ / __/ /_  / / __ \ | /| / /  / /| |/ __  / __ `__ \/ / __ \
+         / _, _/ ___ / /_/ / __/ / / /_/ / |/ |/ /  / ___ / /_/ / / / / / / / / / /
+        /_/ |_/_/  |_\____/_/   /_/\____/|__/|__/  /_/  |_\__,_/_/ /_/ /_/_/_/ /_/ 
+        """)
+        if cli.verify_admin(sys.argv):
+            cli.run_interactive()
+    else:
+        if cli.verify_admin(sys.argv):
+            cli.run_interactive()
+            # cli.run_single_command(sys.argv[1:])
+
+
+if __name__ == '__main__':
+    main()

admin/admin_server.py

@@ -1,18 +1,3 @@
-#
-#  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 os
 import signal
@@ -27,9 +12,6 @@ from api.utils.log_utils import init_root_logger
 from api.constants import SERVICE_CONF
 from api import settings
 from config import load_configurations, SERVICE_CONFIGS
-from auth import init_default_admin, setup_auth
-from flask_session import Session
-from flask_login import LoginManager
 
 stop_event = threading.Event()
 
@@ -45,17 +27,7 @@ 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)
-    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:

admin/auth.py

@@ -0,0 +1,57 @@
+import logging
+import uuid
+from functools import wraps
+from flask import request, jsonify
+
+from exceptions import AdminException
+from api.db.init_data import encode_to_base64
+from api.db.services import UserService
+
+
+def check_admin(username: str, password: str):
+    users = UserService.query(email=username)
+    if not users:
+        logging.info(f"Username: {username} is not registered!")
+        user_info = {
+            "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(**user_info):
+            raise AdminException("Can't init admin.", 500)
+
+    user = UserService.query_user(username, password)
+    if user:
+        return True
+    else:
+        return False
+
+
+def login_verify(f):
+    @wraps(f)
+    def decorated(*args, **kwargs):
+        auth = request.authorization
+        if not auth or 'username' not in auth.parameters or 'password' not in auth.parameters:
+            return jsonify({
+                "code": 401,
+                "message": "Authentication required",
+                "data": None
+            }), 200
+
+        username = auth.parameters['username']
+        password = auth.parameters['password']
+        # TODO: to check the username and password from DB
+        if check_admin(username, password) is False:
+            return jsonify({
+                "code": 403,
+                "message": "Access denied",
+                "data": None
+            }), 200
+
+        return f(*args, **kwargs)
+
+    return decorated

admin/build_cli_release.sh

@@ -1,47 +0,0 @@
-#!/bin/bash
-
-set -e
-
-echo "🚀 Start building..."
-echo "================================"
-
-PROJECT_NAME="ragflow-cli"
-
-RELEASE_DIR="release"
-BUILD_DIR="dist"
-SOURCE_DIR="src"
-PACKAGE_DIR="ragflow_cli"
-
-echo "🧹 Clean old build folder..."
-rm -rf release/
-
-echo "📁 Prepare source code..."
-mkdir release/$PROJECT_NAME/$SOURCE_DIR -p
-cp pyproject.toml release/$PROJECT_NAME/pyproject.toml
-cp README.md release/$PROJECT_NAME/README.md
-
-mkdir release/$PROJECT_NAME/$SOURCE_DIR/$PACKAGE_DIR -p
-cp admin_client.py release/$PROJECT_NAME/$SOURCE_DIR/$PACKAGE_DIR/admin_client.py
-
-if [ -d "release/$PROJECT_NAME/$SOURCE_DIR" ]; then
-    echo "✅ source dir: release/$PROJECT_NAME/$SOURCE_DIR"
-else
-    echo "❌ source dir not exist: release/$PROJECT_NAME/$SOURCE_DIR"
-    exit 1
-fi
-
-echo "🔨 Make build file..."
-cd release/$PROJECT_NAME
-export PYTHONPATH=$(pwd)
-python -m build
-
-echo "✅ check build result..."
-if [ -d "$BUILD_DIR" ]; then
-    echo "📦 Package generated:"
-    ls -la $BUILD_DIR/
-else
-    echo "❌ Build Failed: $BUILD_DIR not exist."
-    exit 1
-fi
-
-echo "🎉 Build finished successfully!"

admin/client/admin_client.py

@@ -1,931 +0,0 @@
-#
-#  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 argparse
-import base64
-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
-import requests
-
-GRAMMAR = r"""
-start: command
-
-command: sql_command | meta_command
-
-sql_command: list_services
-           | show_service
-           | startup_service
-           | shutdown_service
-           | restart_service
-           | list_users
-           | show_user
-           | drop_user
-           | alter_user
-           | create_user
-           | 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
-
-// meta command definition
-meta_command: "\\" meta_command_name [meta_args]
-
-meta_command_name: /[a-zA-Z?]+/
-meta_args: (meta_arg)+
-
-meta_arg: /[^\\s"']+/ | quoted_string
-
-// command definition
-
-LIST: "LIST"i
-SERVICES: "SERVICES"i
-SHOW: "SHOW"i
-CREATE: "CREATE"i
-SERVICE: "SERVICE"i
-SHUTDOWN: "SHUTDOWN"i
-STARTUP: "STARTUP"i
-RESTART: "RESTART"i
-USERS: "USERS"i
-DROP: "DROP"i
-USER: "USER"i
-ALTER: "ALTER"i
-ACTIVE: "ACTIVE"i
-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
-
-list_services: LIST SERVICES ";"
-show_service: SHOW SERVICE NUMBER ";"
-startup_service: STARTUP SERVICE NUMBER ";"
-shutdown_service: SHUTDOWN SERVICE NUMBER ";"
-restart_service: RESTART SERVICE NUMBER ";"
-
-list_users: LIST USERS ";"
-drop_user: DROP USER quoted_string ";"
-alter_user: ALTER USER PASSWORD quoted_string quoted_string ";"
-show_user: SHOW USER quoted_string ";"
-create_user: CREATE USER quoted_string quoted_string ";"
-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 ";"
-
-action_list: identifier ("," identifier)*
-
-identifier: WORD
-quoted_string: QUOTED_STRING
-status: WORD
-
-QUOTED_STRING: /'[^']+'/ | /"[^"]+"/
-WORD: /[a-zA-Z0-9_\-\.]+/
-NUMBER: /[0-9]+/
-
-%import common.WS
-%ignore WS
-"""
-
-
-class AdminTransformer(Transformer):
-
-    def start(self, items):
-        return items[0]
-
-    def command(self, items):
-        return items[0]
-
-    def list_services(self, items):
-        result = {'type': 'list_services'}
-        return result
-
-    def show_service(self, items):
-        service_id = int(items[2])
-        return {"type": "show_service", "number": service_id}
-
-    def startup_service(self, items):
-        service_id = int(items[2])
-        return {"type": "startup_service", "number": service_id}
-
-    def shutdown_service(self, items):
-        service_id = int(items[2])
-        return {"type": "shutdown_service", "number": service_id}
-
-    def restart_service(self, items):
-        service_id = int(items[2])
-        return {"type": "restart_service", "number": service_id}
-
-    def list_users(self, items):
-        return {"type": "list_users"}
-
-    def show_user(self, items):
-        user_name = items[2]
-        return {"type": "show_user", "user_name": user_name}
-
-    def drop_user(self, items):
-        user_name = items[2]
-        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", "user_name": user_name, "password": new_password}
-
-    def create_user(self, items):
-        user_name = items[2]
-        password = items[3]
-        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, "user_name": user_name}
-
-    def list_datasets(self, items):
-        user_name = items[3]
-        return {"type": "list_datasets", "user_name": user_name}
-
-    def list_agents(self, items):
-        user_name = items[3]
-        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 action_list(self, items):
-        return items
-
-    def meta_command(self, items):
-        command_name = str(items[0]).lower()
-        args = items[1:] if len(items) > 1 else []
-
-        # handle quoted parameter
-        parsed_args = []
-        for arg in args:
-            if hasattr(arg, 'value'):
-                parsed_args.append(arg.value)
-            else:
-                parsed_args.append(str(arg))
-
-        return {'type': 'meta', 'command': command_name, 'args': parsed_args}
-
-    def meta_command_name(self, items):
-        return items[0]
-
-    def meta_args(self, items):
-        return items
-
-
-def encrypt(input_string):
-    pub = '-----BEGIN PUBLIC KEY-----\nMIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEArq9XTUSeYr2+N1h3Afl/z8Dse/2yD0ZGrKwx+EEEcdsBLca9Ynmx3nIB5obmLlSfmskLpBo0UACBmB5rEjBp2Q2f3AG3Hjd4B+gNCG6BDaawuDlgANIhGnaTLrIqWrrcm4EMzJOnAOI1fgzJRsOOUEfaS318Eq9OVO3apEyCCt0lOQK6PuksduOjVxtltDav+guVAA068NrPYmRNabVKRNLJpL8w4D44sfth5RvZ3q9t+6RTArpEtc5sh5ChzvqPOzKGMXW83C95TxmXqpbK6olN4RevSfVjEAgCydH6HN6OhtOQEcnrU97r9H0iZOWwbw3pVrZiUkuRD1R56Wzs2wIDAQAB\n-----END PUBLIC KEY-----'
-    pub_key = RSA.importKey(pub)
-    cipher = Cipher_pkcs1_v1_5.new(pub_key)
-    cipher_text = cipher.encrypt(base64.b64encode(input_string.encode('utf-8')))
-    return base64.b64encode(cipher_text).decode("utf-8")
-
-
-def encode_to_base64(input_string):
-    base64_encoded = base64.b64encode(input_string.encode('utf-8'))
-    return base64_encoded.decode('utf-8')
-
-
-class AdminCLI(Cmd):
-    def __init__(self):
-        super().__init__()
-        self.parser = Lark(GRAMMAR, start='start', parser='lalr', transformer=AdminTransformer())
-        self.command_history = []
-        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
-
-    intro = r"""Type "\h" for help."""
-    prompt = "admin> "
-
-    def onecmd(self, command: str) -> bool:
-        try:
-            result = self.parse_command(command)
-
-            if isinstance(result, dict):
-                if 'type' in result and result.get('type') == 'empty':
-                    return False
-
-            self.execute_command(result)
-
-            if isinstance(result, Tree):
-                return False
-
-            if result.get('type') == 'meta' and result.get('command') in ['q', 'quit', 'exit']:
-                return True
-
-        except KeyboardInterrupt:
-            print("\nUse '\\q' to quit")
-        except EOFError:
-            print("\nGoodbye!")
-            return True
-        return False
-
-    def emptyline(self) -> bool:
-        return False
-
-    def default(self, line: str) -> bool:
-        return self.onecmd(line)
-
-    def parse_command(self, command_str: str) -> dict[str, str]:
-        if not command_str.strip():
-            return {'type': 'empty'}
-
-        self.command_history.append(command_str)
-
-        try:
-            result = self.parser.parse(command_str)
-            return result
-        except Exception as e:
-            return {'type': 'error', 'message': f'Parse error: {str(e)}'}
-
-    def verify_admin(self, arguments: dict, single_command: bool):
-        self.host = arguments['host']
-        self.port = arguments['port']
-        print(f"Attempt to access ip: {self.host}, port: {self.port}")
-        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 > attempt_count:
-                return False
-
-            if single_command:
-                admin_passwd = arguments['password']
-            else:
-                admin_passwd = input(f"password for {self.admin_account}: ").strip()
-            try:
-                self.admin_password = encrypt(admin_passwd)
-                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/0.21.1'
-                        })
-                        print("Authentication successful.")
-                        return True
-                    else:
-                        error_message = res_json.get('message', 'Unknown error')
-                        print(f"Authentication failed: {error_message}, try again")
-                        continue
-                else:
-                    print(f"Bad response，status: {response.status_code}, password is wrong")
-            except Exception as e:
-                print(str(e))
-                print(f"Can't access {self.host}, port: {self.port}")
-
-    def _print_table_simple(self, data):
-        if not data:
-            print("No data to print")
-            return
-        if isinstance(data, dict):
-            # handle single row data
-            data = [data]
-
-        columns = list(data[0].keys())
-        col_widths = {}
-
-        def get_string_width(text):
-            half_width_chars = (
-                " !\"#$%&'()*+,-./0123456789:;<=>?@"
-                "ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`"
-                "abcdefghijklmnopqrstuvwxyz{|}~"
-                "\t\n\r"
-            )
-            width = 0
-            for char in text:
-                if char in half_width_chars:
-                    width += 1
-                else:
-                    width += 2
-            return width
-
-        for col in columns:
-            max_width = get_string_width(str(col))
-            for item in data:
-                value_len = get_string_width(str(item.get(col, '')))
-                if value_len > max_width:
-                    max_width = value_len
-            col_widths[col] = max(2, max_width)
-
-        # Generate delimiter
-        separator = "+" + "+".join(["-" * (col_widths[col] + 2) for col in columns]) + "+"
-
-        # Print header
-        print(separator)
-        header = "|" + "|".join([f" {col:<{col_widths[col]}} " for col in columns]) + "|"
-        print(header)
-        print(separator)
-
-        # Print data
-        for item in data:
-            row = "|"
-            for col in columns:
-                value = str(item.get(col, ''))
-                if get_string_width(value) > col_widths[col]:
-                    value = value[:col_widths[col] - 3] + "..."
-                row += f" {value:<{col_widths[col] - (get_string_width(value) - len(value))}} |"
-            print(row)
-
-        print(separator)
-
-    def run_interactive(self):
-
-        self.is_interactive = True
-        print("RAGFlow Admin command line interface - Type '\\?' for help, '\\q' to quit")
-
-        while True:
-            try:
-                command = input("admin> ").strip()
-                if not command:
-                    continue
-
-                print(f"command: {command}")
-                result = self.parse_command(command)
-                self.execute_command(result)
-
-                if isinstance(result, Tree):
-                    continue
-
-                if result.get('type') == 'meta' and result.get('command') in ['q', 'quit', 'exit']:
-                    break
-
-            except KeyboardInterrupt:
-                print("\nUse '\\q' to quit")
-            except EOFError:
-                print("\nGoodbye!")
-                break
-
-    def run_single_command(self, command: str):
-        result = self.parse_command(command)
-        self.execute_command(result)
-
-    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('-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)
-            if remaining_args:
-                command = remaining_args[0]
-                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'}
-
-    def execute_command(self, parsed_command: Dict[str, Any]):
-
-        command_dict: dict
-        if isinstance(parsed_command, Tree):
-            command_dict = parsed_command.children[0]
-        else:
-            if parsed_command['type'] == 'error':
-                print(f"Error: {parsed_command['message']}")
-                return
-            else:
-                command_dict = parsed_command
-
-        # print(f"Parsed command: {command_dict}")
-
-        command_type = command_dict['type']
-
-        match command_type:
-            case 'list_services':
-                self._handle_list_services(command_dict)
-            case 'show_service':
-                self._handle_show_service(command_dict)
-            case 'restart_service':
-                self._handle_restart_service(command_dict)
-            case 'shutdown_service':
-                self._handle_shutdown_service(command_dict)
-            case 'startup_service':
-                self._handle_startup_service(command_dict)
-            case 'list_users':
-                self._handle_list_users(command_dict)
-            case 'show_user':
-                self._handle_show_user(command_dict)
-            case 'drop_user':
-                self._handle_drop_user(command_dict)
-            case 'alter_user':
-                self._handle_alter_user(command_dict)
-            case 'create_user':
-                self._handle_create_user(command_dict)
-            case 'activate_user':
-                self._handle_activate_user(command_dict)
-            case 'list_datasets':
-                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 'meta':
-                self._handle_meta_command(command_dict)
-            case _:
-                print(f"Command '{command_type}' would be executed with API")
-
-    def _handle_list_services(self, command):
-        print("Listing all services")
-
-        url = f'http://{self.host}:{self.port}/api/v1/admin/services'
-        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 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 = self.session.get(url)
-        res_json = response.json()
-        if response.status_code == 200:
-            res_data = res_json['data']
-            if 'status' in res_data and res_data['status'] == 'alive':
-                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'])
-            else:
-                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']}")
-
-    def _handle_restart_service(self, command):
-        service_id: int = command['number']
-        print(f"Restart service {service_id}")
-
-    def _handle_shutdown_service(self, command):
-        service_id: int = command['number']
-        print(f"Shutdown service {service_id}")
-
-    def _handle_startup_service(self, command):
-        service_id: int = command['number']
-        print(f"Startup service {service_id}")
-
-    def _handle_list_users(self, command):
-        print("Listing all users")
-
-        url = f'http://{self.host}:{self.port}/api/v1/admin/users'
-        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']}")
-
-    def _handle_show_user(self, command):
-        username_tree: Tree = command['user_name']
-        user_name: str = username_tree.children[0].strip("'\"")
-        print(f"Showing user: {user_name}")
-        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{user_name}'
-        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 user {user_name}, code: {res_json['code']}, message: {res_json['message']}")
-
-    def _handle_drop_user(self, command):
-        username_tree: Tree = command['user_name']
-        user_name: str = username_tree.children[0].strip("'\"")
-        print(f"Drop user: {user_name}")
-        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{user_name}'
-        response = self.session.delete(url)
-        res_json = response.json()
-        if response.status_code == 200:
-            print(res_json["message"])
-        else:
-            print(f"Fail to drop user, code: {res_json['code']}, message: {res_json['message']}")
-
-    def _handle_alter_user(self, command):
-        user_name_tree: Tree = command['user_name']
-        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: {user_name}, password: {password}")
-        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{user_name}/password'
-        response = self.session.put(url, json={'new_password': encrypt(password)})
-        res_json = response.json()
-        if response.status_code == 200:
-            print(res_json["message"])
-        else:
-            print(f"Fail to alter password, code: {res_json['code']}, message: {res_json['message']}")
-
-    def _handle_create_user(self, command):
-        user_name_tree: Tree = command['user_name']
-        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: {user_name}, password: {password}, role: {role}")
-        url = f'http://{self.host}:{self.port}/api/v1/admin/users'
-        response = self.session.post(
-            url,
-            json={'user_name': user_name, '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 {user_name}, code: {res_json['code']}, message: {res_json['message']}")
-
-    def _handle_activate_user(self, command):
-        user_name_tree: Tree = command['user_name']
-        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 {user_name} activate status, turn {activate_status.lower()}.")
-            url = f'http://{self.host}:{self.port}/api/v1/admin/users/{user_name}/activate'
-            response = self.session.put(url, json={'activate_status': activate_status})
-            res_json = response.json()
-            if response.status_code == 200:
-                print(res_json["message"])
-            else:
-                print(f"Fail to alter activate status, code: {res_json['code']}, message: {res_json['message']}")
-        else:
-            print(f"Unknown activate status: {activate_status}.")
-
-    def _handle_list_datasets(self, command):
-        username_tree: Tree = command['user_name']
-        user_name: str = username_tree.children[0].strip("'\"")
-        print(f"Listing all datasets of user: {user_name}")
-        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{user_name}/datasets'
-        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 datasets of {user_name}, code: {res_json['code']}, message: {res_json['message']}")
-
-    def _handle_list_agents(self, command):
-        username_tree: Tree = command['user_name']
-        user_name: str = username_tree.children[0].strip("'\"")
-        print(f"Listing all agents of user: {user_name}")
-        url = f'http://{self.host}:{self.port}/api/v1/admin/users/{user_name}/agents'
-        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 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 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 _handle_meta_command(self, command):
-        meta_command = command['command']
-        args = command.get('args', [])
-
-        if meta_command in ['?', 'h', 'help']:
-            self.show_help()
-        elif meta_command in ['q', 'quit', 'exit']:
-            print("Goodbye!")
-        else:
-            print(f"Meta command '{meta_command}' with args {args}")
-
-    def show_help(self):
-        """Help info"""
-        help_text = """
-Commands:
-  LIST SERVICES
-  SHOW SERVICE <service>
-  STARTUP SERVICE <service>
-  SHUTDOWN SERVICE <service>
-  RESTART SERVICE <service>
-  LIST USERS
-  SHOW USER <user>
-  DROP USER <user>
-  CREATE USER <user> <password>
-  ALTER USER PASSWORD <user> <new_password>
-  ALTER USER ACTIVE <user> <on/off>
-  LIST DATASETS OF <user>
-  LIST AGENTS OF <user>
-
-Meta Commands:
-  \\?, \\h, \\help     Show this help
-  \\q, \\quit, \\exit   Quit the CLI
-        """
-        print(help_text)
-
-
-def main():
-    import sys
-
-    cli = AdminCLI()
-
-    args = cli.parse_connection_args(sys.argv)
-    if 'error' in args:
-        print(f"Error: {args['error']}")
-        return
-
-    if 'command' in args:
-        if 'password' not in args:
-            print("Error: password is missing")
-            return
-        if cli.verify_admin(args, single_command=True):
-            command: str = args['command']
-            print(f"Run single command: {command}")
-            cli.run_single_command(command)
-    else:
-        if cli.verify_admin(args, single_command=False):
-            print(r"""
-                ____  ___   ______________                 ___       __          _     
-               / __ \/   | / ____/ ____/ /___ _      __   /   | ____/ /___ ___  (_)___ 
-              / /_/ / /| |/ / __/ /_  / / __ \ | /| / /  / /| |/ __  / __ `__ \/ / __ \
-             / _, _/ ___ / /_/ / __/ / / /_/ / |/ |/ /  / ___ / /_/ / / / / / / / / / /
-            /_/ |_/_/  |_\____/_/   /_/\____/|__/|__/  /_/  |_\__,_/_/ /_/ /_/_/_/ /_/ 
-            """)
-            cli.cmdloop()
-
-
-if __name__ == '__main__':
-    main()

admin/client/pyproject.toml

@@ -1,24 +0,0 @@
-[project]
-name = "ragflow-cli"
-version = "0.21.1"
-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" }
-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 = "admin_client:main"

admin/config.py

@@ -1,20 +1,3 @@
-#
-#  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
 import threading
 from enum import Enum
@@ -26,8 +9,6 @@ from urllib.parse import urlparse
 
 
 class ServiceConfigs:
-    configs = dict
-
     def __init__(self):
         self.configs = []
         self.lock = threading.Lock()
@@ -51,11 +32,9 @@ class BaseConfig(BaseModel):
     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}
+        return {'id': self.id, 'name': self.name, 'host': self.host, 'port': self.port, 'service_type': self.service_type}
 
 
 class MetaConfig(BaseConfig):
@@ -230,9 +209,7 @@ def load_configurations(config_path: str) -> list[BaseConfig]:
                 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")
+                config = RAGFlowServerConfig(id=id_count, name=name, host=host, port=http_port, service_type="ragflow_server")
                 configurations.append(config)
                 id_count += 1
             case "es":
@@ -245,8 +222,7 @@ def load_configurations(config_path: str) -> list[BaseConfig]:
                 password: str = v.get('password')
                 config = ElasticsearchConfig(id=id_count, name=name, host=host, port=port, service_type="retrieval",
                                              retrieval_type="elasticsearch",
-                                             username=username, password=password,
-                                             detail_func_name="get_es_cluster_stats")
+                                             username=username, password=password)
                 configurations.append(config)
                 id_count += 1
 
@@ -257,9 +233,8 @@ 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",
-                                        db_name=database, detail_func_name="get_infinity_status")
+                config = InfinityConfig(id=id_count, name=name, host=host, port=port, service_type="retrieval", retrieval_type="infinity",
+                                        db_name=database)
                 configurations.append(config)
                 id_count += 1
             case "minio":
@@ -270,9 +245,8 @@ 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",
-                                     store_type="minio", detail_func_name="check_minio_alive")
+                config = MinioConfig(id=id_count, name=name, host=host, port=port, user=user, password=password, service_type="file_store",
+                                     store_type="minio")
                 configurations.append(config)
                 id_count += 1
             case "redis":
@@ -284,7 +258,7 @@ def load_configurations(config_path: str) -> list[BaseConfig]:
                 password = v.get('password')
                 db: int = v.get('db')
                 config = RedisConfig(id=id_count, name=name, host=host, port=port, password=password, database=db,
-                                     service_type="message_queue", mq_type="redis", detail_func_name="get_redis_info")
+                                     service_type="message_queue", mq_type="redis")
                 configurations.append(config)
                 id_count += 1
             case "mysql":
@@ -294,7 +268,7 @@ def load_configurations(config_path: str) -> list[BaseConfig]:
                 username = v.get('user')
                 password = v.get('password')
                 config = MySQLConfig(id=id_count, name=name, host=host, port=port, username=username, password=password,
-                                     service_type="meta_data", meta_type="mysql", detail_func_name="get_mysql_status")
+                                     service_type="meta_data", meta_type="mysql")
                 configurations.append(config)
                 id_count += 1
             case "admin":

admin/responses.py

@@ -0,0 +1,15 @@
+from flask import jsonify
+
+def success_response(data=None, message="Success", code = 0):
+    return jsonify({
+        "code": code,
+        "message": message,
+        "data": data
+    }), 200
+
+def error_response(message="Error", code=-1, data=None):
+    return jsonify({
+        "code": code,
+        "message": message,
+        "data": data
+    }), 400

admin/routes.py

@@ -0,0 +1,190 @@
+from flask import Blueprint, request
+
+from auth import login_verify
+from responses import success_response, error_response
+from services import UserMgr, ServiceMgr, UserServiceMgr
+from exceptions import AdminException
+
+admin_bp = Blueprint('admin', __name__, url_prefix='/api/v1/admin')
+
+
+@admin_bp.route('/auth', methods=['GET'])
+@login_verify
+def auth_admin():
+    try:
+        return success_response(None, "Admin is authorized", 0)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/users', methods=['GET'])
+@login_verify
+def list_users():
+    try:
+        users = UserMgr.get_all_users()
+        return success_response(users, "Get all users", 0)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/users', methods=['POST'])
+@login_verify
+def create_user():
+    try:
+        data = request.get_json()
+        if not data or 'username' not in data or 'password' not in data:
+            return error_response("Username and password are required", 400)
+
+        username = data['username']
+        password = data['password']
+        role = data.get('role', 'user')
+
+        res = UserMgr.create_user(username, password, role)
+        if res["success"]:
+            user_info = res["user_info"]
+            user_info.pop("password") # do not return password
+            return success_response(user_info, "User created successfully")
+        else:
+            return error_response("create user failed")
+
+    except AdminException as e:
+        return error_response(e.message, e.code)
+    except Exception as e:
+        return error_response(str(e))
+
+
+@admin_bp.route('/users/<username>', methods=['DELETE'])
+@login_verify
+def delete_user(username):
+    try:
+        res = UserMgr.delete_user(username)
+        if res["success"]:
+            return success_response(None, res["message"])
+        else:
+            return error_response(res["message"])
+
+    except AdminException as e:
+        return error_response(e.message, e.code)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/users/<username>/password', methods=['PUT'])
+@login_verify
+def change_password(username):
+    try:
+        data = request.get_json()
+        if not data or 'new_password' not in data:
+            return error_response("New password is required", 400)
+
+        new_password = data['new_password']
+        msg = UserMgr.update_user_password(username, new_password)
+        return success_response(None, msg)
+
+    except AdminException as e:
+        return error_response(e.message, e.code)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/users/<username>/activate', methods=['PUT'])
+@login_verify
+def alter_user_activate_status(username):
+    try:
+        data = request.get_json()
+        if not data or 'activate_status' not in data:
+            return error_response("Activation status is required", 400)
+        activate_status = data['activate_status']
+        msg = UserMgr.update_user_activate_status(username, activate_status)
+        return success_response(None, msg)
+    except AdminException as e:
+        return error_response(e.message, e.code)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+@admin_bp.route('/users/<username>', methods=['GET'])
+@login_verify
+def get_user_details(username):
+    try:
+        user_details = UserMgr.get_user_details(username)
+        return success_response(user_details)
+
+    except AdminException as e:
+        return error_response(e.message, e.code)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+@admin_bp.route('/users/<username>/datasets', methods=['GET'])
+@login_verify
+def get_user_datasets(username):
+    try:
+        datasets_list = UserServiceMgr.get_user_datasets(username)
+        return success_response(datasets_list)
+
+    except AdminException as e:
+        return error_response(e.message, e.code)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/users/<username>/agents', methods=['GET'])
+@login_verify
+def get_user_agents(username):
+    try:
+        agents_list = UserServiceMgr.get_user_agents(username)
+        return success_response(agents_list)
+
+    except AdminException as e:
+        return error_response(e.message, e.code)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/services', methods=['GET'])
+@login_verify
+def get_services():
+    try:
+        services = ServiceMgr.get_all_services()
+        return success_response(services, "Get all services", 0)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/service_types/<service_type>', methods=['GET'])
+@login_verify
+def get_services_by_type(service_type_str):
+    try:
+        services = ServiceMgr.get_services_by_type(service_type_str)
+        return success_response(services)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/services/<service_id>', methods=['GET'])
+@login_verify
+def get_service(service_id):
+    try:
+        services = ServiceMgr.get_service_details(service_id)
+        return success_response(services)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/services/<service_id>', methods=['DELETE'])
+@login_verify
+def shutdown_service(service_id):
+    try:
+        services = ServiceMgr.shutdown_service(service_id)
+        return success_response(services)
+    except Exception as e:
+        return error_response(str(e), 500)
+
+
+@admin_bp.route('/services/<service_id>', methods=['PUT'])
+@login_verify
+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/server/auth.py

@@ -1,189 +0,0 @@
-#
-#  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
-import uuid
-from functools import wraps
-from datetime import datetime
-from flask import request, jsonify
-from flask_login import current_user, login_user
-from itsdangerous.url_safe import URLSafeTimedSerializer as Serializer
-
-from api import settings
-from api.common.exceptions import AdminException, UserNotFoundError
-from api.db.init_data import encode_to_base64
-from api.db.services import UserService
-from api.db import ActiveEnum, StatusEnum
-from api.utils.crypt import decrypt
-from api.utils import get_uuid
-from common.time_utils import current_timestamp, datetime_format, get_format_time
-from api.utils.api_utils import (
-    construct_response,
-)
-
-
-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 construct_response(data=resp, auth=user.get_id(), message=msg)
-
-
-def check_admin(username: str, password: str):
-    users = UserService.query(email=username)
-    if not users:
-        logging.info(f"Username: {username} is not registered!")
-        user_info = {
-            "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(**user_info):
-            raise AdminException("Can't init admin.", 500)
-
-    user = UserService.query_user(username, password)
-    if user:
-        return True
-    else:
-        return False
-
-
-def login_verify(f):
-    @wraps(f)
-    def decorated(*args, **kwargs):
-        auth = request.authorization
-        if not auth or 'username' not in auth.parameters or 'password' not in auth.parameters:
-            return jsonify({
-                "code": 401,
-                "message": "Authentication required",
-                "data": None
-            }), 200
-
-        username = auth.parameters['username']
-        password = auth.parameters['password']
-        try:
-            if check_admin(username, password) is False:
-                return jsonify({
-                    "code": 500,
-                    "message": "Access denied",
-                    "data": None
-                }), 200
-        except Exception as e:
-            error_msg = str(e)
-            return jsonify({
-                "code": 500,
-                "message": error_msg
-            }), 200
-
-        return f(*args, **kwargs)
-
-    return decorated

admin/server/models.py

@@ -1,15 +0,0 @@
-#
-#  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.
-#

admin/server/responses.py

@@ -1,34 +0,0 @@
-#
-#  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.
-#
-
-
-from flask import jsonify
-
-
-def success_response(data=None, message="Success", code=0):
-    return jsonify({
-        "code": code,
-        "message": message,
-        "data": data
-    }), 200
-
-
-def error_response(message="Error", code=-1, data=None):
-    return jsonify({
-        "code": code,
-        "message": message,
-        "data": data
-    }), 400

admin/server/roles.py

@@ -1,76 +0,0 @@
-#
-#  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

@@ -1,371 +0,0 @@
-#
-#  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 secrets
-
-from flask import Blueprint, request
-from flask_login import current_user, logout_user, login_required
-
-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
-
-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():
-    try:
-        return success_response(None, "Admin is authorized", 0)
-    except Exception as e:
-        return error_response(str(e), 500)
-
-
-@admin_bp.route('/users', methods=['GET'])
-@login_required
-@check_admin_auth
-def list_users():
-    try:
-        users = UserMgr.get_all_users()
-        return success_response(users, "Get all users", 0)
-    except Exception as e:
-        return error_response(str(e), 500)
-
-
-@admin_bp.route('/users', methods=['POST'])
-@login_required
-@check_admin_auth
-def create_user():
-    try:
-        data = request.get_json()
-        if not data or 'username' not in data or 'password' not in data:
-            return error_response("Username and password are required", 400)
-
-        username = data['username']
-        password = data['password']
-        role = data.get('role', 'user')
-
-        res = UserMgr.create_user(username, password, role)
-        if res["success"]:
-            user_info = res["user_info"]
-            user_info.pop("password")  # do not return password
-            return success_response(user_info, "User created successfully")
-        else:
-            return error_response("create user failed")
-
-    except AdminException as e:
-        return error_response(e.message, e.code)
-    except Exception as e:
-        return error_response(str(e))
-
-
-@admin_bp.route('/users/<username>', methods=['DELETE'])
-@login_required
-@check_admin_auth
-def delete_user(username):
-    try:
-        res = UserMgr.delete_user(username)
-        if res["success"]:
-            return success_response(None, res["message"])
-        else:
-            return error_response(res["message"])
-
-    except AdminException as e:
-        return error_response(e.message, e.code)
-    except Exception as e:
-        return error_response(str(e), 500)
-
-
-@admin_bp.route('/users/<username>/password', methods=['PUT'])
-@login_required
-@check_admin_auth
-def change_password(username):
-    try:
-        data = request.get_json()
-        if not data or 'new_password' not in data:
-            return error_response("New password is required", 400)
-
-        new_password = data['new_password']
-        msg = UserMgr.update_user_password(username, new_password)
-        return success_response(None, msg)
-
-    except AdminException as e:
-        return error_response(e.message, e.code)
-    except Exception as e:
-        return error_response(str(e), 500)
-
-
-@admin_bp.route('/users/<username>/activate', methods=['PUT'])
-@login_required
-@check_admin_auth
-def alter_user_activate_status(username):
-    try:
-        data = request.get_json()
-        if not data or 'activate_status' not in data:
-            return error_response("Activation status is required", 400)
-        activate_status = data['activate_status']
-        msg = UserMgr.update_user_activate_status(username, activate_status)
-        return success_response(None, msg)
-    except AdminException as e:
-        return error_response(e.message, e.code)
-    except Exception as e:
-        return error_response(str(e), 500)
-
-
-@admin_bp.route('/users/<username>', methods=['GET'])
-@login_required
-@check_admin_auth
-def get_user_details(username):
-    try:
-        user_details = UserMgr.get_user_details(username)
-        return success_response(user_details)
-
-    except AdminException as e:
-        return error_response(e.message, e.code)
-    except Exception as e:
-        return error_response(str(e), 500)
-
-
-@admin_bp.route('/users/<username>/datasets', methods=['GET'])
-@login_required
-@check_admin_auth
-def get_user_datasets(username):
-    try:
-        datasets_list = UserServiceMgr.get_user_datasets(username)
-        return success_response(datasets_list)
-
-    except AdminException as e:
-        return error_response(e.message, e.code)
-    except Exception as e:
-        return error_response(str(e), 500)
-
-
-@admin_bp.route('/users/<username>/agents', methods=['GET'])
-@login_required
-@check_admin_auth
-def get_user_agents(username):
-    try:
-        agents_list = UserServiceMgr.get_user_agents(username)
-        return success_response(agents_list)
-
-    except AdminException as e:
-        return error_response(e.message, e.code)
-    except Exception as e:
-        return error_response(str(e), 500)
-
-
-@admin_bp.route('/services', methods=['GET'])
-@login_required
-@check_admin_auth
-def get_services():
-    try:
-        services = ServiceMgr.get_all_services()
-        return success_response(services, "Get all services", 0)
-    except Exception as e:
-        return error_response(str(e), 500)
-
-
-@admin_bp.route('/service_types/<service_type>', methods=['GET'])
-@login_required
-@check_admin_auth
-def get_services_by_type(service_type_str):
-    try:
-        services = ServiceMgr.get_services_by_type(service_type_str)
-        return success_response(services)
-    except Exception as e:
-        return error_response(str(e), 500)
-
-
-@admin_bp.route('/services/<service_id>', methods=['GET'])
-@login_required
-@check_admin_auth
-def get_service(service_id):
-    try:
-        services = ServiceMgr.get_service_details(service_id)
-        return success_response(services)
-    except Exception as e:
-        return error_response(str(e), 500)
-
-
-@admin_bp.route('/services/<service_id>', methods=['DELETE'])
-@login_required
-@check_admin_auth
-def shutdown_service(service_id):
-    try:
-        services = ServiceMgr.shutdown_service(service_id)
-        return success_response(services)
-    except Exception as e:
-        return error_response(str(e), 500)
-
-
-@admin_bp.route('/services/<service_id>', methods=['PUT'])
-@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/services.py

@@ -1,20 +1,3 @@
-#
-#  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 re
 from werkzeug.security import check_password_hash
 from api.db import ActiveEnum
@@ -24,25 +7,16 @@ from api.db.services.canvas_service import UserCanvasService
 from api.db.services.user_service import TenantService
 from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.utils.crypt import decrypt
-from api.utils import health_utils
-
-from api.common.exceptions import AdminException, UserAlreadyExistsError, UserNotFoundError
+from exceptions import AdminException, UserAlreadyExistsError, UserNotFoundError
 from config import SERVICE_CONFIGS
 
-
 class UserMgr:
     @staticmethod
     def get_all_users():
         users = UserService.get_all_users()
         result = []
         for user in users:
-            result.append({
-                'email': user.email,
-                'nickname': user.nickname,
-                'create_date': user.create_date,
-                'is_active': user.is_active,
-                'is_superuser': user.is_superuser,
-            })
+            result.append({'email': user.email, 'nickname': user.nickname, 'create_date': user.create_date, 'is_active': user.is_active})
         return result
 
     @staticmethod
@@ -55,6 +29,7 @@ class UserMgr:
                 '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,
@@ -135,7 +110,6 @@ class UserMgr:
         UserService.update_user(usr.id, {"is_active": target_status})
         return f"Turn {_activate_status} user activate status successfully!"
 
-
 class UserServiceMgr:
 
     @staticmethod
@@ -170,27 +144,18 @@ class UserServiceMgr:
         return [{
             'title': r['title'],
             'permission': r['permission'],
-            'canvas_category': r['canvas_category'].split('_')[0]
+            'canvas_type': r['canvas_type'],
+            'canvas_category': r['canvas_category']
         } for r in res]
 
-
 class ServiceMgr:
 
     @staticmethod
     def get_all_services():
         result = []
         configs = SERVICE_CONFIGS.configs
-        for service_id, config in enumerate(configs):
-            config_dict = config.to_dict()
-            try:
-                service_detail = ServiceMgr.get_service_details(service_id)
-                if "status" in service_detail:
-                    config_dict['status'] = service_detail['status']
-                else:
-                    config_dict['status'] = 'timeout'
-            except Exception:
-                config_dict['status'] = 'timeout'
-            result.append(config_dict)
+        for config in configs:
+            result.append(config.to_dict())
         return result
 
     @staticmethod
@@ -199,22 +164,7 @@ class ServiceMgr:
 
     @staticmethod
     def get_service_details(service_id: int):
-        service_id = int(service_id)
-        configs = SERVICE_CONFIGS.configs
-        service_config_mapping = {
-            c.id: {
-                'name': c.name,
-                'detail_func_name': c.detail_func_name
-            } for c in configs
-        }
-        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()
-        res.update({'service_name': service_info.get('name')})
-        return res
+        raise AdminException("get_service_details: not implemented")
 
     @staticmethod
     def shutdown_service(service_id: int):

agent/canvas.py

@@ -203,6 +203,7 @@ class Canvas(Graph):
             self.history = []
             self.retrieval = []
             self.memory = []
+
         for k in self.globals.keys():
             if isinstance(self.globals[k], str):
                 self.globals[k] = ""
@@ -291,6 +292,7 @@ class Canvas(Graph):
                     "thoughts": self.get_component_thoughts(self.path[i])
                 })
             _run_batch(idx, to)
+
             # post processing of components invocation
             for i in range(idx, to):
                 cpn = self.get_component(self.path[i])
@@ -391,6 +393,7 @@ class Canvas(Graph):
                 self.path = path
                 yield decorate("user_inputs", {"inputs": another_inputs, "tips": tips})
                 return
+
         self.path = self.path[:idx]
         if not self.error:
             yield decorate("workflow_finished",

agent/component/agent_with_tools.py

@@ -346,11 +346,3 @@ Respond immediately with your final comprehensive answer.
 
         return "Error occurred."
 
-    def reset(self, temp=False):
-        """
-        Reset all tools if they have a reset method. This avoids errors for tools like MCPToolCallSession.
-        """
-        for k, cpn in self.tools.items():
-            if hasattr(cpn, "reset") and callable(cpn.reset):
-                cpn.reset()
-

agent/component/invoke.py

@@ -19,12 +19,11 @@ import os
 import re
 import time
 from abc import ABC
-
 import requests
 
-from agent.component.base import ComponentBase, ComponentParamBase
 from api.utils.api_utils import timeout
 from deepdoc.parser import HtmlParser
+from agent.component.base import ComponentBase, ComponentParamBase
 
 
 class InvokeParam(ComponentParamBase):
@@ -44,11 +43,11 @@ class InvokeParam(ComponentParamBase):
         self.datatype = "json"  # New parameter to determine data posting type
 
     def check(self):
-        self.check_valid_value(self.method.lower(), "Type of content from the crawler", ["get", "post", "put"])
+        self.check_valid_value(self.method.lower(), "Type of content from the crawler", ['get', 'post', 'put'])
         self.check_empty(self.url, "End point URL")
         self.check_positive_integer(self.timeout, "Timeout time in second")
         self.check_boolean(self.clean_html, "Clean HTML")
-        self.check_valid_value(self.datatype.lower(), "Data post type", ["json", "formdata"])  # Check for valid datapost value
+        self.check_valid_value(self.datatype.lower(), "Data post type", ['json', 'formdata'])  # Check for valid datapost value
 
 
 class Invoke(ComponentBase, ABC):
@@ -64,18 +63,6 @@ class Invoke(ComponentBase, ABC):
                 args[para["key"]] = self._canvas.get_variable_value(para["ref"])
 
         url = self._param.url.strip()
-
-        def replace_variable(match):
-            var_name = match.group(1)
-            try:
-                value = self._canvas.get_variable_value(var_name)
-                return str(value or "")
-            except Exception:
-                return ""
-
-        # {base_url} or {component_id@variable_name}
-        url = re.sub(r"\{([a-zA-Z_][a-zA-Z0-9_.@-]*)\}", replace_variable, url)
-
         if url.find("http") != 0:
             url = "http://" + url
 
@@ -88,32 +75,52 @@ class Invoke(ComponentBase, ABC):
             proxies = {"http": self._param.proxy, "https": self._param.proxy}
 
         last_e = ""
-        for _ in range(self._param.max_retries + 1):
+        for _ in range(self._param.max_retries+1):
             try:
-                if method == "get":
-                    response = requests.get(url=url, params=args, headers=headers, proxies=proxies, timeout=self._param.timeout)
+                if method == 'get':
+                    response = requests.get(url=url,
+                                            params=args,
+                                            headers=headers,
+                                            proxies=proxies,
+                                            timeout=self._param.timeout)
                     if self._param.clean_html:
                         sections = HtmlParser()(None, response.content)
                         self.set_output("result", "\n".join(sections))
                     else:
                         self.set_output("result", response.text)
 
-                if method == "put":
-                    if self._param.datatype.lower() == "json":
-                        response = requests.put(url=url, json=args, headers=headers, proxies=proxies, timeout=self._param.timeout)
+                if method == 'put':
+                    if self._param.datatype.lower() == 'json':
+                        response = requests.put(url=url,
+                                                json=args,
+                                                headers=headers,
+                                                proxies=proxies,
+                                                timeout=self._param.timeout)
                     else:
-                        response = requests.put(url=url, data=args, headers=headers, proxies=proxies, timeout=self._param.timeout)
+                        response = requests.put(url=url,
+                                                data=args,
+                                                headers=headers,
+                                                proxies=proxies,
+                                                timeout=self._param.timeout)
                     if self._param.clean_html:
                         sections = HtmlParser()(None, response.content)
                         self.set_output("result", "\n".join(sections))
                     else:
                         self.set_output("result", response.text)
 
-                if method == "post":
-                    if self._param.datatype.lower() == "json":
-                        response = requests.post(url=url, json=args, headers=headers, proxies=proxies, timeout=self._param.timeout)
+                if method == 'post':
+                    if self._param.datatype.lower() == 'json':
+                        response = requests.post(url=url,
+                                                 json=args,
+                                                 headers=headers,
+                                                 proxies=proxies,
+                                                 timeout=self._param.timeout)
                     else:
-                        response = requests.post(url=url, data=args, headers=headers, proxies=proxies, timeout=self._param.timeout)
+                        response = requests.post(url=url,
+                                                 data=args,
+                                                 headers=headers,
+                                                 proxies=proxies,
+                                                 timeout=self._param.timeout)
                     if self._param.clean_html:
                         self.set_output("result", "\n".join(sections))
                     else:

agent/tools/code_exec.py

@@ -156,8 +156,8 @@ class CodeExec(ToolBase, ABC):
             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)))
-            logging.info(f"http://{settings.SANDBOX_HOST}:9385/run,  code_req: {code_req}, resp.status_code {resp.status_code}:")
+            resp = requests.post(url=f"http://{settings.SANDBOX_HOST}:9385/run", json=code_req, timeout=os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60))
+            logging.info(f"http://{settings.SANDBOX_HOST}:9385/run", code_req, resp.status_code)
             if resp.status_code != 200:
                 resp.raise_for_status()
             body = resp.json()

agent/tools/exesql.py

@@ -53,13 +53,12 @@ class ExeSQLParam(ToolParamBase):
         self.max_records = 1024
 
     def check(self):
-        self.check_valid_value(self.db_type, "Choose DB type", ['mysql', 'postgres', 'mariadb', 'mssql', 'IBM DB2', 'trino'])
+        self.check_valid_value(self.db_type, "Choose DB type", ['mysql', 'postgres', 'mariadb', 'mssql', 'IBM DB2'])
         self.check_empty(self.database, "Database name")
         self.check_empty(self.username, "database username")
         self.check_empty(self.host, "IP Address")
         self.check_positive_integer(self.port, "IP Port")
-        if self.db_type != "trino":
-            self.check_empty(self.password, "Database password")
+        self.check_empty(self.password, "Database password")
         self.check_positive_integer(self.max_records, "Maximum number of records")
         if self.database == "rag_flow":
             if self.host == "ragflow-mysql":
@@ -124,45 +123,6 @@ class ExeSQL(ToolBase, ABC):
                     r'PWD=' + self._param.password
             )
             db = pyodbc.connect(conn_str)
-        elif self._param.db_type == 'trino':
-            try:
-                import trino
-                from trino.auth import BasicAuthentication
-            except Exception:
-                raise Exception("Missing dependency 'trino'. Please install: pip install trino")
-
-            def _parse_catalog_schema(db: str):
-                if not db:
-                    return None, None
-                if "." in db:
-                    c, s = db.split(".", 1)
-                elif "/" in db:
-                    c, s = db.split("/", 1)
-                else:
-                    c, s = db, "default"
-                return c, s
-
-            catalog, schema = _parse_catalog_schema(self._param.database)
-            if not catalog:
-                raise Exception("For Trino, `database` must be 'catalog.schema' or at least 'catalog'.")
-
-            http_scheme = "https" if os.environ.get("TRINO_USE_TLS", "0") == "1" else "http"
-            auth = None
-            if http_scheme == "https" and self._param.password:
-                auth = BasicAuthentication(self._param.username, self._param.password)
-
-            try:
-                db = trino.dbapi.connect(
-                    host=self._param.host,
-                    port=int(self._param.port or 8080),
-                    user=self._param.username or "ragflow",
-                    catalog=catalog,
-                    schema=schema or "default",
-                    http_scheme=http_scheme,
-                    auth=auth
-                )
-            except Exception as e:
-                raise Exception("Database Connection Failed! \n" + str(e))
         elif self._param.db_type == 'IBM DB2':
             import ibm_db
             conn_str = (

agent/tools/pubmed.py

@@ -85,7 +85,13 @@ class PubMed(ToolBase, ABC):
                 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),)
+                                      get_content=lambda child: child.find("MedlineCitation") \
+                                                                    .find("Article") \
+                                                                    .find("Abstract") \
+                                                                    .find("AbstractText").text \
+                                                                    if child.find("MedlineCitation")\
+                                                                            .find("Article").find("Abstract")  \
+                                                                    else "No abstract available")
                 return self.output("formalized_content")
             except Exception as e:
                 last_e = e
@@ -98,50 +104,5 @@ class PubMed(ToolBase, ABC):
 
         assert False, self.output()
 
-    def _format_pubmed_content(self, child):
-        """Extract structured reference info from PubMed XML"""
-        def safe_find(path):
-            node = child
-            for p in path.split("/"):
-                if node is None:
-                    return None
-                node = node.find(p)
-            return node.text if node is not None and node.text else None
-
-        title = safe_find("MedlineCitation/Article/ArticleTitle") or "No title"
-        abstract = safe_find("MedlineCitation/Article/Abstract/AbstractText") or "No abstract available"
-        journal = safe_find("MedlineCitation/Article/Journal/Title") or "Unknown Journal"
-        volume = safe_find("MedlineCitation/Article/Journal/JournalIssue/Volume") or "-"
-        issue = safe_find("MedlineCitation/Article/Journal/JournalIssue/Issue") or "-"
-        pages = safe_find("MedlineCitation/Article/Pagination/MedlinePgn") or "-"
-
-        # Authors
-        authors = []
-        for author in child.findall(".//AuthorList/Author"):
-            lastname = safe_find("LastName") or ""
-            forename = safe_find("ForeName") or ""
-            fullname = f"{forename} {lastname}".strip()
-            if fullname:
-                authors.append(fullname)
-        authors_str = ", ".join(authors) if authors else "Unknown Authors"
-
-        # DOI
-        doi = None
-        for eid in child.findall(".//ArticleId"):
-            if eid.attrib.get("IdType") == "doi":
-                doi = eid.text
-                break
-
-        return (
-            f"Title: {title}\n"
-            f"Authors: {authors_str}\n"
-            f"Journal: {journal}\n"
-            f"Volume: {volume}\n"
-            f"Issue: {issue}\n"
-            f"Pages: {pages}\n"
-            f"DOI: {doi or '-'}\n"
-            f"Abstract: {abstract.strip()}"
-        )
-
     def thoughts(self) -> str:
         return "Looking for scholarly papers on `{}`,” prioritising reputable sources.".format(self.get_input().get("query", "-_-!"))

agent/tools/retrieval.py

@@ -18,14 +18,12 @@ import re
 from abc import ABC
 from agent.tools.base import ToolParamBase, ToolBase, ToolMeta
 from api.db 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 api.utils.api_utils import timeout
 from rag.app.tag import label_question
-from rag.prompts.generator import cross_languages, kb_prompt, gen_meta_filter
+from rag.prompts.generator import cross_languages, kb_prompt
 
 
 class RetrievalParam(ToolParamBase):
@@ -59,8 +57,6 @@ class RetrievalParam(ToolParamBase):
         self.empty_response = ""
         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")
@@ -120,27 +116,12 @@ 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 = gen_meta_filter(chat_mdl, metas, query)
-                doc_ids.extend(meta_filter(metas, filters))
-                if not doc_ids:
-                    doc_ids = None
-            elif self._param.meta_data_filter.get("method") == "manual":
-                doc_ids.extend(meta_filter(metas, self._param.meta_data_filter["manual"]))
-                if not doc_ids:
-                    doc_ids = None
-
         if self._param.cross_languages:
             query = cross_languages(kbs[0].tenant_id, None, query, self._param.cross_languages)
 
         if kbs:
             query = re.sub(r"^user[:：\s]*", "", query, flags=re.IGNORECASE)
-            kbinfos = settings.retriever.retrieval(
+            kbinfos = settings.retrievaler.retrieval(
                 query,
                 embd_mdl,
                 [kb.tenant_id for kb in kbs],
@@ -149,18 +130,12 @@ 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._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 cks:
-                    kbinfos["chunks"] = cks
             if self._param.use_kg:
-                ck = settings.kg_retriever.retrieval(query,
+                ck = settings.kg_retrievaler.retrieval(query,
                                                        [kb.tenant_id for kb in kbs],
                                                        kb_ids,
                                                        embd_mdl,
@@ -171,7 +146,7 @@ class Retrieval(ToolBase, ABC):
             kbinfos = {"chunks": [], "doc_aggs": []}
 
         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))
+            ck = settings.kg_retrievaler.retrieval(query, [kb.tenant_id for kb in kbs], filtered_kb_ids, embd_mdl, LLMBundle(kbs[0].tenant_id, LLMType.CHAT))
             if ck["content_with_weight"]:
                 ck["content"] = ck["content_with_weight"]
                 del ck["content_with_weight"]

agent/tools/searxng.py

@@ -85,7 +85,7 @@ class SearXNG(ToolBase, ABC):
             self.set_output("formalized_content", "")
             return ""
 
-        searxng_url = (getattr(self._param, "searxng_url", "") or kwargs.get("searxng_url") or "").strip()
+        searxng_url = (kwargs.get("searxng_url") or getattr(self._param, "searxng_url", "") or "").strip()
         # In try-run, if no URL configured, just return empty instead of raising
         if not searxng_url:
             self.set_output("formalized_content", "")

api/apps/api_app.py

@@ -33,7 +33,7 @@ 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
+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
 
@@ -41,7 +41,6 @@ from api.utils.file_utils import filename_type, thumbnail
 from rag.app.tag import label_question
 from rag.prompts.generator import keyword_extraction
 from rag.utils.storage_factory import STORAGE_IMPL
-from common.time_utils import current_timestamp, datetime_format
 
 from api.db.services.canvas_service import UserCanvasService
 from agent.canvas import Canvas
@@ -537,7 +536,7 @@ def list_chunks():
             )
         kb_ids = KnowledgebaseService.get_kb_ids(tenant_id)
 
-        res = settings.retriever.chunk_list(doc_id, tenant_id, kb_ids)
+        res = settings.retrievaler.chunk_list(doc_id, tenant_id, kb_ids)
         res = [
             {
                 "content": res_item["content_with_weight"],
@@ -885,7 +884,7 @@ def retrieval():
         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,
+        ranks = settings.retrievaler.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))

api/apps/canvas_app.py

@@ -51,7 +51,7 @@ from rag.utils.redis_conn import REDIS_CONN
 @manager.route('/templates', methods=['GET'])  # noqa: F821
 @login_required
 def templates():
-    return get_json_result(data=[c.to_dict() for c in CanvasTemplateService.get_all()])
+    return get_json_result(data=[c.to_dict() for c in CanvasTemplateService.query(canvas_category=CanvasCategory.Agent)])
 
 
 @manager.route('/rm', methods=['POST'])  # noqa: F821
@@ -409,49 +409,6 @@ def test_db_connect():
             ibm_db.fetch_assoc(stmt)
             ibm_db.close(conn)
             return get_json_result(data="Database Connection Successful!")
-        elif req["db_type"] == 'trino':
-            def _parse_catalog_schema(db: str):
-                if not db:
-                    return None, None
-                if "." in db:
-                    c, s = db.split(".", 1)
-                elif "/" in db:
-                    c, s = db.split("/", 1)
-                else:
-                    c, s = db, "default"
-                return c, s
-            try:
-                import trino
-                import os
-                from trino.auth import BasicAuthentication
-            except Exception:
-                return server_error_response("Missing dependency 'trino'. Please install: pip install trino")
-
-            catalog, schema = _parse_catalog_schema(req["database"])
-            if not catalog:
-                return server_error_response("For Trino, 'database' must be 'catalog.schema' or at least 'catalog'.")
-            
-            http_scheme = "https" if os.environ.get("TRINO_USE_TLS", "0") == "1" else "http"
-
-            auth = None
-            if http_scheme == "https" and req.get("password"):
-                auth = BasicAuthentication(req.get("username") or "ragflow", req["password"])
-
-            conn = trino.dbapi.connect(
-                host=req["host"],
-                port=int(req["port"] or 8080),
-                user=req["username"] or "ragflow",
-                catalog=catalog,
-                schema=schema or "default",
-                http_scheme=http_scheme,
-                auth=auth
-            )
-            cur = conn.cursor()
-            cur.execute("SELECT 1")
-            cur.fetchall()
-            cur.close()
-            conn.close()
-            return get_json_result(data="Database Connection Successful!")
         else:
             return server_error_response("Unsupported database type.")
         if req["db_type"] != 'mssql':

api/apps/chunk_app.py

@@ -35,7 +35,7 @@ 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
 
 
 @manager.route('/list', methods=['POST'])  # noqa: F821
@@ -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=["content_ltks"])
+        sres = settings.retrievaler.search(query, search.index_name(tenant_id), kb_ids, highlight=True)
         res = {"total": sres.total, "chunks": [], "doc": doc.to_dict()}
         for id in sres.ids:
             d = {
                 "chunk_id": id,
-                "content_with_weight": remove_redundant_spaces(sres.highlight[id]) if question and id in sres.highlight else sres.field[
+                "content_with_weight": rmSpace(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"],
@@ -346,16 +346,15 @@ def retrieval_test():
             question += keyword_extraction(chat_mdl, question)
 
         labels = label_question(question, [kb])
-        ranks = settings.retriever.retrieval(question, embd_mdl, tenant_ids, kb_ids, page, size,
+        ranks = settings.retrievaler.retrieval(question, embd_mdl, tenant_ids, kb_ids, page, size,
                                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", False),
+                               doc_ids, rerank_mdl=rerank_mdl, highlight=req.get("highlight"),
                                rank_feature=labels
                                )
         if use_kg:
-            ck = settings.kg_retriever.retrieval(question,
+            ck = settings.kg_retrievaler.retrieval(question,
                                                    tenant_ids,
                                                    kb_ids,
                                                    embd_mdl,
@@ -385,7 +384,7 @@ def knowledge_graph():
         "doc_ids": [doc_id],
         "knowledge_graph_kwd": ["graph", "mind_map"]
     }
-    sres = settings.retriever.search(req, search.index_name(tenant_id), kb_ids)
+    sres = settings.retrievaler.search(req, search.index_name(tenant_id), kb_ids)
     obj = {"graph": {}, "mind_map": {}}
     for id in sres.ids[:2]:
         ty = sres.field[id]["knowledge_graph_kwd"]

api/apps/document_app.py

@@ -24,7 +24,6 @@ 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.db_models import File, Task
@@ -45,7 +44,7 @@ from api.utils.api_utils import (
 from api.utils.file_utils import filename_type, get_project_base_directory, thumbnail
 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, rag_tokenizer
+from rag.nlp import search
 from rag.utils.storage_factory import STORAGE_IMPL
 
 
@@ -69,10 +68,8 @@ def upload():
     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)
-
     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)
 
@@ -97,8 +94,6 @@ def web_crawl():
     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)
 
     blob = html2pdf(url)
     if not blob:
@@ -524,21 +519,6 @@ 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)
@@ -572,8 +552,8 @@ def get(doc_id):
 @login_required
 @validate_request("doc_id")
 def change_parser():
-
     req = 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)
 
@@ -583,7 +563,7 @@ def change_parser():
 
     def reset_doc():
         nonlocal doc
-        e = DocumentService.update_by_id(doc.id, {"pipeline_id": req["pipeline_id"], "parser_id": req["parser_id"], "progress": 0, "progress_msg": "", "run": TaskStatus.UNSTART.value})
+        e = DocumentService.update_by_id(doc.id, {"parser_id": req["parser_id"], "progress": 0, "progress_msg": "", "run": TaskStatus.UNSTART.value})
         if not e:
             return get_data_error_result(message="Document not found!")
         if doc.token_num > 0:
@@ -597,7 +577,7 @@ def change_parser():
                 settings.docStoreConn.delete({"doc_id": doc.id}, search.index_name(tenant_id), doc.kb_id)
 
     try:
-        if "pipeline_id" in req and req["pipeline_id"] != "":
+        if "pipeline_id" in req:
             if doc.pipeline_id == req["pipeline_id"]:
                 return get_json_result(data=True)
             DocumentService.update_by_id(doc.id, {"pipeline_id": req["pipeline_id"]})

api/apps/file_app.py

@@ -13,7 +13,6 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License
 #
-import logging
 import os
 import pathlib
 import re
@@ -22,7 +21,6 @@ import flask
 from flask import request
 from flask_login import login_required, current_user
 
-from api.common.check_team_permission import check_file_team_permission
 from api.db.services.document_service import DocumentService
 from api.db.services.file2document_service import File2DocumentService
 from api.utils.api_utils import server_error_response, get_data_error_result, validate_request
@@ -235,63 +233,54 @@ def get_all_parent_folders():
         return server_error_response(e)
 
 
-@manager.route("/rm", methods=["POST"])  # noqa: F821
+@manager.route('/rm', methods=['POST'])  # noqa: F821
 @login_required
 @validate_request("file_ids")
 def rm():
     req = request.json
     file_ids = req["file_ids"]
-
-    def _delete_single_file(file):
-        try:
-            if file.location:
-                STORAGE_IMPL.rm(file.parent_id, file.location)
-        except Exception:
-            logging.exception(f"Fail to remove object: {file.parent_id}/{file.location}")
-
-        informs = File2DocumentService.get_by_file_id(file.id)
-        for inform in informs:
-            doc_id = inform.document_id
-            e, doc = DocumentService.get_by_id(doc_id)
-            if e and doc:
-                tenant_id = DocumentService.get_tenant_id(doc_id)
-                if tenant_id:
-                    DocumentService.remove_document(doc, tenant_id)
-            File2DocumentService.delete_by_file_id(file.id)
-
-        FileService.delete(file)
-
-    def _delete_folder_recursive(folder, tenant_id):
-        sub_files = FileService.list_all_files_by_parent_id(folder.id)
-        for sub_file in sub_files:
-            if sub_file.type == FileType.FOLDER.value:
-                _delete_folder_recursive(sub_file, tenant_id)
-            else:
-                _delete_single_file(sub_file)
-
-        FileService.delete(folder)
-
     try:
         for file_id in file_ids:
             e, file = FileService.get_by_id(file_id)
-            if not e or not file:
+            if not e:
                 return get_data_error_result(message="File or Folder not found!")
             if not file.tenant_id:
                 return get_data_error_result(message="Tenant not found!")
-            if not check_file_team_permission(file, current_user.id):
-                return get_json_result(data=False, message="No authorization.", code=settings.RetCode.AUTHENTICATION_ERROR)
-
+            if file.tenant_id != current_user.id:
+                return get_json_result(data=False, message='No authorization.', code=settings.RetCode.AUTHENTICATION_ERROR)
             if file.source_type == FileSource.KNOWLEDGEBASE:
                 continue
 
             if file.type == FileType.FOLDER.value:
-                _delete_folder_recursive(file, current_user.id)
-                continue
+                file_id_list = FileService.get_all_innermost_file_ids(file_id, [])
+                for inner_file_id in file_id_list:
+                    e, file = FileService.get_by_id(inner_file_id)
+                    if not e:
+                        return get_data_error_result(message="File not found!")
+                    STORAGE_IMPL.rm(file.parent_id, file.location)
+                FileService.delete_folder_by_pf_id(current_user.id, file_id)
+            else:
+                STORAGE_IMPL.rm(file.parent_id, file.location)
+                if not FileService.delete(file):
+                    return get_data_error_result(
+                        message="Database error (File removal)!")
 
-            _delete_single_file(file)
+            # delete file2document
+            informs = File2DocumentService.get_by_file_id(file_id)
+            for inform in informs:
+                doc_id = inform.document_id
+                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!")
+                if not DocumentService.remove_document(doc, tenant_id):
+                    return get_data_error_result(
+                        message="Database error (Document removal)!")
+            File2DocumentService.delete_by_file_id(file_id)
 
         return get_json_result(data=True)
-
     except Exception as e:
         return server_error_response(e)
 
@@ -305,7 +294,7 @@ def rename():
         e, file = FileService.get_by_id(req["file_id"])
         if not e:
             return get_data_error_result(message="File not found!")
-        if not check_file_team_permission(file, current_user.id):
+        if file.tenant_id != current_user.id:
             return get_json_result(data=False, message='No authorization.', code=settings.RetCode.AUTHENTICATION_ERROR)
         if file.type != FileType.FOLDER.value \
             and pathlib.Path(req["name"].lower()).suffix != pathlib.Path(
@@ -343,7 +332,7 @@ def get(file_id):
         e, file = FileService.get_by_id(file_id)
         if not e:
             return get_data_error_result(message="Document not found!")
-        if not check_file_team_permission(file, current_user.id):
+        if file.tenant_id != current_user.id:
             return get_json_result(data=False, message='No authorization.', code=settings.RetCode.AUTHENTICATION_ERROR)
 
         blob = STORAGE_IMPL.get(file.parent_id, file.location)
@@ -365,89 +354,31 @@ def get(file_id):
         return server_error_response(e)
 
 
-@manager.route("/mv", methods=["POST"])  # noqa: F821
+@manager.route('/mv', methods=['POST'])  # noqa: F821
 @login_required
 @validate_request("src_file_ids", "dest_file_id")
 def move():
     req = request.json
     try:
         file_ids = req["src_file_ids"]
-        dest_parent_id = req["dest_file_id"]
-
-        ok, dest_folder = FileService.get_by_id(dest_parent_id)
-        if not ok or not dest_folder:
-            return get_data_error_result(message="Parent Folder not found!")
-
+        parent_id = req["dest_file_id"]
         files = FileService.get_by_ids(file_ids)
-        if not files:
-            return get_data_error_result(message="Source files not found!")
-
-        files_dict = {f.id: f for f in files}
+        files_dict = {}
+        for file in files:
+            files_dict[file.id] = file
 
         for file_id in file_ids:
-            file = files_dict.get(file_id)
+            file = files_dict[file_id]
             if not file:
                 return get_data_error_result(message="File or Folder not found!")
             if not file.tenant_id:
                 return get_data_error_result(message="Tenant not found!")
-            if not check_file_team_permission(file, current_user.id):
-                return get_json_result(
-                    data=False,
-                    message="No authorization.",
-                    code=settings.RetCode.AUTHENTICATION_ERROR,
-                )
-
-        def _move_entry_recursive(source_file_entry, dest_folder):
-            if source_file_entry.type == FileType.FOLDER.value:
-                existing_folder = FileService.query(name=source_file_entry.name, parent_id=dest_folder.id)
-                if existing_folder:
-                    new_folder = existing_folder[0]
-                else:
-                    new_folder = FileService.insert(
-                        {
-                            "id": get_uuid(),
-                            "parent_id": dest_folder.id,
-                            "tenant_id": source_file_entry.tenant_id,
-                            "created_by": current_user.id,
-                            "name": source_file_entry.name,
-                            "location": "",
-                            "size": 0,
-                            "type": FileType.FOLDER.value,
-                        }
-                    )
-
-                sub_files = FileService.list_all_files_by_parent_id(source_file_entry.id)
-                for sub_file in sub_files:
-                    _move_entry_recursive(sub_file, new_folder)
-
-                FileService.delete_by_id(source_file_entry.id)
-                return
-
-            old_parent_id = source_file_entry.parent_id
-            old_location = source_file_entry.location
-            filename = source_file_entry.name
-
-            new_location = filename
-            while STORAGE_IMPL.obj_exist(dest_folder.id, new_location):
-                new_location += "_"
-
-            try:
-                STORAGE_IMPL.move(old_parent_id, old_location, dest_folder.id, new_location)
-            except Exception as storage_err:
-                raise RuntimeError(f"Move file failed at storage layer: {str(storage_err)}")
-
-            FileService.update_by_id(
-                source_file_entry.id,
-                {
-                    "parent_id": dest_folder.id,
-                    "location": new_location,
-                },
-            )
-
-        for file in files:
-            _move_entry_recursive(file, dest_folder)
-
+            if file.tenant_id != current_user.id:
+                return get_json_result(data=False, message='No authorization.', code=settings.RetCode.AUTHENTICATION_ERROR)
+        fe, _ = FileService.get_by_id(parent_id)
+        if not fe:
+            return get_data_error_result(message="Parent Folder not found!")
+        FileService.move_file(file_ids, parent_id)
         return get_json_result(data=True)
-
     except Exception as e:
         return server_error_response(e)

api/apps/kb_app.py

@@ -36,10 +36,8 @@ from api import settings
 from rag.nlp import search
 from api.constants import DATASET_NAME_LIMIT
 from rag.settings import PAGERANK_FLD
-from rag.utils.redis_conn import REDIS_CONN
 from rag.utils.storage_factory import STORAGE_IMPL
 
-
 @manager.route('/create', methods=['post'])  # noqa: F821
 @login_required
 @validate_request("name")
@@ -70,7 +68,6 @@ def create():
         e, t = TenantService.get_by_id(current_user.id)
         if not e:
             return get_data_error_result(message="Tenant not found.")
-
         req["parser_config"] = {
             "layout_recognize": "DeepDOC",
             "chunk_token_num": 512,
@@ -189,9 +186,6 @@ def detail():
             return get_data_error_result(
                 message="Can't find this knowledgebase!")
         kb["size"] = DocumentService.get_total_size_by_kb_id(kb_id=kb["id"],keywords="", run_status=[], types=[])
-        for key in ["graphrag_task_finish_at", "raptor_task_finish_at", "mindmap_task_finish_at"]:
-            if finish_at := kb.get(key):
-                kb[key] = finish_at.strftime("%Y-%m-%d %H:%M:%S")
         return get_json_result(data=kb)
     except Exception as e:
         return server_error_response(e)
@@ -287,7 +281,7 @@ def list_tags(kb_id):
     tenants = UserTenantService.get_tenants_by_user_id(current_user.id)
     tags = []
     for tenant in tenants:
-        tags += settings.retriever.all_tags(tenant["tenant_id"], [kb_id])
+        tags += settings.retrievaler.all_tags(tenant["tenant_id"], [kb_id])
     return get_json_result(data=tags)
 
 
@@ -306,7 +300,7 @@ def list_tags_from_kbs():
     tenants = UserTenantService.get_tenants_by_user_id(current_user.id)
     tags = []
     for tenant in tenants:
-        tags += settings.retriever.all_tags(tenant["tenant_id"], kb_ids)
+        tags += settings.retrievaler.all_tags(tenant["tenant_id"], kb_ids)
     return get_json_result(data=tags)
 
 
@@ -367,7 +361,7 @@ def knowledge_graph(kb_id):
     obj = {"graph": {}, "mind_map": {}}
     if not settings.docStoreConn.indexExist(search.index_name(kb.tenant_id), kb_id):
         return get_json_result(data=obj)
-    sres = settings.retriever.search(req, search.index_name(kb.tenant_id), [kb_id])
+    sres = settings.retrievaler.search(req, search.index_name(kb.tenant_id), [kb_id])
     if not len(sres.ids):
         return get_json_result(data=obj)
 
@@ -580,7 +574,7 @@ def run_graphrag():
     sample_document = documents[0]
     document_ids = [document["id"] for document in documents]
 
-    task_id = queue_raptor_o_graphrag_tasks(sample_doc_id=sample_document, ty="graphrag", priority=0, fake_doc_id=GRAPH_RAPTOR_FAKE_DOC_ID, doc_ids=list(document_ids))
+    task_id = queue_raptor_o_graphrag_tasks(doc=sample_document, ty="graphrag", priority=0, fake_doc_id=GRAPH_RAPTOR_FAKE_DOC_ID, doc_ids=list(document_ids))
 
     if not KnowledgebaseService.update_by_id(kb.id, {"graphrag_task_id": task_id}):
         logging.warning(f"Cannot save graphrag_task_id for kb {kb_id}")
@@ -649,7 +643,7 @@ def run_raptor():
     sample_document = documents[0]
     document_ids = [document["id"] for document in documents]
 
-    task_id = queue_raptor_o_graphrag_tasks(sample_doc_id=sample_document, ty="raptor", priority=0, fake_doc_id=GRAPH_RAPTOR_FAKE_DOC_ID, doc_ids=list(document_ids))
+    task_id = queue_raptor_o_graphrag_tasks(doc=sample_document, ty="raptor", priority=0, fake_doc_id=GRAPH_RAPTOR_FAKE_DOC_ID, doc_ids=list(document_ids))
 
     if not KnowledgebaseService.update_by_id(kb.id, {"raptor_task_id": task_id}):
         logging.warning(f"Cannot save raptor_task_id for kb {kb_id}")
@@ -718,7 +712,7 @@ def run_mindmap():
     sample_document = documents[0]
     document_ids = [document["id"] for document in documents]
 
-    task_id = queue_raptor_o_graphrag_tasks(sample_doc_id=sample_document, ty="mindmap", priority=0, fake_doc_id=GRAPH_RAPTOR_FAKE_DOC_ID, doc_ids=list(document_ids))
+    task_id = queue_raptor_o_graphrag_tasks(doc=sample_document, ty="mindmap", priority=0, fake_doc_id=GRAPH_RAPTOR_FAKE_DOC_ID, doc_ids=list(document_ids))
 
     if not KnowledgebaseService.update_by_id(kb.id, {"mindmap_task_id": task_id}):
         logging.warning(f"Cannot save mindmap_task_id for kb {kb_id}")
@@ -765,25 +759,18 @@ def delete_kb_task():
     match pipeline_task_type:
         case PipelineTaskType.GRAPH_RAG:
             settings.docStoreConn.delete({"knowledge_graph_kwd": ["graph", "subgraph", "entity", "relation"]}, search.index_name(kb.tenant_id), kb_id)
-            kb_task_id_field = "graphrag_task_id"
-            task_id = kb.graphrag_task_id
+            kb_task_id = "graphrag_task_id"
             kb_task_finish_at = "graphrag_task_finish_at"
         case PipelineTaskType.RAPTOR:
-            kb_task_id_field = "raptor_task_id"
-            task_id = kb.raptor_task_id
+            kb_task_id = "raptor_task_id"
             kb_task_finish_at = "raptor_task_finish_at"
         case PipelineTaskType.MINDMAP:
-            kb_task_id_field = "mindmap_task_id"
-            task_id = kb.mindmap_task_id
+            kb_task_id = "mindmap_task_id"
             kb_task_finish_at = "mindmap_task_finish_at"
         case _:
             return get_error_data_result(message="Internal Error: Invalid task type")
 
-    def cancel_task(task_id):
-        REDIS_CONN.set(f"{task_id}-cancel", "x")
-    cancel_task(task_id)
-
-    ok = KnowledgebaseService.update_by_id(kb_id, {kb_task_id_field: "", kb_task_finish_at: None})
+    ok = KnowledgebaseService.update_by_id(kb_id, {kb_task_id: "", kb_task_finish_at: None})
     if not ok:
         return server_error_response(f"Internal error: cannot delete task {pipeline_task_type}")
 

api/apps/llm_app.py

@@ -15,11 +15,11 @@
 #
 import logging
 import json
-import os
 from flask import request
 from flask_login import login_required, current_user
 from api.db.services.tenant_llm_service import LLMFactoriesService, TenantLLMService
 from api.db.services.llm_service import LLMService
+from api import settings
 from api.utils.api_utils import server_error_response, get_data_error_result, validate_request
 from api.db import StatusEnum, LLMType
 from api.db.db_models import TenantLLM
@@ -194,9 +194,6 @@ def add_llm():
     elif factory == "Azure-OpenAI":
         api_key = apikey_json(["api_key", "api_version"])
 
-    elif factory == "OpenRouter":
-        api_key = apikey_json(["api_key", "provider_order"])
-
     llm = {
         "tenant_id": current_user.id,
         "llm_factory": factory,
@@ -369,7 +366,7 @@ def my_llms():
 @login_required
 def list_app():
     self_deployed = ["Youdao", "FastEmbed", "BAAI", "Ollama", "Xinference", "LocalAI", "LM-Studio", "GPUStack"]
-    weighted = []
+    weighted = ["Youdao", "FastEmbed", "BAAI"] if settings.LIGHTEN != 0 else []
     model_type = request.args.get("model_type")
     try:
         objs = TenantLLMService.query(tenant_id=current_user.id)
@@ -379,8 +376,6 @@ def list_app():
                 for m in llms if m.status == StatusEnum.VALID.value and m.fid not in weighted]
         for m in llms:
             m["available"] = m["fid"] in facts or m["llm_name"].lower() == "flag-embedding" or m["fid"] in self_deployed
-            if "tei-" in os.getenv("COMPOSE_PROFILES", "") and m["model_type"]==LLMType.EMBEDDING and m["fid"]=="Builtin" and m["llm_name"]==os.getenv('TEI_MODEL', ''):
-                m["available"] = True
 
         llm_set = set([m["llm_name"] + "@" + m["fid"] for m in llms])
         for o in objs:

api/apps/plugin_app.py

@@ -1,26 +1,8 @@
-#
-#  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.
-#
-
-
 from flask import Response
 from flask_login import login_required
 from api.utils.api_utils import get_json_result
 from plugin import GlobalPluginManager
 
-
 @manager.route('/llm_tools', methods=['GET'])  # noqa: F821
 @login_required
 def llm_tools() -> Response:

api/apps/sdk/agent.py

@@ -25,7 +25,6 @@ from api.utils.api_utils import get_data_error_result, get_error_data_result, ge
 from api.utils.api_utils import get_result
 from flask import request
 
-
 @manager.route('/agents', methods=['GET'])  # noqa: F821
 @token_required
 def list_agents(tenant_id):
@@ -42,7 +41,7 @@ def list_agents(tenant_id):
         desc = False
     else:
         desc = True
-    canvas = UserCanvasService.get_list(tenant_id, page_number, items_per_page, orderby, desc, id, title)
+    canvas = UserCanvasService.get_list(tenant_id,page_number,items_per_page,orderby,desc,id,title)
     return get_result(data=canvas)
 
 
@@ -94,7 +93,7 @@ def update_agent(tenant_id: str, agent_id: str):
             req["dsl"] = json.dumps(req["dsl"], ensure_ascii=False)
 
         req["dsl"] = json.loads(req["dsl"])
-
+    
     if req.get("title") is not None:
         req["title"] = req["title"].strip()
 

api/apps/sdk/chat.py

@@ -169,8 +169,6 @@ def update(tenant_id, chat_id):
         if len(embd_count) > 1:
             return get_result(message='Datasets use different embedding models."', code=settings.RetCode.AUTHENTICATION_ERROR)
         req["kb_ids"] = ids
-    else:
-        req["kb_ids"] = []
     llm = req.get("llm")
     if llm:
         if "model_name" in llm:

api/apps/sdk/dataset.py

@@ -215,8 +215,7 @@ def delete(tenant_id):
                     continue
                 kb_id_instance_pairs.append((kb_id, kb))
             if len(error_kb_ids) > 0:
-                return get_error_permission_result(
-                    message=f"""User '{tenant_id}' lacks permission for datasets: '{", ".join(error_kb_ids)}'""")
+                return get_error_permission_result(message=f"""User '{tenant_id}' lacks permission for datasets: '{", ".join(error_kb_ids)}'""")
 
         errors = []
         success_count = 0
@@ -233,8 +232,7 @@ def delete(tenant_id):
                     ]
                 )
                 File2DocumentService.delete_by_document_id(doc.id)
-            FileService.filter_delete(
-                [File.source_type == FileSource.KNOWLEDGEBASE, File.type == "folder", File.name == kb.name])
+            FileService.filter_delete([File.source_type == FileSource.KNOWLEDGEBASE, File.type == "folder", File.name == kb.name])
             if not KnowledgebaseService.delete_by_id(kb_id):
                 errors.append(f"Delete dataset error for {kb_id}")
                 continue
@@ -331,8 +329,7 @@ def update(tenant_id, dataset_id):
     try:
         kb = KnowledgebaseService.get_or_none(id=dataset_id, tenant_id=tenant_id)
         if kb is None:
-            return get_error_permission_result(
-                message=f"User '{tenant_id}' lacks permission for dataset '{dataset_id}'")
+            return get_error_permission_result(message=f"User '{tenant_id}' lacks permission for dataset '{dataset_id}'")
 
         if req.get("parser_config"):
             req["parser_config"] = deep_merge(kb.parser_config, req["parser_config"])
@@ -344,8 +341,7 @@ def update(tenant_id, dataset_id):
             del req["parser_config"]
 
         if "name" in req and req["name"].lower() != kb.name.lower():
-            exists = KnowledgebaseService.get_or_none(name=req["name"], tenant_id=tenant_id,
-                                                      status=StatusEnum.VALID.value)
+            exists = KnowledgebaseService.get_or_none(name=req["name"], tenant_id=tenant_id, status=StatusEnum.VALID.value)
             if exists:
                 return get_error_data_result(message=f"Dataset name '{req['name']}' already exists")
 
@@ -353,8 +349,7 @@ def update(tenant_id, dataset_id):
             if not req["embd_id"]:
                 req["embd_id"] = kb.embd_id
             if kb.chunk_num != 0 and req["embd_id"] != kb.embd_id:
-                return get_error_data_result(
-                    message=f"When chunk_num ({kb.chunk_num}) > 0, embedding_model must remain {kb.embd_id}")
+                return get_error_data_result(message=f"When chunk_num ({kb.chunk_num}) > 0, embedding_model must remain {kb.embd_id}")
             ok, err = verify_embedding_availability(req["embd_id"], tenant_id)
             if not ok:
                 return err
@@ -364,12 +359,10 @@ def update(tenant_id, dataset_id):
                 return get_error_argument_result(message="'pagerank' can only be set when doc_engine is elasticsearch")
 
             if req["pagerank"] > 0:
-                settings.docStoreConn.update({"kb_id": kb.id}, {PAGERANK_FLD: req["pagerank"]},
-                                             search.index_name(kb.tenant_id), kb.id)
+                settings.docStoreConn.update({"kb_id": kb.id}, {PAGERANK_FLD: req["pagerank"]}, search.index_name(kb.tenant_id), kb.id)
             else:
                 # Elasticsearch requires PAGERANK_FLD be non-zero!
-                settings.docStoreConn.update({"exists": PAGERANK_FLD}, {"remove": PAGERANK_FLD},
-                                             search.index_name(kb.tenant_id), kb.id)
+                settings.docStoreConn.update({"exists": PAGERANK_FLD}, {"remove": PAGERANK_FLD}, search.index_name(kb.tenant_id), kb.id)
 
         if not KnowledgebaseService.update_by_id(kb.id, req):
             return get_error_data_result(message="Update dataset error.(Database error)")
@@ -461,7 +454,7 @@ def list_datasets(tenant_id):
                 return get_error_permission_result(message=f"User '{tenant_id}' lacks permission for dataset '{name}'")
 
         tenants = TenantService.get_joined_tenants_by_user_id(tenant_id)
-        kbs, total = KnowledgebaseService.get_list(
+        kbs = KnowledgebaseService.get_list(
             [m["tenant_id"] for m in tenants],
             tenant_id,
             args["page"],
@@ -475,15 +468,14 @@ def list_datasets(tenant_id):
         response_data_list = []
         for kb in kbs:
             response_data_list.append(remap_dictionary_keys(kb))
-        return get_result(data=response_data_list, total=total)
+        return get_result(data=response_data_list)
     except OperationalError as e:
         logging.exception(e)
         return get_error_data_result(message="Database operation failed")
 
-
 @manager.route('/datasets/<dataset_id>/knowledge_graph', methods=['GET'])  # noqa: F821
 @token_required
-def knowledge_graph(tenant_id, dataset_id):
+def knowledge_graph(tenant_id,dataset_id):
     if not KnowledgebaseService.accessible(dataset_id, tenant_id):
         return get_result(
             data=False,
@@ -499,7 +491,7 @@ def knowledge_graph(tenant_id, dataset_id):
     obj = {"graph": {}, "mind_map": {}}
     if not settings.docStoreConn.indexExist(search.index_name(kb.tenant_id), dataset_id):
         return get_result(data=obj)
-    sres = settings.retriever.search(req, search.index_name(kb.tenant_id), [dataset_id])
+    sres = settings.retrievaler.search(req, search.index_name(kb.tenant_id), [dataset_id])
     if not len(sres.ids):
         return get_result(data=obj)
 
@@ -515,16 +507,14 @@ def knowledge_graph(tenant_id, dataset_id):
     if "nodes" in obj["graph"]:
         obj["graph"]["nodes"] = sorted(obj["graph"]["nodes"], key=lambda x: x.get("pagerank", 0), reverse=True)[:256]
         if "edges" in obj["graph"]:
-            node_id_set = {o["id"] for o in obj["graph"]["nodes"]}
-            filtered_edges = [o for o in obj["graph"]["edges"] if
-                              o["source"] != o["target"] and o["source"] in node_id_set and o["target"] in node_id_set]
+            node_id_set = { o["id"] for o in obj["graph"]["nodes"] }
+            filtered_edges = [o for o in obj["graph"]["edges"] if o["source"] != o["target"] and o["source"] in node_id_set and o["target"] in node_id_set]
             obj["graph"]["edges"] = sorted(filtered_edges, key=lambda x: x.get("weight", 0), reverse=True)[:128]
     return get_result(data=obj)
 
-
 @manager.route('/datasets/<dataset_id>/knowledge_graph', methods=['DELETE'])  # noqa: F821
 @token_required
-def delete_knowledge_graph(tenant_id, dataset_id):
+def delete_knowledge_graph(tenant_id,dataset_id):
     if not KnowledgebaseService.accessible(dataset_id, tenant_id):
         return get_result(
             data=False,
@@ -532,7 +522,6 @@ def delete_knowledge_graph(tenant_id, dataset_id):
             code=settings.RetCode.AUTHENTICATION_ERROR
         )
     _, kb = KnowledgebaseService.get_by_id(dataset_id)
-    settings.docStoreConn.delete({"knowledge_graph_kwd": ["graph", "subgraph", "entity", "relation"]},
-                                 search.index_name(kb.tenant_id), dataset_id)
+    settings.docStoreConn.delete({"knowledge_graph_kwd": ["graph", "subgraph", "entity", "relation"]}, search.index_name(kb.tenant_id), dataset_id)
 
     return get_result(data=True)

api/apps/sdk/dify_retrieval.py

@@ -1,4 +1,4 @@
-#
+    #
 #  Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
 #
 #  Licensed under the Apache License, Version 2.0 (the "License");
@@ -31,89 +31,6 @@ from api.db.services.dialog_service import meta_filter, convert_conditions
 @apikey_required
 @validate_request("knowledge_id", "query")
 def retrieval(tenant_id):
-    """
-    Dify-compatible retrieval API
-    ---
-    tags:
-      - SDK
-    security:
-      - ApiKeyAuth: []
-    parameters:
-      - in: body
-        name: body
-        required: true
-        schema:
-          type: object
-          required:
-            - knowledge_id
-            - query
-          properties:
-            knowledge_id:
-              type: string
-              description: Knowledge base ID
-            query:
-              type: string
-              description: Query text
-            use_kg:
-              type: boolean
-              description: Whether to use knowledge graph
-              default: false
-            retrieval_setting:
-              type: object
-              description: Retrieval configuration
-              properties:
-                score_threshold:
-                  type: number
-                  description: Similarity threshold
-                  default: 0.0
-                top_k:
-                  type: integer
-                  description: Number of results to return
-                  default: 1024
-            metadata_condition:
-              type: object
-              description: Metadata filter condition
-              properties:
-                conditions:
-                  type: array
-                  items:
-                    type: object
-                    properties:
-                      name:
-                        type: string
-                        description: Field name
-                      comparison_operator:
-                        type: string
-                        description: Comparison operator
-                      value:
-                        type: string
-                        description: Field value
-    responses:
-      200:
-        description: Retrieval succeeded
-        schema:
-          type: object
-          properties:
-            records:
-              type: array
-              items:
-                type: object
-                properties:
-                  content:
-                    type: string
-                    description: Content text
-                  score:
-                    type: number
-                    description: Similarity score
-                  title:
-                    type: string
-                    description: Document title
-                  metadata:
-                    type: object
-                    description: Metadata info
-      404:
-        description: Knowledge base or document not found
-    """
     req = request.json
     question = req["query"]
     kb_id = req["knowledge_id"]
@@ -121,9 +38,9 @@ def retrieval(tenant_id):
     retrieval_setting = req.get("retrieval_setting", {})
     similarity_threshold = float(retrieval_setting.get("score_threshold", 0.0))
     top = int(retrieval_setting.get("top_k", 1024))
-    metadata_condition = req.get("metadata_condition", {})
+    metadata_condition = req.get("metadata_condition",{})
     metas = DocumentService.get_meta_by_kbs([kb_id])
-
+ 
     doc_ids = []
     try:
 
@@ -133,12 +50,12 @@ def retrieval(tenant_id):
 
         embd_mdl = LLMBundle(kb.tenant_id, LLMType.EMBEDDING.value, llm_name=kb.embd_id)
         print(metadata_condition)
-        # print("after", convert_conditions(metadata_condition))
+        print("after",convert_conditions(metadata_condition))
         doc_ids.extend(meta_filter(metas, convert_conditions(metadata_condition)))
-        # print("doc_ids", doc_ids)
+        print("doc_ids",doc_ids)
         if not doc_ids and metadata_condition is not None:
             doc_ids = ['-999']
-        ranks = settings.retriever.retrieval(
+        ranks = settings.retrievaler.retrieval(
             question,
             embd_mdl,
             kb.tenant_id,
@@ -153,17 +70,17 @@ def retrieval(tenant_id):
         )
 
         if use_kg:
-            ck = settings.kg_retriever.retrieval(question,
-                                                 [tenant_id],
-                                                 [kb_id],
-                                                 embd_mdl,
-                                                 LLMBundle(kb.tenant_id, LLMType.CHAT))
+            ck = settings.kg_retrievaler.retrieval(question,
+                                                   [tenant_id],
+                                                   [kb_id],
+                                                   embd_mdl,
+                                                   LLMBundle(kb.tenant_id, LLMType.CHAT))
             if ck["content_with_weight"]:
                 ranks["chunks"].insert(0, ck)
 
         records = []
         for c in ranks["chunks"]:
-            e, doc = DocumentService.get_by_id(c["doc_id"])
+            e, doc = DocumentService.get_by_id( c["doc_id"])
             c.pop("vector", None)
             meta = getattr(doc, 'meta_fields', {})
             meta["doc_id"] = c["doc_id"]
@@ -183,3 +100,5 @@ def retrieval(tenant_id):
             )
         logging.exception(e)
         return build_error_result(message=str(e), code=settings.RetCode.SERVER_ERROR)
+
+

api/apps/sdk/doc.py

@@ -41,8 +41,8 @@ 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 cross_languages, keyword_extraction
+from rag.utils import rmSpace
 from rag.utils.storage_factory import STORAGE_IMPL
-from common.string_utils import remove_redundant_spaces
 
 MAXIMUM_OF_UPLOADING_FILES = 256
 
@@ -458,7 +458,7 @@ def list_docs(dataset_id, tenant_id):
         required: false
         default: true
         description: Order in descending.
-      - in: query
+    - in: query
         name: create_time_from
         type: integer
         required: false
@@ -470,20 +470,6 @@ def list_docs(dataset_id, tenant_id):
         required: false
         default: 0
         description: Unix timestamp for filtering documents created before this time. 0 means no filter.
-      - in: query
-        name: suffix
-        type: array
-        items:
-          type: string
-        required: false
-        description: Filter by file suffix (e.g., ["pdf", "txt", "docx"]).
-      - in: query
-        name: run
-        type: array
-        items:
-          type: string
-        required: false
-        description: Filter by document run status. Supports both numeric ("0", "1", "2", "3", "4") and text formats ("UNSTART", "RUNNING", "CANCEL", "DONE", "FAIL").
       - in: header
         name: Authorization
         type: string
@@ -526,62 +512,63 @@ def list_docs(dataset_id, tenant_id):
                     description: Processing status.
     """
     if not KnowledgebaseService.accessible(kb_id=dataset_id, user_id=tenant_id):
-      return get_error_data_result(message=f"You don't own the dataset {dataset_id}. ")
+        return get_error_data_result(message=f"You don't own the dataset {dataset_id}. ")
+    id = request.args.get("id")
+    name = request.args.get("name")
 
-    q = request.args
-    document_id = q.get("id")  
-    name        = q.get("name")
-
-    if document_id and not DocumentService.query(id=document_id, kb_id=dataset_id):
-        return get_error_data_result(message=f"You don't own the document {document_id}.")
+    if id and not DocumentService.query(id=id, kb_id=dataset_id):
+        return get_error_data_result(message=f"You don't own the document {id}.")
     if name and not DocumentService.query(name=name, kb_id=dataset_id):
         return get_error_data_result(message=f"You don't own the document {name}.")
 
-    page        = int(q.get("page", 1))
-    page_size   = int(q.get("page_size", 30))  
-    orderby     = q.get("orderby", "create_time")
-    desc        = str(q.get("desc", "true")).strip().lower() != "false"
-    keywords    = q.get("keywords", "")
+    page = int(request.args.get("page", 1))
+    keywords = request.args.get("keywords", "")
+    page_size = int(request.args.get("page_size", 30))
+    orderby = request.args.get("orderby", "create_time")
+    if request.args.get("desc") == "False":
+        desc = False
+    else:
+        desc = True
+    docs, tol = DocumentService.get_list(dataset_id, page, page_size, orderby, desc, keywords, id, name)
 
-    # filters - align with OpenAPI parameter names
-    suffix               = q.getlist("suffix") 
-    run_status           = q.getlist("run")   
-    create_time_from     = int(q.get("create_time_from", 0))  
-    create_time_to       = int(q.get("create_time_to", 0))    
+    create_time_from = int(request.args.get("create_time_from", 0))
+    create_time_to = int(request.args.get("create_time_to", 0))
 
-    # map run status (accept text or numeric) - align with API parameter
-    run_status_text_to_numeric = {"UNSTART": "0", "RUNNING": "1", "CANCEL": "2", "DONE": "3", "FAIL": "4"}
-    run_status_converted = [run_status_text_to_numeric.get(v, v) for v in run_status]
-
-    docs, total = DocumentService.get_list(
-        dataset_id, page, page_size, orderby, desc, keywords, document_id, name, suffix, run_status_converted
-    )
-
-    # time range filter (0 means no bound)
     if create_time_from or create_time_to:
-        docs = [
-            d for d in docs
-            if (create_time_from == 0 or d.get("create_time", 0) >= create_time_from)
-            and (create_time_to == 0 or d.get("create_time", 0) <= create_time_to)
-        ]
+        filtered_docs = []
+        for doc in docs:
+            doc_create_time = doc.get("create_time", 0)
+            if (create_time_from == 0 or doc_create_time >= create_time_from) and (create_time_to == 0 or doc_create_time <= create_time_to):
+                filtered_docs.append(doc)
+        docs = filtered_docs
 
-    # rename keys + map run status back to text for output
+    # rename key's name
+    renamed_doc_list = []
     key_mapping = {
         "chunk_num": "chunk_count",
-        "kb_id": "dataset_id", 
+        "kb_id": "dataset_id",
         "token_num": "token_count",
         "parser_id": "chunk_method",
     }
-    run_status_numeric_to_text = {"0": "UNSTART", "1": "RUNNING", "2": "CANCEL", "3": "DONE", "4": "FAIL"}
+    run_mapping = {
+        "0": "UNSTART",
+        "1": "RUNNING",
+        "2": "CANCEL",
+        "3": "DONE",
+        "4": "FAIL",
+    }
+    for doc in docs:
+        renamed_doc = {}
+        for key, value in doc.items():
+            if key == "run":
+                renamed_doc["run"] = run_mapping.get(str(value))
+            new_key = key_mapping.get(key, key)
+            renamed_doc[new_key] = value
+            if key == "run":
+                renamed_doc["run"] = run_mapping.get(value)
+        renamed_doc_list.append(renamed_doc)
+    return get_result(data={"total": tol, "docs": renamed_doc_list})
 
-    output_docs = []
-    for d in docs:
-        renamed_doc = {key_mapping.get(k, k): v for k, v in d.items()}
-        if "run" in d:
-            renamed_doc["run"] = run_status_numeric_to_text.get(str(d["run"]), d["run"])
-        output_docs.append(renamed_doc)
-
-    return get_result(data={"total": total, "docs": output_docs})
 
 @manager.route("/datasets/<dataset_id>/documents", methods=["DELETE"])  # noqa: F821
 @token_required
@@ -995,12 +982,12 @@ def list_chunks(tenant_id, dataset_id, document_id):
         _ = Chunk(**final_chunk)
 
     elif settings.docStoreConn.indexExist(search.index_name(tenant_id), dataset_id):
-        sres = settings.retriever.search(query, search.index_name(tenant_id), [dataset_id], emb_mdl=None, highlight=True)
+        sres = settings.retrievaler.search(query, search.index_name(tenant_id), [dataset_id], emb_mdl=None, highlight=True)
         res["total"] = sres.total
         for id in sres.ids:
             d = {
                 "id": id,
-                "content": (remove_redundant_spaces(sres.highlight[id]) if question and id in sres.highlight else sres.field[id].get("content_with_weight", "")),
+                "content": (rmSpace(sres.highlight[id]) if question and id in sres.highlight else sres.field[id].get("content_with_weight", "")),
                 "document_id": sres.field[id]["doc_id"],
                 "docnm_kwd": sres.field[id]["docnm_kwd"],
                 "important_keywords": sres.field[id].get("important_kwd", []),
@@ -1459,7 +1446,7 @@ def retrieval_test(tenant_id):
             chat_mdl = LLMBundle(kb.tenant_id, LLMType.CHAT)
             question += keyword_extraction(chat_mdl, question)
 
-        ranks = settings.retriever.retrieval(
+        ranks = settings.retrievaler.retrieval(
             question,
             embd_mdl,
             tenant_ids,
@@ -1475,7 +1462,7 @@ def retrieval_test(tenant_id):
             rank_feature=label_question(question, kbs),
         )
         if use_kg:
-            ck = settings.kg_retriever.retrieval(question, [k.tenant_id for k in kbs], kb_ids, embd_mdl, LLMBundle(kb.tenant_id, LLMType.CHAT))
+            ck = settings.kg_retrievaler.retrieval(question, [k.tenant_id for k in kbs], kb_ids, embd_mdl, LLMBundle(kb.tenant_id, LLMType.CHAT))
             if ck["content_with_weight"]:
                 ranks["chunks"].insert(0, ck)
 

api/apps/sdk/files.py

@@ -1,20 +1,3 @@
-#
-#  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 pathlib
 import re
 
@@ -34,8 +17,7 @@ from api.utils.api_utils import get_json_result
 from api.utils.file_utils import filename_type
 from rag.utils.storage_factory import STORAGE_IMPL
 
-
-@manager.route('/file/upload', methods=['POST'])  # noqa: F821
+@manager.route('/file/upload', methods=['POST']) # noqa: F821
 @token_required
 def upload(tenant_id):
     """
@@ -62,22 +44,22 @@ def upload(tenant_id):
           type: object
           properties:
             data:
-              type: array
-              items:
-                type: object
-                properties:
-                  id:
-                    type: string
-                    description: File ID
-                  name:
-                    type: string
-                    description: File name
-                  size:
-                    type: integer
-                    description: File size in bytes
-                  type:
-                    type: string
-                    description: File type (e.g., document, folder)
+            type: array
+            items:
+              type: object
+              properties:
+                id:
+                  type: string
+                  description: File ID
+                name:
+                  type: string
+                  description: File name
+                size:
+                  type: integer
+                  description: File size in bytes
+                type:
+                  type: string
+                  description: File type (e.g., document, folder)
     """
     pf_id = request.form.get("parent_id")
 
@@ -115,14 +97,12 @@ def upload(tenant_id):
                 e, file = FileService.get_by_id(file_id_list[len_id_list - 1])
                 if not e:
                     return get_json_result(data=False, message="Folder not found!", code=404)
-                last_folder = FileService.create_folder(file, file_id_list[len_id_list - 1], file_obj_names,
-                                                        len_id_list)
+                last_folder = FileService.create_folder(file, file_id_list[len_id_list - 1], file_obj_names, len_id_list)
             else:
                 e, file = FileService.get_by_id(file_id_list[len_id_list - 2])
                 if not e:
                     return get_json_result(data=False, message="Folder not found!", code=404)
-                last_folder = FileService.create_folder(file, file_id_list[len_id_list - 2], file_obj_names,
-                                                        len_id_list)
+                last_folder = FileService.create_folder(file, file_id_list[len_id_list - 2], file_obj_names, len_id_list)
 
             filetype = filename_type(file_obj_names[file_len - 1])
             location = file_obj_names[file_len - 1]
@@ -149,7 +129,7 @@ def upload(tenant_id):
         return server_error_response(e)
 
 
-@manager.route('/file/create', methods=['POST'])  # noqa: F821
+@manager.route('/file/create', methods=['POST']) # noqa: F821
 @token_required
 def create(tenant_id):
     """
@@ -227,7 +207,7 @@ def create(tenant_id):
         return server_error_response(e)
 
 
-@manager.route('/file/list', methods=['GET'])  # noqa: F821
+@manager.route('/file/list', methods=['GET']) # noqa: F821
 @token_required
 def list_files(tenant_id):
     """
@@ -319,7 +299,7 @@ def list_files(tenant_id):
         return server_error_response(e)
 
 
-@manager.route('/file/root_folder', methods=['GET'])  # noqa: F821
+@manager.route('/file/root_folder', methods=['GET']) # noqa: F821
 @token_required
 def get_root_folder(tenant_id):
     """
@@ -355,7 +335,7 @@ def get_root_folder(tenant_id):
         return server_error_response(e)
 
 
-@manager.route('/file/parent_folder', methods=['GET'])  # noqa: F821
+@manager.route('/file/parent_folder', methods=['GET']) # noqa: F821
 @token_required
 def get_parent_folder():
     """
@@ -400,7 +380,7 @@ def get_parent_folder():
         return server_error_response(e)
 
 
-@manager.route('/file/all_parent_folder', methods=['GET'])  # noqa: F821
+@manager.route('/file/all_parent_folder', methods=['GET']) # noqa: F821
 @token_required
 def get_all_parent_folders(tenant_id):
     """
@@ -448,7 +428,7 @@ def get_all_parent_folders(tenant_id):
         return server_error_response(e)
 
 
-@manager.route('/file/rm', methods=['POST'])  # noqa: F821
+@manager.route('/file/rm', methods=['POST']) # noqa: F821
 @token_required
 def rm(tenant_id):
     """
@@ -522,7 +502,7 @@ def rm(tenant_id):
         return server_error_response(e)
 
 
-@manager.route('/file/rename', methods=['POST'])  # noqa: F821
+@manager.route('/file/rename', methods=['POST']) # noqa: F821
 @token_required
 def rename(tenant_id):
     """
@@ -562,8 +542,7 @@ def rename(tenant_id):
         if not e:
             return get_json_result(message="File not found!", code=404)
 
-        if file.type != FileType.FOLDER.value and pathlib.Path(req["name"].lower()).suffix != pathlib.Path(
-                file.name.lower()).suffix:
+        if file.type != FileType.FOLDER.value and pathlib.Path(req["name"].lower()).suffix != pathlib.Path(file.name.lower()).suffix:
             return get_json_result(data=False, message="The extension of file can't be changed", code=400)
 
         for existing_file in FileService.query(name=req["name"], pf_id=file.parent_id):
@@ -583,9 +562,9 @@ def rename(tenant_id):
         return server_error_response(e)
 
 
-@manager.route('/file/get/<file_id>', methods=['GET'])  # noqa: F821
+@manager.route('/file/get/<file_id>', methods=['GET']) # noqa: F821
 @token_required
-def get(tenant_id, file_id):
+def get(tenant_id,file_id):
     """
     Download a file.
     ---
@@ -631,7 +610,7 @@ def get(tenant_id, file_id):
         return server_error_response(e)
 
 
-@manager.route('/file/mv', methods=['POST'])  # noqa: F821
+@manager.route('/file/mv', methods=['POST']) # noqa: F821
 @token_required
 def move(tenant_id):
     """
@@ -690,7 +669,6 @@ def move(tenant_id):
     except Exception as e:
         return server_error_response(e)
 
-
 @manager.route('/file/convert', methods=['POST'])  # noqa: F821
 @token_required
 def convert(tenant_id):
@@ -757,4 +735,4 @@ def convert(tenant_id):
                     file2documents.append(file2document.to_json())
         return get_json_result(data=file2documents)
     except Exception as e:
-        return server_error_response(e)
+        return server_error_response(e)

api/apps/sdk/session.py

@@ -36,8 +36,7 @@ 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 import get_uuid
-from api.utils.api_utils import check_duplicate_ids, get_data_openai, get_error_data_result, get_json_result, \
-    get_result, server_error_response, token_required, validate_request
+from api.utils.api_utils import check_duplicate_ids, get_data_openai, get_error_data_result, get_json_result, get_result, server_error_response, token_required, validate_request
 from rag.app.tag import label_question
 from rag.prompts.template import load_prompt
 from rag.prompts.generator import cross_languages, gen_meta_filter, keyword_extraction, chunks_format
@@ -89,8 +88,7 @@ def create_agent_session(tenant_id, agent_id):
     canvas.reset()
 
     cvs.dsl = json.loads(str(canvas))
-    conv = {"id": session_id, "dialog_id": cvs.id, "user_id": user_id,
-            "message": [{"role": "assistant", "content": canvas.get_prologue()}], "source": "agent", "dsl": cvs.dsl}
+    conv = {"id": session_id, "dialog_id": cvs.id, "user_id": user_id, "message": [{"role": "assistant", "content": canvas.get_prologue()}], "source": "agent", "dsl": cvs.dsl}
     API4ConversationService.save(**conv)
     conv["agent_id"] = conv.pop("dialog_id")
     return get_result(data=conv)
@@ -281,7 +279,7 @@ def chat_completion_openai_like(tenant_id, chat_id):
                     reasoning_match = re.search(r"<think>(.*?)</think>", answer, flags=re.DOTALL)
                     if reasoning_match:
                         reasoning_part = reasoning_match.group(1)
-                        content_part = answer[reasoning_match.end():]
+                        content_part = answer[reasoning_match.end() :]
                     else:
                         reasoning_part = ""
                         content_part = answer
@@ -326,8 +324,7 @@ def chat_completion_openai_like(tenant_id, chat_id):
             response["choices"][0]["delta"]["content"] = None
             response["choices"][0]["delta"]["reasoning_content"] = None
             response["choices"][0]["finish_reason"] = "stop"
-            response["usage"] = {"prompt_tokens": len(prompt), "completion_tokens": token_used,
-                                 "total_tokens": len(prompt) + token_used}
+            response["usage"] = {"prompt_tokens": len(prompt), "completion_tokens": token_used, "total_tokens": len(prompt) + token_used}
             if need_reference:
                 response["choices"][0]["delta"]["reference"] = chunks_format(last_ans.get("reference", []))
                 response["choices"][0]["delta"]["final_content"] = last_ans.get("answer", "")
@@ -562,8 +559,7 @@ def list_agent_session(tenant_id, agent_id):
         desc = True
     # dsl defaults to True in all cases except for False and false
     include_dsl = request.args.get("dsl") != "False" and request.args.get("dsl") != "false"
-    total, convs = API4ConversationService.get_list(agent_id, tenant_id, page_number, items_per_page, orderby, desc, id,
-                                                    user_id, include_dsl)
+    total, convs = API4ConversationService.get_list(agent_id, tenant_id, page_number, items_per_page, orderby, desc, id, user_id, include_dsl)
     if not convs:
         return get_result(data=[])
     for conv in convs:
@@ -585,8 +581,7 @@ def list_agent_session(tenant_id, agent_id):
                 if message_num != 0 and messages[message_num]["role"] != "user":
                     chunk_list = []
                     # Add boundary and type checks to prevent KeyError
-                    if chunk_num < len(conv["reference"]) and conv["reference"][chunk_num] is not None and isinstance(
-                            conv["reference"][chunk_num], dict) and "chunks" in conv["reference"][chunk_num]:
+                    if chunk_num < len(conv["reference"]) and conv["reference"][chunk_num] is not None and isinstance(conv["reference"][chunk_num], dict) and "chunks" in conv["reference"][chunk_num]:
                         chunks = conv["reference"][chunk_num]["chunks"]
                         for chunk in chunks:
                             # Ensure chunk is a dictionary before calling get method
@@ -644,16 +639,13 @@ def delete(tenant_id, chat_id):
 
     if errors:
         if success_count > 0:
-            return get_result(data={"success_count": success_count, "errors": errors},
-                              message=f"Partially deleted {success_count} sessions with {len(errors)} errors")
+            return get_result(data={"success_count": success_count, "errors": errors}, message=f"Partially deleted {success_count} sessions with {len(errors)} errors")
         else:
             return get_error_data_result(message="; ".join(errors))
 
     if duplicate_messages:
         if success_count > 0:
-            return get_result(
-                message=f"Partially deleted {success_count} sessions with {len(duplicate_messages)} errors",
-                data={"success_count": success_count, "errors": duplicate_messages})
+            return get_result(message=f"Partially deleted {success_count} sessions with {len(duplicate_messages)} errors", data={"success_count": success_count, "errors": duplicate_messages})
         else:
             return get_error_data_result(message=";".join(duplicate_messages))
 
@@ -699,16 +691,13 @@ def delete_agent_session(tenant_id, agent_id):
 
     if errors:
         if success_count > 0:
-            return get_result(data={"success_count": success_count, "errors": errors},
-                              message=f"Partially deleted {success_count} sessions with {len(errors)} errors")
+            return get_result(data={"success_count": success_count, "errors": errors}, message=f"Partially deleted {success_count} sessions with {len(errors)} errors")
         else:
             return get_error_data_result(message="; ".join(errors))
 
     if duplicate_messages:
         if success_count > 0:
-            return get_result(
-                message=f"Partially deleted {success_count} sessions with {len(duplicate_messages)} errors",
-                data={"success_count": success_count, "errors": duplicate_messages})
+            return get_result(message=f"Partially deleted {success_count} sessions with {len(duplicate_messages)} errors", data={"success_count": success_count, "errors": duplicate_messages})
         else:
             return get_error_data_result(message=";".join(duplicate_messages))
 
@@ -741,9 +730,7 @@ def ask_about(tenant_id):
             for ans in ask(req["question"], req["kb_ids"], uid):
                 yield "data:" + json.dumps({"code": 0, "message": "", "data": ans}, ensure_ascii=False) + "\n\n"
         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": 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(stream(), mimetype="text/event-stream")
@@ -895,9 +882,7 @@ def begin_inputs(agent_id):
         return get_error_data_result(f"Can't find agent by ID: {agent_id}")
 
     canvas = Canvas(json.dumps(cvs.dsl), objs[0].tenant_id)
-    return get_result(
-        data={"title": cvs.title, "avatar": cvs.avatar, "inputs": canvas.get_component_input_form("begin"),
-              "prologue": canvas.get_prologue(), "mode": canvas.get_mode()})
+    return get_result(data={"title": cvs.title, "avatar": cvs.avatar, "inputs": canvas.get_component_input_form("begin"), "prologue": canvas.get_prologue(), "mode": canvas.get_mode()})
 
 
 @manager.route("/searchbots/ask", methods=["POST"])  # noqa: F821
@@ -926,9 +911,7 @@ def ask_about_embedded():
             for ans in ask(req["question"], req["kb_ids"], uid, search_config=search_config):
                 yield "data:" + json.dumps({"code": 0, "message": "", "data": ans}, ensure_ascii=False) + "\n\n"
         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": 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(stream(), mimetype="text/event-stream")
@@ -995,8 +978,7 @@ def retrieval_test_embedded():
                     tenant_ids.append(tenant.tenant_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=settings.RetCode.OPERATING_ERROR)
 
         e, kb = KnowledgebaseService.get_by_id(kb_ids[0])
         if not e:
@@ -1016,13 +998,11 @@ def retrieval_test_embedded():
             question += keyword_extraction(chat_mdl, question)
 
         labels = label_question(question, [kb])
-        ranks = settings.retriever.retrieval(
-            question, embd_mdl, tenant_ids, kb_ids, page, size, similarity_threshold, vector_similarity_weight, top,
-            doc_ids, rerank_mdl=rerank_mdl, highlight=req.get("highlight"), rank_feature=labels
+        ranks = settings.retrievaler.retrieval(
+            question, embd_mdl, tenant_ids, kb_ids, page, size, similarity_threshold, vector_similarity_weight, top, doc_ids, rerank_mdl=rerank_mdl, highlight=req.get("highlight"), rank_feature=labels
         )
         if use_kg:
-            ck = settings.kg_retriever.retrieval(question, tenant_ids, kb_ids, embd_mdl,
-                                                 LLMBundle(kb.tenant_id, LLMType.CHAT))
+            ck = settings.kg_retrievaler.retrieval(question, tenant_ids, kb_ids, embd_mdl, LLMBundle(kb.tenant_id, LLMType.CHAT))
             if ck["content_with_weight"]:
                 ranks["chunks"].insert(0, ck)
 
@@ -1033,8 +1013,7 @@ def retrieval_test_embedded():
         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 get_json_result(data=False, message="No chunk found! Check the chunk status please!", code=settings.RetCode.DATA_ERROR)
         return server_error_response(e)
 
 
@@ -1103,8 +1082,7 @@ def detail_share_embedded():
             if SearchService.query(tenant_id=tenant.tenant_id, id=search_id):
                 break
         else:
-            return get_json_result(data=False, message="Has no permission for this operation.",
-                                   code=settings.RetCode.OPERATING_ERROR)
+            return get_json_result(data=False, message="Has no permission for this operation.", code=settings.RetCode.OPERATING_ERROR)
 
         search = SearchService.get_detail(search_id)
         if not search:

api/apps/system_app.py

@@ -24,6 +24,7 @@ from api.db.services.api_service import APITokenService
 from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.db.services.user_service import UserTenantService
 from api import settings
+from api.utils import current_timestamp, datetime_format
 from api.utils.api_utils import (
     get_json_result,
     get_data_error_result,
@@ -31,7 +32,6 @@ from api.utils.api_utils import (
     generate_confirmation_token,
 )
 from api.versions import get_ragflow_version
-from common.time_utils import current_timestamp, datetime_format
 from rag.utils.storage_factory import STORAGE_IMPL, STORAGE_IMPL_TYPE
 from timeit import default_timer as timer
 
@@ -162,7 +162,7 @@ def status():
         task_executors = REDIS_CONN.smembers("TASKEXE")
         now = datetime.now().timestamp()
         for task_executor_id in task_executors:
-            heartbeats = REDIS_CONN.zrangebyscore(task_executor_id, now - 60 * 30, now)
+            heartbeats = REDIS_CONN.zrangebyscore(task_executor_id, now - 60*30, now)
             heartbeats = [json.loads(heartbeat) for heartbeat in heartbeats]
             task_executor_heartbeats[task_executor_id] = heartbeats
     except Exception:
@@ -178,11 +178,6 @@ def healthz():
     return jsonify(result), (200 if all_ok else 500)
 
 
-@manager.route("/ping", methods=["GET"]) # noqa: F821
-def ping():
-    return "pong", 200
-
-
 @manager.route("/new_token", methods=["POST"])  # noqa: F821
 @login_required
 def new_token():
@@ -274,8 +269,7 @@ def token_list():
         objs = [o.to_dict() for o in objs]
         for o in objs:
             if not o["beta"]:
-                o["beta"] = generate_confirmation_token(generate_confirmation_token(tenants[0].tenant_id)).replace(
-                    "ragflow-", "")[:32]
+                o["beta"] = generate_confirmation_token(generate_confirmation_token(tenants[0].tenant_id)).replace("ragflow-", "")[:32]
                 APITokenService.filter_update([APIToken.tenant_id == tenant_id, APIToken.token == o["token"]], o)
         return get_json_result(data=objs)
     except Exception as e:

api/apps/tenant_app.py

@@ -23,8 +23,7 @@ from api.db import UserTenantRole, StatusEnum
 from api.db.db_models import UserTenant
 from api.db.services.user_service import UserTenantService, UserService
 
-from api.utils import get_uuid
-from common.time_utils import delta_seconds
+from api.utils import get_uuid, delta_seconds
 from api.utils.api_utils import get_json_result, validate_request, server_error_response, get_data_error_result
 from api.utils.web_utils import send_invite_email
 
@@ -71,8 +70,7 @@ def create(tenant_id):
             return get_data_error_result(message=f"{invite_user_email} is already in the team.")
         if user_tenant_role == UserTenantRole.OWNER:
             return get_data_error_result(message=f"{invite_user_email} is the owner of the team.")
-        return get_data_error_result(
-            message=f"{invite_user_email} is in the team, but the role: {user_tenant_role} is invalid.")
+        return get_data_error_result(message=f"{invite_user_email} is in the team, but the role: {user_tenant_role} is invalid.")
 
     UserTenantService.save(
         id=get_uuid(),
@@ -134,8 +132,7 @@ def tenant_list():
 @login_required
 def agree(tenant_id):
     try:
-        UserTenantService.filter_update([UserTenant.tenant_id == tenant_id, UserTenant.user_id == current_user.id],
-                                        {"role": UserTenantRole.NORMAL})
+        UserTenantService.filter_update([UserTenant.tenant_id == tenant_id, UserTenant.user_id == current_user.id], {"role": UserTenantRole.NORMAL})
         return get_json_result(data=True)
     except Exception as e:
         return server_error_response(e)

api/apps/user_app.py

@@ -15,14 +15,11 @@
 #
 import json
 import logging
-import string
-import os
 import re
 import secrets
-import time
 from datetime import datetime
 
-from flask import redirect, request, session, make_response
+from flask import redirect, request, session
 from flask_login import current_user, login_required, login_user, logout_user
 from werkzeug.security import check_password_hash, generate_password_hash
 
@@ -34,8 +31,13 @@ from api.db.services.file_service import FileService
 from api.db.services.llm_service import get_init_tenant_llm
 from api.db.services.tenant_llm_service import TenantLLMService
 from api.db.services.user_service import TenantService, UserService, UserTenantService
-from common.time_utils import current_timestamp, datetime_format, get_format_time
-from api.utils import download_img, get_uuid
+from api.utils import (
+    current_timestamp,
+    datetime_format,
+    download_img,
+    get_format_time,
+    get_uuid,
+)
 from api.utils.api_utils import (
     construct_response,
     get_data_error_result,
@@ -44,19 +46,6 @@ from api.utils.api_utils import (
     validate_request,
 )
 from api.utils.crypt import decrypt
-from rag.utils.redis_conn import REDIS_CONN
-from api.apps import smtp_mail_server
-from api.utils.web_utils import (
-    send_email_html,
-    OTP_LENGTH,
-    OTP_TTL_SECONDS,
-    ATTEMPT_LIMIT,
-    ATTEMPT_LOCK_SECONDS,
-    RESEND_COOLDOWN_SECONDS,
-    otp_keys,
-    hash_code,
-    captcha_key,
-)
 
 
 @manager.route("/login", methods=["POST", "GET"])  # noqa: F821
@@ -836,172 +825,3 @@ def set_tenant_info():
         return get_json_result(data=True)
     except Exception as e:
         return server_error_response(e)
-        
-
-@manager.route("/forget/captcha", methods=["GET"])  # noqa: F821
-def forget_get_captcha():
-    """
-    GET /forget/captcha?email=<email>
-    - Generate an image captcha and cache it in Redis under key captcha:{email} with TTL = OTP_TTL_SECONDS.
-    - Returns the captcha as a PNG image.
-    """
-    email = (request.args.get("email") or "")
-    if not email:
-        return get_json_result(data=False, code=settings.RetCode.ARGUMENT_ERROR, message="email is required")
-
-    users = UserService.query(email=email)
-    if not users:
-        return get_json_result(data=False, code=settings.RetCode.DATA_ERROR, message="invalid email")
-
-    # Generate captcha text
-    allowed = string.ascii_uppercase + string.digits
-    captcha_text = "".join(secrets.choice(allowed) for _ in range(OTP_LENGTH))
-    REDIS_CONN.set(captcha_key(email), captcha_text, 60) # Valid for 60 seconds
-
-    from captcha.image import ImageCaptcha
-    image = ImageCaptcha(width=300, height=120, font_sizes=[50, 60, 70])
-    img_bytes = image.generate(captcha_text).read()
-    response = make_response(img_bytes)
-    response.headers.set("Content-Type", "image/JPEG")
-    return response
-
-
-@manager.route("/forget/otp", methods=["POST"])  # noqa: F821
-def forget_send_otp():
-    """
-    POST /forget/otp
-    - Verify the image captcha stored at captcha:{email} (case-insensitive).
-    - On success, generate an email OTP (A–Z with length = OTP_LENGTH), store hash + salt (and timestamp) in Redis with TTL, reset attempts and cooldown, and send the OTP via email.
-    """
-    req = request.get_json()
-    email = req.get("email") or ""
-    captcha = (req.get("captcha") or "").strip()
-
-    if not email or not captcha:
-        return get_json_result(data=False, code=settings.RetCode.ARGUMENT_ERROR, message="email and captcha required")
-
-    users = UserService.query(email=email)
-    if not users:
-        return get_json_result(data=False, code=settings.RetCode.DATA_ERROR, message="invalid email")
-
-    stored_captcha = REDIS_CONN.get(captcha_key(email))
-    if not stored_captcha:
-        return get_json_result(data=False, code=settings.RetCode.NOT_EFFECTIVE, message="invalid or expired captcha")
-    if (stored_captcha or "").strip().lower() != captcha.lower():
-        return get_json_result(data=False, code=settings.RetCode.AUTHENTICATION_ERROR, message="invalid or expired captcha")
-
-    # Delete captcha to prevent reuse
-    REDIS_CONN.delete(captcha_key(email))
-
-    k_code, k_attempts, k_last, k_lock = otp_keys(email)
-    now = int(time.time())
-    last_ts = REDIS_CONN.get(k_last)
-    if last_ts:
-        try:
-            elapsed = now - int(last_ts)
-        except Exception:
-            elapsed = RESEND_COOLDOWN_SECONDS
-        remaining = RESEND_COOLDOWN_SECONDS - elapsed
-        if remaining > 0:
-            return get_json_result(data=False, code=settings.RetCode.NOT_EFFECTIVE, message=f"you still have to wait {remaining} seconds")
-
-    # Generate OTP (uppercase letters only) and store hashed
-    otp = "".join(secrets.choice(string.ascii_uppercase) for _ in range(OTP_LENGTH))
-    salt = os.urandom(16)
-    code_hash = hash_code(otp, salt)
-    REDIS_CONN.set(k_code, f"{code_hash}:{salt.hex()}", OTP_TTL_SECONDS)
-    REDIS_CONN.set(k_attempts, 0, OTP_TTL_SECONDS)
-    REDIS_CONN.set(k_last, now, OTP_TTL_SECONDS)
-    REDIS_CONN.delete(k_lock)
-
-    ttl_min = OTP_TTL_SECONDS // 60
-
-    if not smtp_mail_server:
-        logging.warning("SMTP mail server not initialized; skip sending email.")
-    else:
-        try:
-            send_email_html(
-                subject="Your Password Reset Code",
-                to_email=email,
-                template_key="reset_code",
-                code=otp,
-                ttl_min=ttl_min,
-            )
-        except Exception:
-            return get_json_result(data=False, code=settings.RetCode.SERVER_ERROR, message="failed to send email")
-        
-    return get_json_result(data=True, code=settings.RetCode.SUCCESS, message="verification passed, email sent")
-
-
-@manager.route("/forget", methods=["POST"])  # noqa: F821
-def forget():
-    """
-    POST: Verify email + OTP and reset password, then log the user in.
-    Request JSON: { email, otp, new_password, confirm_new_password }
-    """
-    req = request.get_json()
-    email = req.get("email") or ""
-    otp = (req.get("otp") or "").strip()
-    new_pwd = req.get("new_password")
-    new_pwd2 = req.get("confirm_new_password")
-
-    if not all([email, otp, new_pwd, new_pwd2]):
-        return get_json_result(data=False, code=settings.RetCode.ARGUMENT_ERROR, message="email, otp and passwords are required")
-
-    # For reset, passwords are provided as-is (no decrypt needed)
-    if new_pwd != new_pwd2:
-        return get_json_result(data=False, code=settings.RetCode.ARGUMENT_ERROR, message="passwords do not match")
-
-    users = UserService.query(email=email)
-    if not users:
-        return get_json_result(data=False, code=settings.RetCode.DATA_ERROR, message="invalid email")
-
-    user = users[0]
-    # Verify OTP from Redis
-    k_code, k_attempts, k_last, k_lock = otp_keys(email)
-    if REDIS_CONN.get(k_lock):
-        return get_json_result(data=False, code=settings.RetCode.NOT_EFFECTIVE, message="too many attempts, try later")
-
-    stored = REDIS_CONN.get(k_code)
-    if not stored:
-        return get_json_result(data=False, code=settings.RetCode.NOT_EFFECTIVE, message="expired otp")
-
-    try:
-        stored_hash, salt_hex = str(stored).split(":", 1)
-        salt = bytes.fromhex(salt_hex)
-    except Exception:
-        return get_json_result(data=False, code=settings.RetCode.EXCEPTION_ERROR, message="otp storage corrupted")
-
-    # Case-insensitive verification: OTP generated uppercase
-    calc = hash_code(otp.upper(), salt)
-    if calc != stored_hash:
-        # bump attempts
-        try:
-            attempts = int(REDIS_CONN.get(k_attempts) or 0) + 1
-        except Exception:
-            attempts = 1
-        REDIS_CONN.set(k_attempts, attempts, OTP_TTL_SECONDS)
-        if attempts >= ATTEMPT_LIMIT:
-            REDIS_CONN.set(k_lock, int(time.time()), ATTEMPT_LOCK_SECONDS)
-        return get_json_result(data=False, code=settings.RetCode.AUTHENTICATION_ERROR, message="expired otp")
-
-    # Success: consume OTP and reset password
-    REDIS_CONN.delete(k_code)
-    REDIS_CONN.delete(k_attempts)
-    REDIS_CONN.delete(k_last)
-    REDIS_CONN.delete(k_lock)
-
-    try:
-        UserService.update_user_password(user.id, new_pwd)
-    except Exception as e:
-        logging.exception(e)
-        return get_json_result(data=False, code=settings.RetCode.EXCEPTION_ERROR, message="failed to reset password")
-
-    # Auto login (reuse login flow)
-    user.access_token = get_uuid()
-    login_user(user)
-    user.update_time = (current_timestamp(),)
-    user.update_date = (datetime_format(datetime.now()),)
-    user.save()
-    msg = "Password reset successful. Logged in."
-    return construct_response(data=user.to_json(), auth=user.get_id(), message=msg)

api/common/check_team_permission.py

@@ -1,59 +0,0 @@
-#
-#  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.
-#
-
-
-from api.db import TenantPermission
-from api.db.db_models import File, Knowledgebase
-from api.db.services.file_service import FileService
-from api.db.services.knowledgebase_service import KnowledgebaseService
-from api.db.services.user_service import TenantService
-
-
-def check_kb_team_permission(kb: dict | Knowledgebase, other: str) -> bool:
-    kb = kb.to_dict() if isinstance(kb, Knowledgebase) else kb
-
-    kb_tenant_id = kb["tenant_id"]
-
-    if kb_tenant_id == other:
-        return True
-
-    if kb["permission"] != TenantPermission.TEAM:
-        return False
-
-    joined_tenants = TenantService.get_joined_tenants_by_user_id(other)
-    return any(tenant["tenant_id"] == kb_tenant_id for tenant in joined_tenants)
-
-
-def check_file_team_permission(file: dict | File, other: str) -> bool:
-    file = file.to_dict() if isinstance(file, File) else file
-
-    file_tenant_id = file["tenant_id"]
-    if file_tenant_id == other:
-        return True
-
-    file_id = file["id"]
-
-    kb_ids = [kb_info["kb_id"] for kb_info in FileService.get_kb_id_by_file_id(file_id)]
-
-    for kb_id in kb_ids:
-        ok, kb = KnowledgebaseService.get_by_id(kb_id)
-        if not ok:
-            continue
-
-        if check_kb_team_permission(kb, other):
-            return True
-
-    return False

api/common/exceptions.py

@@ -1,43 +0,0 @@
-#
-#  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.
-#
-
-
-class AdminException(Exception):
-    def __init__(self, message, code=400):
-        super().__init__(message)
-        self.type = "admin"
-        self.code = code
-        self.message = message
-
-
-class UserNotFoundError(AdminException):
-    def __init__(self, username):
-        super().__init__(f"User '{username}' not found", 404)
-
-
-class UserAlreadyExistsError(AdminException):
-    def __init__(self, username):
-        super().__init__(f"User '{username}' already exists", 409)
-
-
-class CannotDeleteAdminError(AdminException):
-    def __init__(self):
-        super().__init__("Cannot delete admin account", 403)
-
-
-class NotAdminError(AdminException):
-    def __init__(self, username):
-        super().__init__(f"User '{username}' is not admin", 403)

api/db/db_models.py

@@ -35,8 +35,6 @@ from api.db import ParserType, SerializedType
 from api.utils.json import json_dumps, json_loads
 from api.utils.configs import deserialize_b64, serialize_b64
 
-from common.time_utils import current_timestamp, timestamp_to_date, date_string_to_timestamp
-
 
 def singleton(cls, *args, **kw):
     instances = {}
@@ -191,7 +189,7 @@ class BaseModel(Model):
                         for i, v in enumerate(f_v):
                             if isinstance(v, str) and f_n in auto_date_timestamp_field():
                                 # time type: %Y-%m-%d %H:%M:%S
-                                f_v[i] = date_string_to_timestamp(v)
+                                f_v[i] = utils.date_string_to_timestamp(v)
                         lt_value = f_v[0]
                         gt_value = f_v[1]
                         if lt_value is not None and gt_value is not None:
@@ -220,9 +218,9 @@ class BaseModel(Model):
     @classmethod
     def insert(cls, __data=None, **insert):
         if isinstance(__data, dict) and __data:
-            __data[cls._meta.combined["create_time"]] = current_timestamp()
+            __data[cls._meta.combined["create_time"]] = utils.current_timestamp()
         if insert:
-            insert["create_time"] = current_timestamp()
+            insert["create_time"] = utils.current_timestamp()
 
         return super().insert(__data, **insert)
 
@@ -233,11 +231,11 @@ class BaseModel(Model):
         if not normalized:
             return {}
 
-        normalized[cls._meta.combined["update_time"]] = current_timestamp()
+        normalized[cls._meta.combined["update_time"]] = utils.current_timestamp()
 
         for f_n in AUTO_DATE_TIMESTAMP_FIELD_PREFIX:
             if {f"{f_n}_time", f"{f_n}_date"}.issubset(cls._meta.combined.keys()) and cls._meta.combined[f"{f_n}_time"] in normalized and normalized[cls._meta.combined[f"{f_n}_time"]] is not None:
-                normalized[cls._meta.combined[f"{f_n}_date"]] = timestamp_to_date(normalized[cls._meta.combined[f"{f_n}_time"]])
+                normalized[cls._meta.combined[f"{f_n}_date"]] = utils.timestamp_to_date(normalized[cls._meta.combined[f"{f_n}_time"]])
 
         return normalized
 
@@ -315,75 +313,9 @@ class RetryingPooledMySQLDatabase(PooledMySQLDatabase):
                     raise
 
 
-class RetryingPooledPostgresqlDatabase(PooledPostgresqlDatabase):
-    def __init__(self, *args, **kwargs):
-        self.max_retries = kwargs.pop("max_retries", 5)
-        self.retry_delay = kwargs.pop("retry_delay", 1)
-        super().__init__(*args, **kwargs)
-
-    def execute_sql(self, sql, params=None, commit=True):
-        for attempt in range(self.max_retries + 1):
-            try:
-                return super().execute_sql(sql, params, commit)
-            except (OperationalError, InterfaceError) as e:
-                # PostgreSQL specific error codes
-                # 57P01: admin_shutdown
-                # 57P02: crash_shutdown
-                # 57P03: cannot_connect_now
-                # 08006: connection_failure
-                # 08003: connection_does_not_exist
-                # 08000: connection_exception
-                error_messages = ['connection', 'server closed', 'connection refused',
-                                'no connection to the server', 'terminating connection']
-
-                should_retry = any(msg in str(e).lower() for msg in error_messages)
-
-                if should_retry and attempt < self.max_retries:
-                    logging.warning(
-                        f"PostgreSQL connection issue (attempt {attempt+1}/{self.max_retries}): {e}"
-                    )
-                    self._handle_connection_loss()
-                    time.sleep(self.retry_delay * (2 ** attempt))
-                else:
-                    logging.error(f"PostgreSQL execution failure: {e}")
-                    raise
-        return None
-
-    def _handle_connection_loss(self):
-        try:
-            self.close()
-        except Exception:
-            pass
-        try:
-            self.connect()
-        except Exception as e:
-            logging.error(f"Failed to reconnect to PostgreSQL: {e}")
-            time.sleep(0.1)
-            self.connect()
-
-    def begin(self):
-        for attempt in range(self.max_retries + 1):
-            try:
-                return super().begin()
-            except (OperationalError, InterfaceError) as e:
-                error_messages = ['connection', 'server closed', 'connection refused',
-                                'no connection to the server', 'terminating connection']
-
-                should_retry = any(msg in str(e).lower() for msg in error_messages)
-
-                if should_retry and attempt < self.max_retries:
-                    logging.warning(
-                        f"PostgreSQL connection lost during transaction (attempt {attempt+1}/{self.max_retries})"
-                    )
-                    self._handle_connection_loss()
-                    time.sleep(self.retry_delay * (2 ** attempt))
-                else:
-                    raise
-
-
 class PooledDatabase(Enum):
     MYSQL = RetryingPooledMySQLDatabase
-    POSTGRES = RetryingPooledPostgresqlDatabase
+    POSTGRES = PooledPostgresqlDatabase
 
 
 class DatabaseMigrator(Enum):
@@ -396,7 +328,7 @@ class BaseDataBase:
     def __init__(self):
         database_config = settings.DATABASE.copy()
         db_name = database_config.pop("name")
-
+        
         pool_config = {
             'max_retries': 5,
             'retry_delay': 1,
@@ -709,7 +641,7 @@ class TenantLLM(DataBaseModel):
     llm_factory = CharField(max_length=128, null=False, help_text="LLM factory name", index=True)
     model_type = CharField(max_length=128, null=True, help_text="LLM, Text Embedding, Image2Text, ASR", index=True)
     llm_name = CharField(max_length=128, null=True, help_text="LLM name", default="", index=True)
-    api_key = TextField(null=True, help_text="API KEY")
+    api_key = CharField(max_length=2048, null=True, help_text="API KEY", index=True)
     api_base = CharField(max_length=255, null=True, help_text="API Base")
     max_tokens = IntegerField(default=8192, index=True)
     used_tokens = IntegerField(default=0, index=True)
@@ -1210,8 +1142,4 @@ def migrate_db():
         migrate(migrator.add_column("knowledgebase", "mindmap_task_finish_at", CharField(null=True)))
     except Exception:
         pass
-    try:
-        migrate(migrator.alter_column_type("tenant_llm", "api_key", TextField(null=True, help_text="API KEY")))
-    except Exception:
-        pass
     logging.disable(logging.NOTSET)

api/db/db_utils.py

@@ -18,7 +18,7 @@ from functools import reduce
 
 from playhouse.pool import PooledMySQLDatabase
 
-from common.time_utils import current_timestamp, timestamp_to_date
+from api.utils import current_timestamp, timestamp_to_date
 
 from api.db.db_models import DB, DataBaseModel
 

api/db/services/api_service.py

@@ -19,7 +19,7 @@ import peewee
 
 from api.db.db_models import DB, API4Conversation, APIToken, Dialog
 from api.db.services.common_service import CommonService
-from common.time_utils import current_timestamp, datetime_format
+from api.utils import current_timestamp, datetime_format
 
 
 class APITokenService(CommonService):

api/db/services/canvas_service.py

@@ -143,12 +143,15 @@ class UserCanvasService(CommonService):
         ]
         if keywords:
             agents = cls.model.select(*fields).join(User, on=(cls.model.user_id == User.id)).where(
-                (((cls.model.user_id.in_(joined_tenant_ids)) & (cls.model.permission == TenantPermission.TEAM.value)) | (cls.model.user_id == user_id)),
-                (fn.LOWER(cls.model.title).contains(keywords.lower()))
+                cls.model.user_id.in_(joined_tenant_ids),
+                fn.LOWER(cls.model.title).contains(keywords.lower())
+                #(((cls.model.user_id.in_(joined_tenant_ids)) & (cls.model.permission == TenantPermission.TEAM.value)) | (cls.model.user_id == user_id)),
+                #(fn.LOWER(cls.model.title).contains(keywords.lower()))
             )
         else:
             agents = cls.model.select(*fields).join(User, on=(cls.model.user_id == User.id)).where(
-                (((cls.model.user_id.in_(joined_tenant_ids)) & (cls.model.permission == TenantPermission.TEAM.value)) | (cls.model.user_id == user_id))
+                cls.model.user_id.in_(joined_tenant_ids)
+                #(((cls.model.user_id.in_(joined_tenant_ids)) & (cls.model.permission == TenantPermission.TEAM.value)) | (cls.model.user_id == user_id))
             )
         if canvas_category:
             agents = agents.where(cls.model.canvas_category == canvas_category)

api/db/services/common_service.py

@@ -19,8 +19,7 @@ import peewee
 from peewee import InterfaceError, OperationalError
 
 from api.db.db_models import DB
-from api.utils import get_uuid
-from common.time_utils import current_timestamp, datetime_format
+from api.utils import current_timestamp, datetime_format, get_uuid
 
 def retry_db_operation(func):
     @retry(

api/db/services/dialog_service.py

@@ -34,16 +34,15 @@ from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.db.services.langfuse_service import TenantLangfuseService
 from api.db.services.llm_service import LLMBundle
 from api.db.services.tenant_llm_service import TenantLLMService
-from common.time_utils import current_timestamp, datetime_format
+from api.utils import current_timestamp, datetime_format
 from graphrag.general.mind_map_extractor import MindMapExtractor
 from rag.app.resume import forbidden_select_fields4resume
 from rag.app.tag import label_question
 from rag.nlp.search import index_name
 from rag.prompts.generator import chunks_format, citation_prompt, cross_languages, full_question, kb_prompt, keyword_extraction, message_fit_in, \
     gen_meta_filter, PROMPT_JINJA_ENV, ASK_SUMMARY
-from rag.utils import num_tokens_from_string
+from rag.utils import num_tokens_from_string, rmSpace
 from rag.utils.tavily_conn import Tavily
-from common.string_utils import remove_redundant_spaces
 
 
 class DialogService(CommonService):
@@ -371,7 +370,7 @@ def chat(dialog, messages, stream=True, **kwargs):
         chat_mdl.bind_tools(toolcall_session, tools)
     bind_models_ts = timer()
 
-    retriever = settings.retriever
+    retriever = settings.retrievaler
     questions = [m["content"] for m in messages if m["role"] == "user"][-3:]
     attachments = kwargs["doc_ids"].split(",") if "doc_ids" in kwargs else []
     if "doc_ids" in messages[-1]:
@@ -467,17 +466,13 @@ def chat(dialog, messages, stream=True, **kwargs):
                     rerank_mdl=rerank_mdl,
                     rank_feature=label_question(" ".join(questions), kbs),
                 )
-                if prompt_config.get("toc_enhance"):
-                    cks = retriever.retrieval_by_toc(" ".join(questions), kbinfos["chunks"], tenant_ids, chat_mdl, dialog.top_n)
-                    if cks:
-                        kbinfos["chunks"] = cks
             if prompt_config.get("tavily_api_key"):
                 tav = Tavily(prompt_config["tavily_api_key"])
                 tav_res = tav.retrieve_chunks(" ".join(questions))
                 kbinfos["chunks"].extend(tav_res["chunks"])
                 kbinfos["doc_aggs"].extend(tav_res["doc_aggs"])
             if prompt_config.get("use_kg"):
-                ck = settings.kg_retriever.retrieval(" ".join(questions), tenant_ids, dialog.kb_ids, embd_mdl,
+                ck = settings.kg_retrievaler.retrieval(" ".join(questions), tenant_ids, dialog.kb_ids, embd_mdl,
                                                        LLMBundle(dialog.tenant_id, LLMType.CHAT))
                 if ck["content_with_weight"]:
                     kbinfos["chunks"].insert(0, ck)
@@ -663,7 +658,7 @@ Please write the SQL, only SQL, without any other explanations or text.
 
         logging.debug(f"{question} get SQL(refined): {sql}")
         tried_times += 1
-        return settings.retriever.sql_retrieval(sql, format="json"), sql
+        return settings.retrievaler.sql_retrieval(sql, format="json"), sql
 
     tbl, sql = get_table()
     if tbl is None:
@@ -707,7 +702,7 @@ Please write the SQL, only SQL, without any other explanations or text.
 
     line = "|" + "|".join(["------" for _ in range(len(column_idx))]) + ("|------|" if docid_idx and docid_idx else "")
 
-    rows = ["|" + "|".join([remove_redundant_spaces(str(r[i])) for i in column_idx]).replace("None", " ") + "|" for r in tbl["rows"]]
+    rows = ["|" + "|".join([rmSpace(str(r[i])) for i in column_idx]).replace("None", " ") + "|" for r in tbl["rows"]]
     rows = [r for r in rows if re.sub(r"[ |]+", "", r)]
     if quota:
         rows = "\n".join([r + f" ##{ii}$$ |" for ii, r in enumerate(rows)])
@@ -757,7 +752,7 @@ def ask(question, kb_ids, tenant_id, chat_llm_name=None, search_config={}):
     embedding_list = list(set([kb.embd_id for kb in kbs]))
 
     is_knowledge_graph = all([kb.parser_id == ParserType.KG for kb in kbs])
-    retriever = settings.retriever if not is_knowledge_graph else settings.kg_retriever
+    retriever = settings.retrievaler if not is_knowledge_graph else settings.kg_retrievaler
 
     embd_mdl = LLMBundle(tenant_id, LLMType.EMBEDDING, embedding_list[0])
     chat_mdl = LLMBundle(tenant_id, LLMType.CHAT, chat_llm_name)
@@ -853,7 +848,7 @@ def gen_mindmap(question, kb_ids, tenant_id, search_config={}):
             if not doc_ids:
                 doc_ids = None
 
-    ranks = settings.retriever.retrieval(
+    ranks = settings.retrievaler.retrieval(
         question=question,
         embd_mdl=embd_mdl,
         tenant_ids=tenant_ids,

api/db/services/document_service.py

@@ -34,8 +34,7 @@ from api.db.db_models import DB, Document, Knowledgebase, Task, Tenant, UserTena
 from api.db.db_utils import bulk_insert_into_db
 from api.db.services.common_service import CommonService
 from api.db.services.knowledgebase_service import KnowledgebaseService
-from api.utils import get_uuid
-from common.time_utils import current_timestamp, get_format_time
+from api.utils import current_timestamp, get_format_time, get_uuid
 from rag.nlp import rag_tokenizer, search
 from rag.settings import get_svr_queue_name, SVR_CONSUMER_GROUP_NAME
 from rag.utils.redis_conn import REDIS_CONN
@@ -80,7 +79,7 @@ class DocumentService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_list(cls, kb_id, page_number, items_per_page,
-                 orderby, desc, keywords, id, name, suffix=None, run = None):
+                 orderby, desc, keywords, id, name):
         fields = cls.get_cls_model_fields()
         docs = cls.model.select(*[*fields, UserCanvas.title]).join(File2Document, on = (File2Document.document_id == cls.model.id))\
             .join(File, on = (File.id == File2Document.file_id))\
@@ -97,10 +96,6 @@ class DocumentService(CommonService):
             docs = docs.where(
                 fn.LOWER(cls.model.name).contains(keywords.lower())
             )
-        if suffix:
-            docs = docs.where(cls.model.suffix.in_(suffix))
-        if run:
-            docs = docs.where(cls.model.run.in_(run))
         if desc:
             docs = docs.order_by(cls.model.getter_by(orderby).desc())
         else:
@@ -672,11 +667,9 @@ class DocumentService(CommonService):
     @classmethod
     @DB.connection_context()
     def _sync_progress(cls, docs:list[dict]):
-        from api.db.services.task_service import TaskService
-
         for d in docs:
             try:
-                tsks = TaskService.query(doc_id=d["id"], order_by=Task.create_time)
+                tsks = Task.query(doc_id=d["id"], order_by=Task.create_time)
                 if not tsks:
                     continue
                 msg = []
@@ -794,23 +787,21 @@ class DocumentService(CommonService):
             "cancelled": int(cancelled),
         }
 
-def queue_raptor_o_graphrag_tasks(sample_doc_id, ty, priority, fake_doc_id="", doc_ids=[]):
+def queue_raptor_o_graphrag_tasks(doc, ty, priority, fake_doc_id="", doc_ids=[]):
     """
     You can provide a fake_doc_id to bypass the restriction of tasks at the knowledgebase level.
     Optionally, specify a list of doc_ids to determine which documents participate in the task.
     """
-    assert ty in ["graphrag", "raptor", "mindmap"], "type should be graphrag, raptor or mindmap"
-
-    chunking_config = DocumentService.get_chunking_config(sample_doc_id["id"])
+    chunking_config = DocumentService.get_chunking_config(doc["id"])
     hasher = xxhash.xxh64()
     for field in sorted(chunking_config.keys()):
         hasher.update(str(chunking_config[field]).encode("utf-8"))
 
     def new_task():
-        nonlocal sample_doc_id
+        nonlocal doc
         return {
             "id": get_uuid(),
-            "doc_id": sample_doc_id["id"],
+            "doc_id": fake_doc_id if fake_doc_id else doc["id"],
             "from_page": 100000000,
             "to_page": 100000000,
             "task_type": ty,
@@ -825,9 +816,9 @@ def queue_raptor_o_graphrag_tasks(sample_doc_id, ty, priority, fake_doc_id="", d
     task["digest"] = hasher.hexdigest()
     bulk_insert_into_db(Task, [task], True)
 
-    task["doc_id"] = fake_doc_id
-    task["doc_ids"] = doc_ids
-    DocumentService.begin2parse(sample_doc_id["id"])
+    if ty in ["graphrag", "raptor", "mindmap"]:
+        task["doc_ids"] = doc_ids
+        DocumentService.begin2parse(doc["id"])
     assert REDIS_CONN.queue_product(get_svr_queue_name(priority), message=task), "Can't access Redis. Please check the Redis' status."
     return task["id"]
 

api/db/services/file2document_service.py

@@ -20,7 +20,7 @@ from api.db.db_models import DB
 from api.db.db_models import File, File2Document
 from api.db.services.common_service import CommonService
 from api.db.services.document_service import DocumentService
-from common.time_utils import current_timestamp, datetime_format
+from api.utils import current_timestamp, datetime_format
 
 
 class File2DocumentService(CommonService):

api/db/services/file_service.py

@@ -476,16 +476,6 @@ class FileService(CommonService):
 
         return err, files
 
-    @classmethod
-    @DB.connection_context()
-    def list_all_files_by_parent_id(cls, parent_id):
-        try:
-            files = cls.model.select().where((cls.model.parent_id == parent_id) & (cls.model.id != parent_id))
-            return list(files)
-        except Exception:
-            logging.exception("list_by_parent_id failed")
-            raise RuntimeError("Database error (list_by_parent_id)!")
-
     @staticmethod
     def parse_docs(file_objs, user_id):
         exe = ThreadPoolExecutor(max_workers=12)

api/db/services/knowledgebase_service.py

@@ -20,7 +20,7 @@ from peewee import fn, JOIN
 from api.db import StatusEnum, TenantPermission
 from api.db.db_models import DB, Document, Knowledgebase, User, UserTenant, UserCanvas
 from api.db.services.common_service import CommonService
-from common.time_utils import current_timestamp, datetime_format
+from api.utils import current_timestamp, datetime_format
 
 
 class KnowledgebaseService(CommonService):
@@ -379,7 +379,6 @@ class KnowledgebaseService(CommonService):
         #     name: Optional name filter
         # Returns:
         #     List of knowledge bases
-        #     Total count of knowledge bases
         kbs = cls.model.select()
         if id:
             kbs = kbs.where(cls.model.id == id)
@@ -391,16 +390,14 @@ class KnowledgebaseService(CommonService):
                 cls.model.tenant_id == user_id))
             & (cls.model.status == StatusEnum.VALID.value)
         )
-
         if desc:
             kbs = kbs.order_by(cls.model.getter_by(orderby).desc())
         else:
             kbs = kbs.order_by(cls.model.getter_by(orderby).asc())
 
-        total = kbs.count()
         kbs = kbs.paginate(page_number, items_per_page)
 
-        return list(kbs.dicts()), total
+        return list(kbs.dicts())
 
     @classmethod
     @DB.connection_context()

api/db/services/langfuse_service.py

@@ -20,7 +20,7 @@ import peewee
 
 from api.db.db_models import DB, TenantLangfuse
 from api.db.services.common_service import CommonService
-from common.time_utils import current_timestamp, datetime_format
+from api.utils import current_timestamp, datetime_format
 
 
 class TenantLangfuseService(CommonService):

api/db/services/llm_service.py

@@ -59,6 +59,21 @@ def get_init_tenant_llm(user_id):
                 }
             )
 
+    if settings.LIGHTEN != 1:
+        for buildin_embedding_model in settings.BUILTIN_EMBEDDING_MODELS:
+            mdlnm, fid = TenantLLMService.split_model_name_and_factory(buildin_embedding_model)
+            tenant_llm.append(
+                {
+                    "tenant_id": user_id,
+                    "llm_factory": fid,
+                    "llm_name": mdlnm,
+                    "model_type": "embedding",
+                    "api_key": "",
+                    "api_base": "",
+                    "max_tokens": 1024 if buildin_embedding_model == "BAAI/bge-large-zh-v1.5@BAAI" else 512,
+                }
+            )
+
     unique = {}
     for item in tenant_llm:
         key = (item["tenant_id"], item["llm_factory"], item["llm_name"])
@@ -190,31 +205,32 @@ class LLMBundle(LLM4Tenant):
             return txt
 
         return txt[last_think_end + len("</think>") :]
-
+    
     @staticmethod
     def _clean_param(chat_partial, **kwargs):
         func = chat_partial.func
         sig = inspect.signature(func)
+        keyword_args = []
         support_var_args = False
-        allowed_params = set()
-
         for param in sig.parameters.values():
-            if param.kind == inspect.Parameter.VAR_KEYWORD:
+            if param.kind == inspect.Parameter.VAR_KEYWORD or param.kind == inspect.Parameter.VAR_POSITIONAL:
                 support_var_args = True
-            elif param.kind in (inspect.Parameter.POSITIONAL_OR_KEYWORD, inspect.Parameter.KEYWORD_ONLY):
-                allowed_params.add(param.name)
-        if support_var_args:
-            return kwargs
-        else:
-            return {k: v for k, v in kwargs.items() if k in allowed_params}
+            elif param.kind == inspect.Parameter.KEYWORD_ONLY:
+                keyword_args.append(param.name)
+
+        use_kwargs = kwargs
+        if not support_var_args:
+            use_kwargs = {k: v for k, v in kwargs.items() if k in keyword_args}
+        return use_kwargs
+        
     def chat(self, system: str, history: list, gen_conf: dict = {}, **kwargs) -> str:
         if self.langfuse:
             generation = self.langfuse.start_generation(trace_context=self.trace_context, name="chat", model=self.llm_name, input={"system": system, "history": history})
 
-        chat_partial = partial(self.mdl.chat, system, history, gen_conf, **kwargs)
+        chat_partial = partial(self.mdl.chat, system, history, gen_conf)
         if self.is_tools and self.mdl.is_tools:
-            chat_partial = partial(self.mdl.chat_with_tools, system, history, gen_conf, **kwargs)
-
+            chat_partial = partial(self.mdl.chat_with_tools, system, history, gen_conf)
+            
         use_kwargs = self._clean_param(chat_partial, **kwargs)
         txt, used_tokens = chat_partial(**use_kwargs)
         txt = self._remove_reasoning_content(txt)
@@ -250,7 +266,7 @@ class LLMBundle(LLM4Tenant):
                 break
 
             if txt.endswith("</think>"):
-                ans = ans[: -len("</think>")]
+                ans = ans.rstrip("</think>")
 
             if not self.verbose_tool_use:
                 txt = re.sub(r"<tool_call>.*?</tool_call>", "", txt, flags=re.DOTALL)

api/db/services/mcp_server_service.py

@@ -33,8 +33,7 @@ class MCPServerService(CommonService):
 
     @classmethod
     @DB.connection_context()
-    def get_servers(cls, tenant_id: str, id_list: list[str] | None, page_number, items_per_page, orderby, desc,
-                    keywords):
+    def get_servers(cls, tenant_id: str, id_list: list[str] | None, page_number, items_per_page, orderby, desc, keywords):
         """Retrieve all MCP servers associated with a tenant.
 
         This method fetches all MCP servers for a given tenant, ordered by creation time.

api/db/services/pipeline_operation_log_service.py

@@ -27,8 +27,7 @@ from api.db.services.common_service import CommonService
 from api.db.services.document_service import DocumentService
 from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.db.services.task_service import GRAPH_RAPTOR_FAKE_DOC_ID
-from api.utils import get_uuid
-from common.time_utils import current_timestamp, datetime_format
+from api.utils import current_timestamp, datetime_format, get_uuid
 
 
 class PipelineOperationLogService(CommonService):

api/db/services/search_service.py

@@ -20,7 +20,7 @@ from peewee import fn
 from api.db import StatusEnum
 from api.db.db_models import DB, Search, User
 from api.db.services.common_service import CommonService
-from common.time_utils import current_timestamp, datetime_format
+from api.utils import current_timestamp, datetime_format
 
 
 class SearchService(CommonService):
@@ -94,8 +94,7 @@ class SearchService(CommonService):
         query = (
             cls.model.select(*fields)
             .join(User, on=(cls.model.tenant_id == User.id))
-            .where(((cls.model.tenant_id.in_(joined_tenant_ids)) | (cls.model.tenant_id == user_id)) & (
-                        cls.model.status == StatusEnum.VALID.value))
+            .where(((cls.model.tenant_id.in_(joined_tenant_ids)) | (cls.model.tenant_id == user_id)) & (cls.model.status == StatusEnum.VALID.value))
         )
 
         if keywords:

api/db/services/task_service.py

@@ -27,8 +27,7 @@ from api.db import StatusEnum, FileType, TaskStatus
 from api.db.db_models import Task, Document, Knowledgebase, Tenant
 from api.db.services.common_service import CommonService
 from api.db.services.document_service import DocumentService
-from api.utils import get_uuid
-from common.time_utils import current_timestamp
+from api.utils import current_timestamp, get_uuid
 from deepdoc.parser.excel_parser import RAGFlowExcelParser
 from rag.settings import get_svr_queue_name
 from rag.utils.storage_factory import STORAGE_IMPL
@@ -166,7 +165,7 @@ class TaskService(CommonService):
         ]
         tasks = (
             cls.model.select(*fields).order_by(cls.model.from_page.asc(), cls.model.create_time.desc())
-            .where(cls.model.doc_id == doc_id)
+                .where(cls.model.doc_id == doc_id)
         )
         tasks = list(tasks.dicts())
         if not tasks:
@@ -206,18 +205,18 @@ class TaskService(CommonService):
                 cls.model.select(
                     *[Document.id, Document.kb_id, Document.location, File.parent_id]
                 )
-                .join(Document, on=(cls.model.doc_id == Document.id))
-                .join(
+                    .join(Document, on=(cls.model.doc_id == Document.id))
+                    .join(
                     File2Document,
                     on=(File2Document.document_id == Document.id),
                     join_type=JOIN.LEFT_OUTER,
                 )
-                .join(
+                    .join(
                     File,
                     on=(File2Document.file_id == File.id),
                     join_type=JOIN.LEFT_OUTER,
                 )
-                .where(
+                    .where(
                     Document.status == StatusEnum.VALID.value,
                     Document.run == TaskStatus.RUNNING.value,
                     ~(Document.type == FileType.VIRTUAL.value),
@@ -295,8 +294,8 @@ class TaskService(CommonService):
                 cls.model.update(progress=prog).where(
                     (cls.model.id == id) &
                     (
-                            (cls.model.progress != -1) &
-                            ((prog == -1) | (prog > cls.model.progress))
+                        (cls.model.progress != -1) &
+                        ((prog == -1) | (prog > cls.model.progress))
                     )
                 ).execute()
         else:
@@ -344,7 +343,6 @@ def queue_tasks(doc: dict, bucket: str, name: str, priority: int):
         - Task digests are calculated for optimization and reuse
         - Previous task chunks may be reused if available
     """
-
     def new_task():
         return {
             "id": get_uuid(),
@@ -352,7 +350,7 @@ def queue_tasks(doc: dict, bucket: str, name: str, priority: int):
             "progress": 0.0,
             "from_page": 0,
             "to_page": 100000000,
-            "begin_at": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+            "begin_at": datetime.now(),
         }
 
     parse_task_array = []
@@ -504,7 +502,7 @@ def queue_dataflow(tenant_id:str, flow_id:str, task_id:str, doc_id:str=CANVAS_DE
         to_page=100000000,
         task_type="dataflow" if not rerun else "dataflow_rerun",
         priority=priority,
-        begin_at= datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+        begin_at=datetime.now(),
     )
     if doc_id not in [CANVAS_DEBUG_DOC_ID, GRAPH_RAPTOR_FAKE_DOC_ID]:
         TaskService.model.delete().where(TaskService.model.doc_id == doc_id).execute()
@@ -517,7 +515,7 @@ def queue_dataflow(tenant_id:str, flow_id:str, task_id:str, doc_id:str=CANVAS_DE
     task["file"] = file
 
     if not REDIS_CONN.queue_product(
-            get_svr_queue_name(priority), message=task
+        get_svr_queue_name(priority), message=task
     ):
         return False, "Can't access Redis. Please check the Redis' status."
 

api/db/services/tenant_llm_service.py

@@ -13,7 +13,6 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-import os
 import logging
 from langfuse import Langfuse
 from api import settings
@@ -58,10 +57,8 @@ class TenantLLMService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_my_llms(cls, tenant_id):
-        fields = [cls.model.llm_factory, LLMFactories.logo, LLMFactories.tags, cls.model.model_type, cls.model.llm_name,
-                  cls.model.used_tokens]
-        objs = cls.model.select(*fields).join(LLMFactories, on=(cls.model.llm_factory == LLMFactories.name)).where(
-            cls.model.tenant_id == tenant_id, ~cls.model.api_key.is_null()).dicts()
+        fields = [cls.model.llm_factory, LLMFactories.logo, LLMFactories.tags, cls.model.model_type, cls.model.llm_name, cls.model.used_tokens]
+        objs = cls.model.select(*fields).join(LLMFactories, on=(cls.model.llm_factory == LLMFactories.name)).where(cls.model.tenant_id == tenant_id, ~cls.model.api_key.is_null()).dicts()
 
         return list(objs)
 
@@ -113,17 +110,23 @@ class TenantLLMService(CommonService):
             model_config = cls.get_api_key(tenant_id, mdlnm)
         if model_config:
             model_config = model_config.to_dict()
-        elif llm_type == LLMType.EMBEDDING and fid == 'Builtin' and "tei-" in os.getenv("COMPOSE_PROFILES", "") and mdlnm == os.getenv('TEI_MODEL', ''):
-            embedding_cfg = settings.EMBEDDING_CFG
-            model_config = {"llm_factory": 'Builtin', "api_key": embedding_cfg["api_key"], "llm_name": mdlnm, "api_base": embedding_cfg["base_url"]}
-        else:
-            raise LookupError(f"Model({mdlnm}@{fid}) not authorized")
-
-        llm = LLMService.query(llm_name=mdlnm) if not fid else LLMService.query(llm_name=mdlnm, fid=fid)
-        if not llm and fid:  # for some cases seems fid mismatch
-            llm = LLMService.query(llm_name=mdlnm)
-        if llm:
-            model_config["is_tools"] = llm[0].is_tools
+            llm = LLMService.query(llm_name=mdlnm) if not fid else LLMService.query(llm_name=mdlnm, fid=fid)
+            if not llm and fid:  # for some cases seems fid mismatch
+                llm = LLMService.query(llm_name=mdlnm)
+            if llm:
+                model_config["is_tools"] = llm[0].is_tools
+        if not model_config:
+            if llm_type in [LLMType.EMBEDDING, LLMType.RERANK]:
+                llm = LLMService.query(llm_name=mdlnm) if not fid else LLMService.query(llm_name=mdlnm, fid=fid)
+                if llm and llm[0].fid in ["Youdao", "FastEmbed", "BAAI"]:
+                    model_config = {"llm_factory": llm[0].fid, "api_key": "", "llm_name": mdlnm, "api_base": ""}
+            if not model_config:
+                if mdlnm == "flag-embedding":
+                    model_config = {"llm_factory": "Tongyi-Qianwen", "api_key": "", "llm_name": llm_name, "api_base": ""}
+                else:
+                    if not mdlnm:
+                        raise LookupError(f"Type of {llm_type} model is not set.")
+                    raise LookupError("Model({}) not authorized".format(mdlnm))
         return model_config
 
     @classmethod
@@ -134,33 +137,27 @@ class TenantLLMService(CommonService):
         if llm_type == LLMType.EMBEDDING.value:
             if model_config["llm_factory"] not in EmbeddingModel:
                 return
-            return EmbeddingModel[model_config["llm_factory"]](model_config["api_key"], model_config["llm_name"],
-                                                               base_url=model_config["api_base"])
+            return EmbeddingModel[model_config["llm_factory"]](model_config["api_key"], model_config["llm_name"], base_url=model_config["api_base"])
 
         if llm_type == LLMType.RERANK:
             if model_config["llm_factory"] not in RerankModel:
                 return
-            return RerankModel[model_config["llm_factory"]](model_config["api_key"], model_config["llm_name"],
-                                                            base_url=model_config["api_base"])
+            return RerankModel[model_config["llm_factory"]](model_config["api_key"], model_config["llm_name"], base_url=model_config["api_base"])
 
         if llm_type == LLMType.IMAGE2TEXT.value:
             if model_config["llm_factory"] not in CvModel:
                 return
-            return CvModel[model_config["llm_factory"]](model_config["api_key"], model_config["llm_name"], lang,
-                                                        base_url=model_config["api_base"], **kwargs)
+            return CvModel[model_config["llm_factory"]](model_config["api_key"], model_config["llm_name"], lang, base_url=model_config["api_base"], **kwargs)
 
         if llm_type == LLMType.CHAT.value:
             if model_config["llm_factory"] not in ChatModel:
                 return
-            return ChatModel[model_config["llm_factory"]](model_config["api_key"], model_config["llm_name"],
-                                                          base_url=model_config["api_base"], **kwargs)
+            return ChatModel[model_config["llm_factory"]](model_config["api_key"], model_config["llm_name"], base_url=model_config["api_base"], **kwargs)
 
         if llm_type == LLMType.SPEECH2TEXT:
             if model_config["llm_factory"] not in Seq2txtModel:
                 return
-            return Seq2txtModel[model_config["llm_factory"]](key=model_config["api_key"],
-                                                             model_name=model_config["llm_name"], lang=lang,
-                                                             base_url=model_config["api_base"])
+            return Seq2txtModel[model_config["llm_factory"]](key=model_config["api_key"], model_name=model_config["llm_name"], lang=lang, base_url=model_config["api_base"])
         if llm_type == LLMType.TTS:
             if model_config["llm_factory"] not in TTSModel:
                 return
@@ -197,14 +194,11 @@ class TenantLLMService(CommonService):
         try:
             num = (
                 cls.model.update(used_tokens=cls.model.used_tokens + used_tokens)
-                .where(cls.model.tenant_id == tenant_id, cls.model.llm_name == llm_name,
-                       cls.model.llm_factory == llm_factory if llm_factory else True)
+                .where(cls.model.tenant_id == tenant_id, cls.model.llm_name == llm_name, cls.model.llm_factory == llm_factory if llm_factory else True)
                 .execute()
             )
         except Exception:
-            logging.exception(
-                "TenantLLMService.increase_usage got exception,Failed to update used_tokens for tenant_id=%s, llm_name=%s",
-                tenant_id, llm_name)
+            logging.exception("TenantLLMService.increase_usage got exception,Failed to update used_tokens for tenant_id=%s, llm_name=%s", tenant_id, llm_name)
             return 0
 
         return num
@@ -212,9 +206,7 @@ class TenantLLMService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_openai_models(cls):
-        objs = cls.model.select().where((cls.model.llm_factory == "OpenAI"),
-                                        ~(cls.model.llm_name == "text-embedding-3-small"),
-                                        ~(cls.model.llm_name == "text-embedding-3-large")).dicts()
+        objs = cls.model.select().where((cls.model.llm_factory == "OpenAI"), ~(cls.model.llm_name == "text-embedding-3-small"), ~(cls.model.llm_name == "text-embedding-3-large")).dicts()
         return list(objs)
 
     @classmethod
@@ -258,9 +250,8 @@ class LLM4Tenant:
         langfuse_keys = TenantLangfuseService.filter_by_tenant(tenant_id=tenant_id)
         self.langfuse = None
         if langfuse_keys:
-            langfuse = Langfuse(public_key=langfuse_keys.public_key, secret_key=langfuse_keys.secret_key,
-                                host=langfuse_keys.host)
+            langfuse = Langfuse(public_key=langfuse_keys.public_key, secret_key=langfuse_keys.secret_key, host=langfuse_keys.host)
             if langfuse.auth_check():
                 self.langfuse = langfuse
                 trace_id = self.langfuse.create_trace_id()
-                self.trace_context = {"trace_id": trace_id}
+                self.trace_context = {"trace_id": trace_id}

api/db/services/user_canvas_version.py

@@ -2,22 +2,22 @@ from api.db.db_models import UserCanvasVersion, DB
 from api.db.services.common_service import CommonService
 from peewee import DoesNotExist
 
-
 class UserCanvasVersionService(CommonService):
     model = UserCanvasVersion
-
+    
+    
     @classmethod
     @DB.connection_context()
     def list_by_canvas_id(cls, user_canvas_id):
         try:
             user_canvas_version = cls.model.select(
-                *[cls.model.id,
-                  cls.model.create_time,
-                  cls.model.title,
-                  cls.model.create_date,
-                  cls.model.update_date,
-                  cls.model.user_canvas_id,
-                  cls.model.update_time]
+                *[cls.model.id, 
+                cls.model.create_time,
+                cls.model.title,
+                cls.model.create_date, 
+                cls.model.update_date,
+                cls.model.user_canvas_id, 
+                cls.model.update_time]
             ).where(cls.model.user_canvas_id == user_canvas_id)
             return user_canvas_version
         except DoesNotExist:
@@ -46,16 +46,18 @@ class UserCanvasVersionService(CommonService):
     @DB.connection_context()
     def delete_all_versions(cls, user_canvas_id):
         try:
-            user_canvas_version = cls.model.select().where(cls.model.user_canvas_id == user_canvas_id).order_by(
-                cls.model.create_time.desc())
+            user_canvas_version = cls.model.select().where(cls.model.user_canvas_id == user_canvas_id).order_by(cls.model.create_time.desc())
             if user_canvas_version.count() > 20:
                 delete_ids = []
                 for i in range(20, user_canvas_version.count()):
                     delete_ids.append(user_canvas_version[i].id)
-
+                
                 cls.delete_by_ids(delete_ids)
             return True
         except DoesNotExist:
             return None
         except Exception:
             return None
+
+
+

api/db/services/user_service.py

@@ -24,8 +24,7 @@ from api.db import UserTenantRole
 from api.db.db_models import DB, UserTenant
 from api.db.db_models import User, Tenant
 from api.db.services.common_service import CommonService
-from api.utils import get_uuid
-from common.time_utils import current_timestamp, datetime_format
+from api.utils import get_uuid, current_timestamp, datetime_format
 from api.db import StatusEnum
 from rag.settings import MINIO
 
@@ -316,4 +315,4 @@ class UserTenantService(CommonService):
             ).first()
             return user_tenant
         except peewee.DoesNotExist:
-            return None
+            return None

api/settings.py

@@ -28,6 +28,8 @@ from api.utils.configs import decrypt_database_config, get_base_config
 from api.utils.file_utils import get_project_base_directory
 from rag.nlp import search
 
+LIGHTEN = int(os.environ.get("LIGHTEN", "0"))
+
 LLM = None
 LLM_FACTORY = None
 LLM_BASE_URL = None
@@ -63,8 +65,8 @@ OAUTH_CONFIG = None
 DOC_ENGINE = None
 docStoreConn = None
 
-retriever = None
-kg_retriever = None
+retrievaler = None
+kg_retrievaler = None
 
 # user registration switch
 REGISTER_ENABLED = 1
@@ -75,6 +77,8 @@ SANDBOX_ENABLED = 0
 SANDBOX_HOST = None
 STRONG_TEST_COUNT = int(os.environ.get("STRONG_TEST_COUNT", "8"))
 
+BUILTIN_EMBEDDING_MODELS = ["BAAI/bge-large-zh-v1.5@BAAI", "maidalun1020/bce-embedding-base_v1@Youdao"]
+
 SMTP_CONF = None
 MAIL_SERVER = ""
 MAIL_PORT = 000
@@ -105,7 +109,8 @@ def get_or_create_secret_key():
 
 
 def init_settings():
-    global LLM, LLM_FACTORY, LLM_BASE_URL, DATABASE_TYPE, DATABASE, FACTORY_LLM_INFOS, REGISTER_ENABLED
+    global LLM, LLM_FACTORY, LLM_BASE_URL, LIGHTEN, DATABASE_TYPE, DATABASE, FACTORY_LLM_INFOS, REGISTER_ENABLED
+    LIGHTEN = int(os.environ.get("LIGHTEN", "0"))
     DATABASE_TYPE = os.getenv("DB_TYPE", "mysql")
     DATABASE = decrypt_database_config(name=DATABASE_TYPE)
     LLM = get_base_config("user_default_llm", {}) or {}
@@ -125,6 +130,8 @@ def init_settings():
 
     global CHAT_MDL, EMBEDDING_MDL, RERANK_MDL, ASR_MDL, IMAGE2TEXT_MDL
     global CHAT_CFG, EMBEDDING_CFG, RERANK_CFG, ASR_CFG, IMAGE2TEXT_CFG
+    if not LIGHTEN:
+        EMBEDDING_MDL = BUILTIN_EMBEDDING_MODELS[0]
 
     global API_KEY, PARSERS, HOST_IP, HOST_PORT, SECRET_KEY
     API_KEY = LLM.get("api_key")
@@ -145,7 +152,7 @@ def init_settings():
     IMAGE2TEXT_CFG = _resolve_per_model_config(image2text_entry, LLM_FACTORY, API_KEY, LLM_BASE_URL)
 
     CHAT_MDL = CHAT_CFG.get("model", "") or ""
-    EMBEDDING_MDL = os.getenv("TEI_MODEL", "BAAI/bge-small-en-v1.5") if "tei-" in os.getenv("COMPOSE_PROFILES", "") else ""
+    EMBEDDING_MDL = EMBEDDING_CFG.get("model", "") or ""
     RERANK_MDL = RERANK_CFG.get("model", "") or ""
     ASR_MDL = ASR_CFG.get("model", "") or ""
     IMAGE2TEXT_MDL = IMAGE2TEXT_CFG.get("model", "") or ""
@@ -167,7 +174,7 @@ def init_settings():
 
     OAUTH_CONFIG = get_base_config("oauth", {})
 
-    global DOC_ENGINE, docStoreConn, retriever, kg_retriever
+    global DOC_ENGINE, docStoreConn, retrievaler, kg_retrievaler
     DOC_ENGINE = os.environ.get("DOC_ENGINE", "elasticsearch")
     # DOC_ENGINE = os.environ.get('DOC_ENGINE', "opensearch")
     lower_case_doc_engine = DOC_ENGINE.lower()
@@ -180,10 +187,10 @@ def init_settings():
     else:
         raise Exception(f"Not supported doc engine: {DOC_ENGINE}")
 
-    retriever = search.Dealer(docStoreConn)
+    retrievaler = search.Dealer(docStoreConn)
     from graphrag import search as kg_search
 
-    kg_retriever = kg_search.KGSearch(docStoreConn)
+    kg_retrievaler = kg_search.KGSearch(docStoreConn)
 
     if int(os.environ.get("SANDBOX_ENABLED", "0")):
         global SANDBOX_HOST

api/utils/__init__.py

@@ -14,9 +14,11 @@
 #  limitations under the License.
 #
 import base64
+import datetime
 import hashlib
 import os
 import socket
+import time
 import uuid
 import requests
 
@@ -24,6 +26,26 @@ import importlib
 
 from .common import string_to_bytes
 
+
+def current_timestamp():
+    return int(time.time() * 1000)
+
+
+def timestamp_to_date(timestamp, format_string="%Y-%m-%d %H:%M:%S"):
+    if not timestamp:
+        timestamp = time.time()
+    timestamp = int(timestamp) / 1000
+    time_array = time.localtime(timestamp)
+    str_date = time.strftime(format_string, time_array)
+    return str_date
+
+
+def date_string_to_timestamp(time_str, format_string="%Y-%m-%d %H:%M:%S"):
+    time_array = time.strptime(time_str, format_string)
+    time_stamp = int(time.mktime(time_array) * 1000)
+    return time_stamp
+
+
 def get_lan_ip():
     if os.name != "nt":
         import fcntl
@@ -72,6 +94,26 @@ def get_uuid():
     return uuid.uuid1().hex
 
 
+def datetime_format(date_time: datetime.datetime) -> datetime.datetime:
+    return datetime.datetime(date_time.year, date_time.month, date_time.day,
+                             date_time.hour, date_time.minute, date_time.second)
+
+
+def get_format_time() -> datetime.datetime:
+    return datetime_format(datetime.datetime.now())
+
+
+def str2date(date_time: str):
+    return datetime.datetime.strptime(date_time, '%Y-%m-%d')
+
+
+def elapsed2time(elapsed):
+    seconds = elapsed / 1000
+    minuter, second = divmod(seconds, 60)
+    hour, minuter = divmod(minuter, 60)
+    return '%02d:%02d:%02d' % (hour, minuter, second)
+
+
 def download_img(url):
     if not url:
         return ""
@@ -81,5 +123,10 @@ def download_img(url):
         "base64," + base64.b64encode(response.content).decode("utf-8")
 
 
+def delta_seconds(date_string: str):
+    dt = datetime.datetime.strptime(date_string, "%Y-%m-%d %H:%M:%S")
+    return (datetime.datetime.now() - dt).total_seconds()
+
+
 def hash_str2int(line: str, mod: int = 10 ** 8) -> int:
     return int(hashlib.sha1(line.encode("utf-8")).hexdigest(), 16) % mod

api/utils/api_utils.py

@@ -51,13 +51,15 @@ from api import settings
 from api.constants import REQUEST_MAX_WAIT_SEC, REQUEST_WAIT_SEC
 from api.db import ActiveEnum
 from api.db.db_models import APIToken
+from api.db.services import UserService
+from api.db.services.llm_service import LLMService
+from api.db.services.tenant_llm_service import TenantLLMService
 from api.utils.json import CustomJSONEncoder, json_dumps
 from api.utils import get_uuid
 from rag.utils.mcp_tool_call_conn import MCPToolCallSession, close_multiple_mcp_toolcall_sessions
 
 requests.models.complexjson.dumps = functools.partial(json.dumps, cls=CustomJSONEncoder)
 
-
 def serialize_for_json(obj):
     """
     Recursively serialize objects to make them JSON serializable.
@@ -66,8 +68,8 @@ def serialize_for_json(obj):
     if hasattr(obj, '__dict__'):
         # For objects with __dict__, try to serialize their attributes
         try:
-            return {key: serialize_for_json(value) for key, value in obj.__dict__.items()
-                    if not key.startswith('_')}
+            return {key: serialize_for_json(value) for key, value in obj.__dict__.items() 
+                   if not key.startswith('_')}
         except (AttributeError, TypeError):
             return str(obj)
     elif hasattr(obj, '__name__'):
@@ -83,7 +85,6 @@ def serialize_for_json(obj):
         # Fallback: convert to string representation
         return str(obj)
 
-
 def request(**kwargs):
     sess = requests.Session()
     stream = kwargs.pop("stream", sess.stream)
@@ -104,8 +105,7 @@ def request(**kwargs):
                         settings.HTTP_APP_KEY.encode("ascii"),
                         prepped.path_url.encode("ascii"),
                         prepped.body if kwargs.get("json") else b"",
-                        urlencode(sorted(kwargs["data"].items()), quote_via=quote, safe="-._~").encode(
-                            "ascii") if kwargs.get("data") and isinstance(kwargs["data"], dict) else b"",
+                        urlencode(sorted(kwargs["data"].items()), quote_via=quote, safe="-._~").encode("ascii") if kwargs.get("data") and isinstance(kwargs["data"], dict) else b"",
                     ]
                 ),
                 "sha1",
@@ -127,7 +127,7 @@ def request(**kwargs):
 def get_exponential_backoff_interval(retries, full_jitter=False):
     """Calculate the exponential backoff wait time."""
     # Will be zero if factor equals 0
-    countdown = min(REQUEST_MAX_WAIT_SEC, REQUEST_WAIT_SEC * (2 ** retries))
+    countdown = min(REQUEST_MAX_WAIT_SEC, REQUEST_WAIT_SEC * (2**retries))
     # Full jitter according to
     # https://aws.amazon.com/blogs/architecture/exponential-backoff-and-jitter/
     if full_jitter:
@@ -151,21 +151,18 @@ def get_data_error_result(code=settings.RetCode.DATA_ERROR, message="Sorry! Data
 def server_error_response(e):
     logging.exception(e)
     try:
-        msg = repr(e).lower()
-        if getattr(e, "code", None) == 401 or ("unauthorized" in msg) or ("401" in msg):
-            return get_json_result(code=settings.RetCode.UNAUTHORIZED, message=repr(e))
-    except Exception as ex:
-        logging.warning(f"error checking authorization: {ex}")
-
+        if e.code == 401:
+            return get_json_result(code=401, message=repr(e))
+    except BaseException:
+        pass
     if len(e.args) > 1:
         try:
             serialized_data = serialize_for_json(e.args[1])
-            return get_json_result(code=settings.RetCode.EXCEPTION_ERROR, message=repr(e.args[0]), data=serialized_data)
+            return get_json_result(code= settings.RetCode.EXCEPTION_ERROR, message=repr(e.args[0]), data=serialized_data)
         except Exception:
             return get_json_result(code=settings.RetCode.EXCEPTION_ERROR, message=repr(e.args[0]), data=None)
     if repr(e).find("index_not_found_exception") >= 0:
-        return get_json_result(code=settings.RetCode.EXCEPTION_ERROR,
-                               message="No chunk found, please upload file and parse it.")
+        return get_json_result(code=settings.RetCode.EXCEPTION_ERROR, message="No chunk found, please upload file and parse it.")
 
     return get_json_result(code=settings.RetCode.EXCEPTION_ERROR, message=repr(e))
 
@@ -210,8 +207,7 @@ def validate_request(*args, **kwargs):
                 if no_arguments:
                     error_string += "required argument are missing: {}; ".format(",".join(no_arguments))
                 if error_arguments:
-                    error_string += "required argument values: {}".format(
-                        ",".join(["{}={}".format(a[0], a[1]) for a in error_arguments]))
+                    error_string += "required argument values: {}".format(",".join(["{}={}".format(a[0], a[1]) for a in error_arguments]))
                 return get_json_result(code=settings.RetCode.ARGUMENT_ERROR, message=error_string)
             return func(*_args, **_kwargs)
 
@@ -226,8 +222,7 @@ def not_allowed_parameters(*params):
             input_arguments = flask_request.json or flask_request.form.to_dict()
             for param in params:
                 if param in input_arguments:
-                    return get_json_result(code=settings.RetCode.ARGUMENT_ERROR,
-                                           message=f"Parameter {param} isn't allowed")
+                    return get_json_result(code=settings.RetCode.ARGUMENT_ERROR, message=f"Parameter {param} isn't allowed")
             return f(*args, **kwargs)
 
         return wrapper
@@ -238,14 +233,12 @@ def not_allowed_parameters(*params):
 def active_required(f):
     @wraps(f)
     def wrapper(*args, **kwargs):
-        from api.db.services import UserService
         user_id = current_user.id
         usr = UserService.filter_by_id(user_id)
         # check is_active
         if not usr or not usr.is_active == ActiveEnum.ACTIVE.value:
             return get_json_result(code=settings.RetCode.FORBIDDEN, message="User isn't active, please activate first.")
         return f(*args, **kwargs)
-
     return wrapper
 
 
@@ -266,7 +259,7 @@ def send_file_in_mem(data, filename):
     return send_file(f, as_attachment=True, attachment_filename=filename)
 
 
-def get_json_result(code: settings.RetCode = settings.RetCode.SUCCESS, message="success", data=None):
+def get_json_result(code=settings.RetCode.SUCCESS, message="success", data=None):
     response = {"code": code, "message": message, "data": data}
     return jsonify(response)
 
@@ -321,7 +314,7 @@ def construct_result(code=settings.RetCode.DATA_ERROR, message="data is missing"
     return jsonify(response)
 
 
-def construct_json_result(code: settings.RetCode = settings.RetCode.SUCCESS, message="success", data=None):
+def construct_json_result(code=settings.RetCode.SUCCESS, message="success", data=None):
     if data is None:
         return jsonify({"code": code, "message": message})
     else:
@@ -354,39 +347,27 @@ def token_required(func):
         token = authorization_list[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)
+            return get_json_result(data=False, message="Authentication error: API key is invalid!", code=settings.RetCode.AUTHENTICATION_ERROR)
         kwargs["tenant_id"] = objs[0].tenant_id
         return func(*args, **kwargs)
 
     return decorated_function
 
 
-def get_result(code=settings.RetCode.SUCCESS, message="", data=None, total=None):
-    """
-    Standard API response format:
-    {
-        "code": 0,
-        "data": [...],        # List or object, backward compatible
-        "total": 47,          # Optional field for pagination
-        "message": "..."      # Error or status message
-    }
-    """
-    response = {"code": code}
-
-    if code == settings.RetCode.SUCCESS:
+def get_result(code=settings.RetCode.SUCCESS, message="", data=None):
+    if code == 0:
         if data is not None:
-            response["data"] = data
-        if total is not None:
-            response["total_datasets"] = total
+            response = {"code": code, "data": data}
+        else:
+            response = {"code": code}
     else:
-        response["message"] = message or "Error"
-
+        response = {"code": code, "message": message}
     return jsonify(response)
 
+
 def get_error_data_result(
-        message="Sorry! Data missing!",
-        code=settings.RetCode.DATA_ERROR,
+    message="Sorry! Data missing!",
+    code=settings.RetCode.DATA_ERROR,
 ):
     result_dict = {"code": code, "message": message}
     response = {}
@@ -421,8 +402,7 @@ def get_parser_config(chunk_method, parser_config):
 
     # Define default configurations for each chunking method
     key_mapping = {
-        "naive": {"chunk_token_num": 512, "delimiter": r"\n", "html4excel": False, "layout_recognize": "DeepDOC",
-                  "raptor": {"use_raptor": False}, "graphrag": {"use_graphrag": False}},
+        "naive": {"chunk_token_num": 512, "delimiter": r"\n", "html4excel": False, "layout_recognize": "DeepDOC", "raptor": {"use_raptor": False}, "graphrag": {"use_graphrag": False}},
         "qa": {"raptor": {"use_raptor": False}, "graphrag": {"use_graphrag": False}},
         "tag": None,
         "resume": None,
@@ -461,16 +441,16 @@ def get_parser_config(chunk_method, parser_config):
 
 
 def get_data_openai(
-        id=None,
-        created=None,
-        model=None,
-        prompt_tokens=0,
-        completion_tokens=0,
-        content=None,
-        finish_reason=None,
-        object="chat.completion",
-        param=None,
-        stream=False
+    id=None,
+    created=None,
+    model=None,
+    prompt_tokens=0,
+    completion_tokens=0,
+    content=None,
+    finish_reason=None,
+    object="chat.completion",
+    param=None,
+    stream=False
 ):
     total_tokens = prompt_tokens + completion_tokens
 
@@ -544,8 +524,6 @@ def check_duplicate_ids(ids, id_type="item"):
 
 
 def verify_embedding_availability(embd_id: str, tenant_id: str) -> tuple[bool, Response | None]:
-    from api.db.services.llm_service import LLMService
-    from api.db.services.tenant_llm_service import TenantLLMService
     """
     Verifies availability of an embedding model for a specific tenant.
 
@@ -584,11 +562,9 @@ def verify_embedding_availability(embd_id: str, tenant_id: str) -> tuple[bool, R
         in_llm_service = bool(LLMService.query(llm_name=llm_name, fid=llm_factory, model_type="embedding"))
 
         tenant_llms = TenantLLMService.get_my_llms(tenant_id=tenant_id)
-        is_tenant_model = any(
-            llm["llm_name"] == llm_name and llm["llm_factory"] == llm_factory and llm["model_type"] == "embedding" for
-            llm in tenant_llms)
+        is_tenant_model = any(llm["llm_name"] == llm_name and llm["llm_factory"] == llm_factory and llm["model_type"] == "embedding" for llm in tenant_llms)
 
-        is_builtin_model = llm_factory=='Builtin'
+        is_builtin_model = embd_id in settings.BUILTIN_EMBEDDING_MODELS
         if not (is_builtin_model or is_tenant_model or in_llm_service):
             return False, get_error_argument_result(f"Unsupported model: <{embd_id}>")
 
@@ -817,9 +793,7 @@ async def is_strong_enough(chat_model, embedding_model):
                 _ = await trio.to_thread.run_sync(lambda: embedding_model.encode(["Are you strong enough!?"]))
         if chat_model:
             with trio.fail_after(30):
-                res = await trio.to_thread.run_sync(lambda: chat_model.chat("Nothing special.", [{"role": "user",
-                                                                                                  "content": "Are you strong enough!?"}],
-                                                                            {}))
+                res = await trio.to_thread.run_sync(lambda: chat_model.chat("Nothing special.", [{"role": "user", "content": "Are you strong enough!?"}], {}))
             if res.find("**ERROR**") >= 0:
                 raise Exception(res)
 

api/utils/common.py

@@ -14,12 +14,6 @@
 #  limitations under the License.
 #
 
-import threading
-import subprocess
-import sys
-import os
-import logging
-
 def string_to_bytes(string):
     return string if isinstance(
         string, bytes) else string.encode(encoding="utf-8")
@@ -27,71 +21,3 @@ def string_to_bytes(string):
 
 def bytes_to_string(byte):
     return byte.decode(encoding="utf-8")
-
-
-def convert_bytes(size_in_bytes: int) -> str:
-    """
-    Format size in bytes.
-    """
-    if size_in_bytes == 0:
-        return "0 B"
-
-    units = ['B', 'KB', 'MB', 'GB', 'TB', 'PB']
-    i = 0
-    size = float(size_in_bytes)
-
-    while size >= 1024 and i < len(units) - 1:
-        size /= 1024
-        i += 1
-
-    if i == 0 or size >= 100:
-        return f"{size:.0f} {units[i]}"
-    elif size >= 10:
-        return f"{size:.1f} {units[i]}"
-    else:
-        return f"{size:.2f} {units[i]}"
-
-
-def once(func):
-    """
-    A thread-safe decorator that ensures the decorated function runs exactly once,
-    caching and returning its result for all subsequent calls. This prevents
-    race conditions in multi-threaded environments by using a lock to protect
-    the execution state.
-
-    Args:
-        func (callable): The function to be executed only once.
-
-    Returns:
-        callable: A wrapper function that executes `func` on the first call
-                  and returns the cached result thereafter.
-
-    Example:
-        @once
-        def compute_expensive_value():
-            print("Computing...")
-            return 42
-
-        # First call: executes and prints
-        # Subsequent calls: return 42 without executing
-    """
-    executed = False
-    result = None
-    lock = threading.Lock()
-    def wrapper(*args, **kwargs):
-        nonlocal executed, result
-        with lock:
-            if not executed:
-                executed = True
-                result = func(*args, **kwargs)
-        return result
-    return wrapper
-
-@once
-def pip_install_torch():
-    device = os.getenv("DEVICE", "cpu")
-    if device=="cpu":
-        return
-    logging.info("Installing pytorch")
-    pkg_names = ["torch>=2.5.0,<3.0.0"]
-    subprocess.check_call([sys.executable, "-m", "pip", "install", *pkg_names])

api/utils/email_templates.py

@@ -1,25 +0,0 @@
-"""
-Reusable HTML email templates and registry.
-"""
-
-# Invitation email template
-INVITE_EMAIL_TMPL = """
-<p>Hi {{email}},</p>
-<p>{{inviter}} has invited you to join their team (ID: {{tenant_id}}).</p>
-<p>Click the link below to complete your registration:<br>
-<a href="{{invite_url}}">{{invite_url}}</a></p>
-<p>If you did not request this, please ignore this email.</p>
-"""
-
-# Password reset code template
-RESET_CODE_EMAIL_TMPL = """
-<p>Hello,</p>
-<p>Your password reset code is: <b>{{ code }}</b></p>
-<p>This code will expire in {{ ttl_min }} minutes.</p>
-"""
-
-# Template registry
-EMAIL_TEMPLATES = {
-    "invite": INVITE_EMAIL_TMPL,
-    "reset_code": RESET_CODE_EMAIL_TMPL,
-}

api/utils/file_utils.py

@@ -13,12 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-
-
-# Standard library imports
 import base64
-import hashlib
-import io
 import json
 import os
 import re
@@ -27,20 +22,13 @@ import subprocess
 import sys
 import tempfile
 import threading
-import zipfile
 from io import BytesIO
 
-# Typing
-from typing import List, Union, Tuple
-
-# Third-party imports
-import olefile
 import pdfplumber
 from cachetools import LRUCache, cached
 from PIL import Image
 from ruamel.yaml import YAML
 
-# Local imports
 from api.constants import IMG_BASE64_PREFIX
 from api.db import FileType
 
@@ -173,7 +161,7 @@ def filename_type(filename):
     if re.match(r".*\.(wav|flac|ape|alac|wavpack|wv|mp3|aac|ogg|vorbis|opus)$", filename):
         return FileType.AURAL.value
 
-    if re.match(r".*\.(jpg|jpeg|png|tif|gif|pcx|tga|exif|fpx|svg|psd|cdr|pcd|dxf|ufo|eps|ai|raw|WMF|webp|avif|apng|icon|ico|mpg|mpeg|avi|rm|rmvb|mov|wmv|asf|dat|asx|wvx|mpe|mpa|mp4|avi|mkv)$", filename):
+    if re.match(r".*\.(jpg|jpeg|png|tif|gif|pcx|tga|exif|fpx|svg|psd|cdr|pcd|dxf|ufo|eps|ai|raw|WMF|webp|avif|apng|icon|ico|mpg|mpeg|avi|rm|rmvb|mov|wmv|asf|dat|asx|wvx|mpe|mpa|mp4)$", filename):
         return FileType.VISUAL.value
 
     return FileType.OTHER.value
@@ -296,125 +284,3 @@ def read_potential_broken_pdf(blob):
         return repaired
 
     return blob
-
-
-
-def _is_zip(h: bytes) -> bool:
-    return h.startswith(b"PK\x03\x04") or h.startswith(b"PK\x05\x06") or h.startswith(b"PK\x07\x08")
-
-def _is_pdf(h: bytes) -> bool:
-    return h.startswith(b"%PDF-")
-
-def _is_ole(h: bytes) -> bool:
-    return h.startswith(b"\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1")
-
-def _sha10(b: bytes) -> str:
-    return hashlib.sha256(b).hexdigest()[:10]
-
-def _guess_ext(b: bytes) -> str:
-    h = b[:8]
-    if _is_zip(h):
-        try:
-            with zipfile.ZipFile(io.BytesIO(b), "r") as z:
-                names = [n.lower() for n in z.namelist()]
-                if any(n.startswith("word/") for n in names):
-                    return ".docx"
-                if any(n.startswith("ppt/") for n in names):
-                    return ".pptx"
-                if any(n.startswith("xl/") for n in names):
-                    return ".xlsx"
-        except Exception:
-            pass
-        return ".zip"
-    if _is_pdf(h):
-        return ".pdf"
-    if _is_ole(h):
-        return ".doc"
-    return ".bin"
-
-# Try to extract the real embedded payload from OLE's Ole10Native
-def _extract_ole10native_payload(data: bytes) -> bytes:
-    try:
-        pos = 0
-        if len(data) < 4:
-            return data
-        _ = int.from_bytes(data[pos:pos+4], "little")
-        pos += 4
-        # filename/src/tmp (NUL-terminated ANSI)
-        for _ in range(3):
-            z = data.index(b"\x00", pos)
-            pos = z + 1
-        # skip unknown 4 bytes
-        pos += 4
-        if pos + 4 > len(data):
-            return data
-        size = int.from_bytes(data[pos:pos+4], "little")
-        pos += 4
-        if pos + size <= len(data):
-            return data[pos:pos+size]
-    except Exception:
-        pass
-    return data
-
-def extract_embed_file(target: Union[bytes, bytearray]) -> List[Tuple[str, bytes]]:
-    """
-    Only extract the 'first layer' of embedding, returning raw (filename, bytes).
-    """
-    top = bytes(target)
-    head = top[:8]
-    out: List[Tuple[str, bytes]] = []
-    seen = set()
-
-    def push(b: bytes, name_hint: str = ""):
-        h10 = _sha10(b)
-        if h10 in seen:
-            return
-        seen.add(h10)
-        ext = _guess_ext(b)
-        # If name_hint has an extension use its basename; else fallback to guessed ext
-        if "." in name_hint:
-            fname = name_hint.split("/")[-1]
-        else:
-            fname = f"{h10}{ext}"
-        out.append((fname, b))
-
-    # OOXML/ZIP container (docx/xlsx/pptx)
-    if _is_zip(head):
-        try:
-            with zipfile.ZipFile(io.BytesIO(top), "r") as z:
-                embed_dirs = (
-                    "word/embeddings/", "word/objects/", "word/activex/",
-                    "xl/embeddings/", "ppt/embeddings/"
-                )
-                for name in z.namelist():
-                    low = name.lower()
-                    if any(low.startswith(d) for d in embed_dirs):
-                        try:
-                            b = z.read(name)
-                            push(b, name)
-                        except Exception:
-                            pass
-        except Exception:
-            pass
-        return out
-
-    # OLE container (doc/ppt/xls)
-    if _is_ole(head):
-        try:
-            with olefile.OleFileIO(io.BytesIO(top)) as ole:
-                for entry in ole.listdir():
-                    p = "/".join(entry)
-                    try:
-                        data = ole.openstream(entry).read()
-                    except Exception:
-                        continue
-                    if not data:
-                        continue
-                    if "Ole10Native" in p or "ole10native" in p.lower():
-                        data = _extract_ole10native_payload(data)
-                    push(data, p)
-        except Exception:
-            pass
-        return out
-
-    return out

api/utils/health_utils.py

@@ -13,17 +13,14 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-import os
-import requests
+
+
 from timeit import default_timer as timer
 
 from api import settings
 from api.db.db_models import DB
-from rag import settings as rag_settings
 from rag.utils.redis_conn import REDIS_CONN
 from rag.utils.storage_factory import STORAGE_IMPL
-from rag.utils.es_conn import ESConnection
-from rag.utils.infinity_conn import InfinityConnection
 
 
 def _ok_nok(ok: bool) -> str:
@@ -68,96 +65,6 @@ def check_storage() -> tuple[bool, dict]:
         return False, {"elapsed": f"{(timer() - st) * 1000.0:.1f}", "error": str(e)}
 
 
-def get_es_cluster_stats() -> dict:
-    doc_engine = os.getenv('DOC_ENGINE', 'elasticsearch')
-    if doc_engine != 'elasticsearch':
-        raise Exception("Elasticsearch is not in use.")
-    try:
-        return {
-            "status": "alive",
-            "message": ESConnection().get_cluster_stats()
-        }
-    except Exception as e:
-        return {
-            "status": "timeout",
-            "message": f"error: {str(e)}",
-        }
-
-
-def get_infinity_status():
-    doc_engine = os.getenv('DOC_ENGINE', 'elasticsearch')
-    if doc_engine != 'infinity':
-        raise Exception("Infinity is not in use.")
-    try:
-        return {
-            "status": "alive",
-            "message": InfinityConnection().health()
-        }
-    except Exception as e:
-        return {
-            "status": "timeout",
-            "message": f"error: {str(e)}",
-        }
-
-
-def get_mysql_status():
-    try:
-        cursor = DB.execute_sql("SHOW PROCESSLIST;")
-        res_rows = cursor.fetchall()
-        headers = ['id', 'user', 'host', 'db', 'command', 'time', 'state', 'info']
-        cursor.close()
-        return {
-            "status": "alive",
-            "message": [dict(zip(headers, r)) for r in res_rows]
-        }
-    except Exception as e:
-        return {
-            "status": "timeout",
-            "message": f"error: {str(e)}",
-        }
-
-
-def check_minio_alive():
-    start_time = timer()
-    try:
-        response = requests.get(f'http://{rag_settings.MINIO["host"]}/minio/health/live')
-        if response.status_code == 200:
-            return {"status": "alive", "message": f"Confirm elapsed: {(timer() - start_time) * 1000.0:.1f} ms."}
-        else:
-            return {"status": "timeout", "message": f"Confirm elapsed: {(timer() - start_time) * 1000.0:.1f} ms."}
-    except Exception as e:
-        return {
-            "status": "timeout",
-            "message": f"error: {str(e)}",
-        }
-
-
-def get_redis_info():
-    try:
-        return {
-            "status": "alive",
-            "message": REDIS_CONN.info()
-        }
-    except Exception as e:
-        return {
-            "status": "timeout",
-            "message": f"error: {str(e)}",
-        }
-
-
-def check_ragflow_server_alive():
-    start_time = timer()
-    try:
-        response = requests.get(f'http://{settings.HOST_IP}:{settings.HOST_PORT}/v1/system/ping')
-        if response.status_code == 200:
-            return {"status": "alive", "message": f"Confirm elapsed: {(timer() - start_time) * 1000.0:.1f} ms."}
-        else:
-            return {"status": "timeout", "message": f"Confirm elapsed: {(timer() - start_time) * 1000.0:.1f} ms."}
-    except Exception as e:
-        return {
-            "status": "timeout",
-            "message": f"error: {str(e)}",
-        }
 
 
 def run_health_checks() -> tuple[dict, bool]:
@@ -192,7 +99,9 @@ def run_health_checks() -> tuple[dict, bool]:
     except Exception:
         result["storage"] = "nok"
 
-    all_ok = (result.get("db") == "ok") and (result.get("redis") == "ok") and (result.get("doc_engine") == "ok") and (
-                result.get("storage") == "ok")
+
+    all_ok = (result.get("db") == "ok") and (result.get("redis") == "ok") and (result.get("doc_engine") == "ok") and (result.get("storage") == "ok")
     result["status"] = "ok" if all_ok else "nok"
     return result, all_ok
+
+

api/utils/web_utils.py

@@ -24,7 +24,6 @@ from urllib.parse import urlparse
 from api.apps import smtp_mail_server
 from flask_mail import Message
 from flask import render_template_string
-from api.utils.email_templates import EMAIL_TEMPLATES
 from selenium import webdriver
 from selenium.common.exceptions import TimeoutException
 from selenium.webdriver.chrome.options import Options
@@ -35,12 +34,6 @@ from selenium.webdriver.support.ui import WebDriverWait
 from webdriver_manager.chrome import ChromeDriverManager
 
 
-OTP_LENGTH = 8
-OTP_TTL_SECONDS = 5 * 60
-ATTEMPT_LIMIT = 5
-ATTEMPT_LOCK_SECONDS = 30 * 60
-RESEND_COOLDOWN_SECONDS = 60
-
 
 CONTENT_TYPE_MAP = {
     # Office
@@ -185,49 +178,24 @@ def get_float(req: dict, key: str, default: float | int = 10.0) -> float:
         return default
 
 
-def send_email_html(subject: str, to_email: str, template_key: str, **context):
-    """Generic HTML email sender using shared templates.
-    template_key must exist in EMAIL_TEMPLATES.
-    """
-    from api.apps import app
-    tmpl = EMAIL_TEMPLATES.get(template_key)
-    if not tmpl:
-        raise ValueError(f"Unknown email template: {template_key}")
-    with app.app_context():
-        msg = Message(subject=subject, recipients=[to_email])
-        msg.html = render_template_string(tmpl, **context)
-        smtp_mail_server.send(msg)
-
+INVITE_EMAIL_TMPL = """
+<p>Hi {{email}},</p>
+<p>{{inviter}} has invited you to join their team (ID: {{tenant_id}}).</p>
+<p>Click the link below to complete your registration:<br>
+<a href="{{invite_url}}">{{invite_url}}</a></p>
+<p>If you did not request this, please ignore this email.</p>
+"""
 
 def send_invite_email(to_email, invite_url, tenant_id, inviter):
-    # Reuse the generic HTML sender with 'invite' template
-    send_email_html(
-        subject="RAGFlow Invitation",
-        to_email=to_email,
-        template_key="invite",
-        email=to_email,
-        invite_url=invite_url,
-        tenant_id=tenant_id,
-        inviter=inviter,
-    )
-
-
-def otp_keys(email: str):
-    email = (email or "").strip().lower()
-    return (
-        f"otp:{email}",
-        f"otp_attempts:{email}",
-        f"otp_last_sent:{email}",
-        f"otp_lock:{email}",
-    )
-
-
-def hash_code(code: str, salt: bytes) -> str:
-    import hashlib
-    import hmac 
-    return hmac.new(salt, (code or "").encode("utf-8"), hashlib.sha256).hexdigest()
-    
-
-def captcha_key(email: str) -> str:
-    return f"captcha:{email}"
-    
+    from api.apps import  app
+    with app.app_context():
+        msg = Message(subject="RAGFlow Invitation",
+                      recipients=[to_email])
+        msg.html = render_template_string(
+            INVITE_EMAIL_TMPL,
+            email=to_email,
+            invite_url=invite_url,
+            tenant_id=tenant_id,
+            inviter=inviter,
+        )
+        smtp_mail_server.send(msg)

api/versions.py

@@ -34,6 +34,8 @@ def get_ragflow_version() -> str:
             RAGFLOW_VERSION_INFO = f.read().strip()
     else:
         RAGFLOW_VERSION_INFO = get_closest_tag_and_count()
+        LIGHTEN = int(os.environ.get("LIGHTEN", "0"))
+        RAGFLOW_VERSION_INFO += " slim" if LIGHTEN == 1 else " full"
     return RAGFLOW_VERSION_INFO
 
 

common/float_utils.py

@@ -1,46 +0,0 @@
-#
-#  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.
-#
-
-def get_float(v):
-    """
-    Convert a value to float, handling None and exceptions gracefully.
-
-    Attempts to convert the input value to a float. If the value is None or
-    cannot be converted to float, returns negative infinity as a default value.
-
-    Args:
-        v: The value to convert to float. Can be any type that float() accepts,
-           or None.
-
-    Returns:
-        float: The converted float value if successful, otherwise float('-inf').
-
-    Examples:
-        >>> get_float("3.14")
-        3.14
-        >>> get_float(None)
-        -inf
-        >>> get_float("invalid")
-        -inf
-        >>> get_float(42)
-        42.0
-    """
-    if v is None:
-        return float('-inf')
-    try:
-        return float(v)
-    except Exception:
-        return float('-inf')

common/string_utils.py

@@ -1,73 +0,0 @@
-#
-#  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 re
-
-
-def remove_redundant_spaces(txt: str):
-    """
-    Remove redundant spaces around punctuation marks while preserving meaningful spaces.
-
-    This function performs two main operations:
-    1. Remove spaces after left-boundary characters (opening brackets, etc.)
-    2. Remove spaces before right-boundary characters (closing brackets, punctuation, etc.)
-
-    Args:
-        txt (str): Input text to process
-
-    Returns:
-        str: Text with redundant spaces removed
-    """
-    # First pass: Remove spaces after left-boundary characters
-    # Matches: [non-alphanumeric-and-specific-right-punctuation] + [non-space]
-    # Removes spaces after characters like '(', '<', and other non-alphanumeric chars
-    # Examples:
-    #   "( test" → "(test"
-    txt = re.sub(r"([^a-z0-9.,\)>]) +([^ ])", r"\1\2", txt, flags=re.IGNORECASE)
-
-    # Second pass: Remove spaces before right-boundary characters
-    # Matches: [non-space] + [non-alphanumeric-and-specific-left-punctuation]
-    # Removes spaces before characters like non-')', non-',', non-'.', and non-alphanumeric chars
-    # Examples:
-    #   "world !" → "world!"
-    return re.sub(r"([^ ]) +([^a-z0-9.,\(<])", r"\1\2", txt, flags=re.IGNORECASE)
-
-
-def clean_markdown_block(text):
-    """
-    Remove Markdown code block syntax from the beginning and end of text.
-
-    This function cleans Markdown code blocks by removing:
-    - Opening ```Markdown tags (with optional whitespace and newlines)
-    - Closing ``` tags (with optional whitespace and newlines)
-
-    Args:
-        text (str): Input text that may be wrapped in Markdown code blocks
-
-    Returns:
-        str: Cleaned text with Markdown code block syntax removed, and stripped of surrounding whitespace
-
-    """
-    # Remove opening ```markdown tag with optional whitespace and newlines
-    # Matches: optional whitespace + ```markdown + optional whitespace + optional newline
-    text = re.sub(r'^\s*```markdown\s*\n?', '', text)
-
-    # Remove closing ``` tag with optional whitespace and newlines
-    # Matches: optional newline + optional whitespace + ``` + optional whitespace at end
-    text = re.sub(r'\n?\s*```\s*$', '', text)
-
-    # Return text with surrounding whitespace removed
-    return text.strip()

common/time_utils.py

@@ -1,126 +0,0 @@
-#
-#  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 datetime
-import time
-
-def current_timestamp():
-    """
-    Get the current timestamp in milliseconds.
-
-    Returns:
-        int: Current Unix timestamp in milliseconds (13 digits)
-
-    Example:
-        >>> current_timestamp()
-        1704067200000
-    """
-    return int(time.time() * 1000)
-
-
-def timestamp_to_date(timestamp, format_string="%Y-%m-%d %H:%M:%S"):
-    """
-    Convert a timestamp to formatted date string.
-
-    Args:
-        timestamp: Unix timestamp in milliseconds. If None or empty, uses current time.
-        format_string: Format string for the output date (default: "%Y-%m-%d %H:%M:%S")
-
-    Returns:
-        str: Formatted date string
-
-    Example:
-        >>> timestamp_to_date(1704067200000)
-        '2024-01-01 08:00:00'
-    """
-    if not timestamp:
-        timestamp = time.time()
-    timestamp = int(timestamp) / 1000
-    time_array = time.localtime(timestamp)
-    str_date = time.strftime(format_string, time_array)
-    return str_date
-
-
-def date_string_to_timestamp(time_str, format_string="%Y-%m-%d %H:%M:%S"):
-    """
-    Convert a date string to timestamp in milliseconds.
-
-    Args:
-        time_str: Date string to convert
-        format_string: Format of the input date string (default: "%Y-%m-%d %H:%M:%S")
-
-    Returns:
-        int: Unix timestamp in milliseconds
-
-    Example:
-        >>> date_string_to_timestamp("2024-01-01 00:00:00")
-        1704067200000
-    """
-    time_array = time.strptime(time_str, format_string)
-    time_stamp = int(time.mktime(time_array) * 1000)
-    return time_stamp
-
-def datetime_format(date_time: datetime.datetime) -> datetime.datetime:
-    """
-    Normalize a datetime object by removing microsecond component.
-
-    Creates a new datetime object with only year, month, day, hour, minute, second.
-    Microseconds are set to 0.
-
-    Args:
-        date_time: datetime object to normalize
-
-    Returns:
-        datetime.datetime: New datetime object without microseconds
-
-    Example:
-        >>> dt = datetime.datetime(2024, 1, 1, 12, 30, 45, 123456)
-        >>> datetime_format(dt)
-        datetime.datetime(2024, 1, 1, 12, 30, 45)
-    """
-    return datetime.datetime(date_time.year, date_time.month, date_time.day,
-                             date_time.hour, date_time.minute, date_time.second)
-
-
-def get_format_time() -> datetime.datetime:
-    """
-    Get current datetime normalized without microseconds.
-
-    Returns:
-        datetime.datetime: Current datetime with microseconds set to 0
-
-    Example:
-        >>> get_format_time()
-        datetime.datetime(2024, 1, 1, 12, 30, 45)
-    """
-    return datetime_format(datetime.datetime.now())
-
-
-def delta_seconds(date_string: str):
-    """
-    Calculate seconds elapsed from a given date string to now.
-
-    Args:
-        date_string: Date string in "YYYY-MM-DD HH:MM:SS" format
-
-    Returns:
-        float: Number of seconds between the given date and current time
-
-    Example:
-        >>> delta_seconds("2024-01-01 12:00:00")
-        3600.0  # If current time is 2024-01-01 13:00:00
-    """
-    dt = datetime.datetime.strptime(date_string, "%Y-%m-%d %H:%M:%S")
-    return (datetime.datetime.now() - dt).total_seconds()

conf/infinity_mapping.json

@@ -31,6 +31,7 @@
 	"entities_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
 	"pagerank_fea": {"type": "integer", "default":  0},
 	"tag_feas": {"type": "varchar", "default": "", "analyzer": "rankfeatures"},
+
 	"from_entity_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
 	"to_entity_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
 	"entity_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
@@ -38,6 +39,6 @@
 	"source_id": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
 	"n_hop_with_weight": {"type": "varchar", "default": ""},
 	"removed_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
-	"doc_type_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"},
-	"toc_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"}
+
+	"doc_type_kwd": {"type": "varchar", "default": "", "analyzer": "whitespace-#"}
 }

conf/llm_factories.json

@@ -227,8 +227,8 @@
             "llm": [
                 {
                     "llm_name": "qwen3-8b",
-                    "tags": "LLM,CHAT,128k",
-                    "max_tokens": 128000,
+                    "tags": "LLM,CHAT,131k",
+                    "max_tokens": 131000,
                     "model_type": "chat",
                     "is_tools": true
                 },
@@ -241,15 +241,15 @@
                 },
                 {
                     "llm_name": "qwen3-32b",
-                    "tags": "LLM,CHAT,128k",
-                    "max_tokens": 128000,
+                    "tags": "LLM,CHAT,131k",
+                    "max_tokens": 131000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
-                    "llm_name": "kimi-k2-instruct-0905",
-                    "tags": "LLM,CHAT,256K",
-                    "max_tokens": 256000,
+                    "llm_name": "kimi-k2-instruct",
+                    "tags": "LLM,CHAT,128K",
+                    "max_tokens": 128000,
                     "model_type": "chat",
                     "is_tools": true
                 },
@@ -280,48 +280,6 @@
                     "max_tokens": 128000,
                     "model_type": "chat",
                     "is_tools": true
-                },
-                {
-                    "llm_name": "hunyuan-a13b-instruct",
-                    "tags": "LLM,CHAT,256k",
-                    "max_tokens": 256000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "qwen3-next-80b-a3b-instruct",
-                    "tags": "LLM,CHAT,1024k",
-                    "max_tokens": 1024000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "deepseek-v3.2-exp",
-                    "tags": "LLM,CHAT,128k",
-                    "max_tokens": 128000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "deepseek-v3.1-terminus",
-                    "tags": "LLM,CHAT,128k",
-                    "max_tokens": 128000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "qwen3-vl-235b-a22b-instruct",
-                    "tags": "LLM,CHAT,262k",
-                    "max_tokens": 262000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "qwen3-vl-30b-a3b-instruct",
-                    "tags": "LLM,CHAT,262k",
-                    "max_tokens": 262000,
-                    "model_type": "chat",
-                    "is_tools": true
                 }
             ]
         },
@@ -845,12 +803,6 @@
                     "tags": "TEXT EMBEDDING",
                     "max_tokens": 512,
                     "model_type": "embedding"
-                },
-                {
-                    "llm_name": "glm-asr",
-                    "tags": "SPEECH2TEXT",
-                    "max_tokens": 4096,
-                    "model_type": "speech2text"
                 }
             ]
         },
@@ -1013,9 +965,31 @@
         {
             "name": "VolcEngine",
             "logo": "",
-            "tags": "LLM, TEXT EMBEDDING, IMAGE2TEXT",
+            "tags": "LLM, TEXT EMBEDDING",
             "status": "1",
-            "llm": []
+            "llm": [
+                {
+                    "llm_name": "Doubao-pro-128k",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 131072,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "Doubao-pro-32k",
+                    "tags": "LLM,CHAT,32k",
+                    "max_tokens": 32768,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "Doubao-pro-4k",
+                    "tags": "LLM,CHAT,4k",
+                    "max_tokens": 4096,
+                    "model_type": "chat",
+                    "is_tools": true
+                }
+            ]
         },
         {
             "name": "BaiChuan",
@@ -1154,32 +1128,6 @@
                 }
             ]
         },
-        {
-            "name": "Builtin",
-            "logo": "",
-            "tags": "TEXT EMBEDDING",
-            "status": "1",
-            "llm": [
-                {
-                    "llm_name": "BAAI/bge-small-en-v1.5",
-                    "tags": "TEXT EMBEDDING,512",
-                    "max_tokens": 512,
-                    "model_type": "embedding"
-                },
-                {
-                    "llm_name": "BAAI/bge-m3",
-                    "tags": "TEXT EMBEDDING,8k",
-                    "max_tokens": 8192,
-                    "model_type": "embedding"
-                },
-                {
-                    "llm_name": "Qwen/Qwen3-Embedding-0.6B",
-                    "tags": "TEXT EMBEDDING,32k",
-                    "max_tokens": 32768,
-                    "model_type": "embedding"
-                }
-            ]
-        },
         {
             "name": "MiniMax",
             "logo": "",
@@ -1413,35 +1361,35 @@
                     "llm_name": "gemini-2.5-flash",
                     "tags": "LLM,CHAT,1024K,IMAGE2TEXT",
                     "max_tokens": 1048576,
-                    "model_type": "image2text",
+                    "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "gemini-2.5-pro",
                     "tags": "LLM,CHAT,IMAGE2TEXT,1024K",
                     "max_tokens": 1048576,
-                    "model_type": "image2text",
+                    "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "gemini-2.5-flash-lite",
                     "tags": "LLM,CHAT,1024K,IMAGE2TEXT",
                     "max_tokens": 1048576,
-                    "model_type": "image2text",
+                    "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "gemini-2.0-flash",
                     "tags": "LLM,CHAT,1024K",
                     "max_tokens": 1048576,
-                    "model_type": "image2text",
+                    "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "gemini-2.0-flash-lite",
                     "tags": "LLM,CHAT,1024K",
                     "max_tokens": 1048576,
-                    "model_type": "image2text",
+                    "model_type": "chat",
                     "is_tools": true
                 },
                 {
@@ -2868,13 +2816,6 @@
             "tags": "LLM,TEXT EMBEDDING,TEXT RE-RANK,IMAGE2TEXT",
             "status": "1",
             "llm": [
-                {
-                    "llm_name":"THUDM/GLM-4.1V-9B-Thinking",
-                    "tags":"LLM,CHAT,IMAGE2TEXT, 64k",
-                    "max_tokens":64000,
-                    "model_type":"chat",
-                    "is_tools": false
-                },
                 {
                     "llm_name": "Qwen/Qwen3-Embedding-8B",
                     "tags": "TEXT EMBEDDING,TEXT RE-RANK,32k",
@@ -3055,7 +2996,7 @@
                     "tags": "LLM,CHAT,IMAGE2TEXT,32k",
                     "max_tokens": 32000,
                     "model_type": "image2text",
-                    "is_tools": false
+                    "is_tools": true
                 },
                 {
                     "llm_name": "THUDM/GLM-Z1-32B-0414",
@@ -3204,6 +3145,13 @@
                     "model_type": "chat",
                     "is_tools": true
                 },
+                {
+                    "llm_name": "Qwen/Qwen2-1.5B-Instruct",
+                    "tags": "LLM,CHAT,32k",
+                    "max_tokens": 32000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
                 {
                     "llm_name": "Pro/Qwen/Qwen2.5-Coder-7B-Instruct",
                     "tags": "LLM,CHAT,32k",
@@ -3211,6 +3159,13 @@
                     "model_type": "chat",
                     "is_tools": false
                 },
+                {
+                    "llm_name": "Pro/Qwen/Qwen2-VL-7B-Instruct",
+                    "tags": "LLM,CHAT,IMAGE2TEXT,32k",
+                    "max_tokens": 32000,
+                    "model_type": "image2text",
+                    "is_tools": false
+                },
                 {
                     "llm_name": "Pro/Qwen/Qwen2.5-7B-Instruct",
                     "tags": "LLM,CHAT,32k",
@@ -3578,13 +3533,6 @@
                     "model_type": "chat",
                     "is_tools": true
                 },
-                {
-                    "llm_name": "claude-sonnet-4-5-20250929",
-                    "tags": "LLM,CHAT,IMAGE2TEXT,200k",
-                    "max_tokens": 204800,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
                 {
                     "llm_name": "claude-sonnet-4-20250514",
                     "tags": "LLM,CHAT,IMAGE2TEXT,200k",
@@ -4914,282 +4862,8 @@
                     "max_tokens": 8000,
                     "model_type": "chat",
                     "is_tools": true
-                },
-                {
-                    "llm_name": "LongCat-Flash-Thinking",
-                    "tags": "LLM,CHAT,8000",
-                    "max_tokens": 8000,
-                    "model_type": "chat",
-                    "is_tools": true
-                }
-            ]
-        },
-        {
-            "name": "DeerAPI",
-            "logo": "",
-            "tags": "LLM,TEXT EMBEDDING,IMAGE2TEXT",
-            "status": "1",
-            "llm": [
-                {
-                    "llm_name": "gpt-5-chat-latest",
-                    "tags": "LLM,CHAT,400k",
-                    "max_tokens": 400000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "chatgpt-4o-latest",
-                    "tags": "LLM,CHAT,128k",
-                    "max_tokens": 128000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "gpt-5-mini",
-                    "tags": "LLM,CHAT,400k",
-                    "max_tokens": 400000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "gpt-5-nano",
-                    "tags": "LLM,CHAT,400k",
-                    "max_tokens": 400000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "gpt-5",
-                    "tags": "LLM,CHAT,400k",
-                    "max_tokens": 400000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "gpt-4.1-mini",
-                    "tags": "LLM,CHAT,1M",
-                    "max_tokens": 1047576,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "gpt-4.1-nano",
-                    "tags": "LLM,CHAT,1M",
-                    "max_tokens": 1047576,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "gpt-4.1",
-                    "tags": "LLM,CHAT,1M",
-                    "max_tokens": 1047576,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "gpt-4o-mini",
-                    "tags": "LLM,CHAT,128k",
-                    "max_tokens": 128000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "o4-mini-2025-04-16",
-                    "tags": "LLM,CHAT,200k",
-                    "max_tokens": 200000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "o3-pro-2025-06-10",
-                    "tags": "LLM,CHAT,200k",
-                    "max_tokens": 200000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "claude-opus-4-1-20250805",
-                    "tags": "LLM,CHAT,200k,IMAGE2TEXT",
-                    "max_tokens": 200000,
-                    "model_type": "image2text",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "claude-opus-4-1-20250805-thinking",
-                    "tags": "LLM,CHAT,200k,IMAGE2TEXT",
-                    "max_tokens": 200000,
-                    "model_type": "image2text",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "claude-sonnet-4-20250514",
-                    "tags": "LLM,CHAT,200k,IMAGE2TEXT",
-                    "max_tokens": 200000,
-                    "model_type": "image2text",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "claude-sonnet-4-20250514-thinking",
-                    "tags": "LLM,CHAT,200k,IMAGE2TEXT",
-                    "max_tokens": 200000,
-                    "model_type": "image2text",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "claude-3-7-sonnet-latest",
-                    "tags": "LLM,CHAT,200k",
-                    "max_tokens": 200000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "claude-3-5-haiku-latest",
-                    "tags": "LLM,CHAT,200k",
-                    "max_tokens": 200000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "gemini-2.5-pro",
-                    "tags": "LLM,CHAT,1M,IMAGE2TEXT",
-                    "max_tokens": 1000000,
-                    "model_type": "image2text",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "gemini-2.5-flash",
-                    "tags": "LLM,CHAT,1M,IMAGE2TEXT",
-                    "max_tokens": 1000000,
-                    "model_type": "image2text",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "gemini-2.5-flash-lite",
-                    "tags": "LLM,CHAT,1M,IMAGE2TEXT",
-                    "max_tokens": 1000000,
-                    "model_type": "image2text",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "gemini-2.0-flash",
-                    "tags": "LLM,CHAT,1M,IMAGE2TEXT",
-                    "max_tokens": 1000000,
-                    "model_type": "image2text",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "grok-4-0709",
-                    "tags": "LLM,CHAT,131k",
-                    "max_tokens": 131072,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "grok-3",
-                    "tags": "LLM,CHAT,131k",
-                    "max_tokens": 131072,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "grok-3-mini",
-                    "tags": "LLM,CHAT,131k",
-                    "max_tokens": 131072,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "grok-2-image-1212",
-                    "tags": "LLM,CHAT,32k,IMAGE2TEXT",
-                    "max_tokens": 32768,
-                    "model_type": "image2text",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "deepseek-v3.1",
-                    "tags": "LLM,CHAT,64k",
-                    "max_tokens": 64000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "deepseek-v3",
-                    "tags": "LLM,CHAT,64k",
-                    "max_tokens": 64000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "deepseek-r1-0528",
-                    "tags": "LLM,CHAT,164k",
-                    "max_tokens": 164000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "deepseek-chat",
-                    "tags": "LLM,CHAT,32k",
-                    "max_tokens": 32000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "deepseek-reasoner",
-                    "tags": "LLM,CHAT,64k",
-                    "max_tokens": 64000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "qwen3-30b-a3b",
-                    "tags": "LLM,CHAT,128k",
-                    "max_tokens": 128000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "qwen3-coder-plus-2025-07-22",
-                    "tags": "LLM,CHAT,128k",
-                    "max_tokens": 128000,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "text-embedding-ada-002",
-                    "tags": "TEXT EMBEDDING,8K",
-                    "max_tokens": 8191,
-                    "model_type": "embedding",
-                    "is_tools": false
-                },
-                {
-                    "llm_name": "text-embedding-3-small",
-                    "tags": "TEXT EMBEDDING,8K",
-                    "max_tokens": 8191,
-                    "model_type": "embedding",
-                    "is_tools": false
-                },
-                {
-                    "llm_name": "text-embedding-3-large",
-                    "tags": "TEXT EMBEDDING,8K",
-                    "max_tokens": 8191,
-                    "model_type": "embedding",
-                    "is_tools": false
-                },
-                {
-                    "llm_name": "whisper-1",
-                    "tags": "SPEECH2TEXT",
-                    "max_tokens": 26214400,
-                    "model_type": "speech2text",
-                    "is_tools": false
-                },
-                {
-                    "llm_name": "tts-1",
-                    "tags": "TTS",
-                    "max_tokens": 2048,
-                    "model_type": "tts",
-                    "is_tools": false
                 }
             ]
         }
     ]
-}
+}

conf/os_mapping.json

@@ -200,61 +200,6 @@
           }
         }
       },
-      {
-        "knn_vector": {
-          "match": "*_2048_vec",
-          "mapping": {
-            "type": "knn_vector",
-            "index": true,
-            "space_type": "cosinesimil",
-            "dimension": 2048
-          }
-        }
-      },
-      {
-        "knn_vector": {
-          "match": "*_4096_vec",
-          "mapping": {
-            "type": "knn_vector",
-            "index": true,
-            "space_type": "cosinesimil",
-            "dimension": 4096
-          }
-        }
-      },
-      {
-        "knn_vector": {
-          "match": "*_6144_vec",
-          "mapping": {
-            "type": "knn_vector",
-            "index": true,
-            "space_type": "cosinesimil",
-            "dimension": 6144
-          }
-        }
-      },
-      {
-        "knn_vector": {
-          "match": "*_8192_vec",
-          "mapping": {
-            "type": "knn_vector",
-            "index": true,
-            "space_type": "cosinesimil",
-            "dimension": 8192
-          }
-        }
-      },
-      {
-        "knn_vector": {
-          "match": "*_10240_vec",
-          "mapping": {
-            "type": "knn_vector",
-            "index": true,
-            "space_type": "cosinesimil",
-            "dimension": 10240
-          }
-        }
-      },
       {
         "binary": {
           "match": "*_bin",

conf/service_conf.yaml

@@ -32,11 +32,6 @@ redis:
   db: 1
   password: 'infini_rag_flow'
   host: 'localhost:6379'
-user_default_llm:
-  default_models:
-    embedding_model:
-      api_key: 'xxx'
-      base_url: 'http://localhost:6380'
 # postgres:
 #   name: 'rag_flow'
 #   user: 'rag_flow'
@@ -82,8 +77,7 @@ user_default_llm:
 #       api_key: 'xxxx'
 #       base_url: 'https://api.xx.com'
 #     embedding_model:
-#       api_key: 'xxx'
-#       base_url: 'http://localhost:6380'
+#       name: 'bge-m3'
 #     rerank_model: 'bge-reranker-v2'
 #     asr_model:
 #       model: 'whisper-large-v3' # alias of name
@@ -133,9 +127,3 @@ user_default_llm:
 #     - "RAGFlow" # display name
 #     - "" # sender email address
 #   mail_frontend_url: "https://your-frontend.example.com"
-# tcadp_config:
-#  secret_id: 'tencent_secret_id'
-#  secret_key: 'tencent_secret_key'
-#  region: 'tencent_region'
-#  table_result_type: '1'
-#  markdown_image_response_type: '1'

deepdoc/parser/docling_parser.py

@@ -1,344 +0,0 @@
-#
-#  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.
-#
-from __future__ import annotations
-
-import logging
-import re
-from dataclasses import dataclass
-from enum import Enum
-from io import BytesIO
-from os import PathLike
-from pathlib import Path
-from typing import Any, Callable, Iterable, Optional
-
-import pdfplumber
-from PIL import Image
-
-try:
-    from docling.document_converter import DocumentConverter
-except Exception:
-    DocumentConverter = None  
-
-try:
-    from deepdoc.parser.pdf_parser import RAGFlowPdfParser
-except Exception:
-    class RAGFlowPdfParser:  
-        pass
-
-
-class DoclingContentType(str, Enum):
-    IMAGE = "image"
-    TABLE = "table"
-    TEXT = "text"
-    EQUATION = "equation"
-
-
-@dataclass
-class _BBox:
-    page_no: int  
-    x0: float
-    y0: float
-    x1: float
-    y1: float
-
-
-class DoclingParser(RAGFlowPdfParser):
-    def __init__(self):
-        self.logger = logging.getLogger(self.__class__.__name__)
-        self.page_images: list[Image.Image] = []
-        self.page_from = 0
-        self.page_to = 10_000
-
-    def check_installation(self) -> bool:
-        if DocumentConverter is None:
-            self.logger.warning("[Docling] 'docling' is not importable, please: pip install docling")
-            return False
-        try:
-            _ = DocumentConverter()
-            return True
-        except Exception as e:
-            self.logger.error(f"[Docling] init DocumentConverter failed: {e}")
-            return False
-
-    def __images__(self, fnm, zoomin: int = 1, page_from=0, page_to=600, callback=None):
-        self.page_from = page_from
-        self.page_to = page_to
-        try:
-            opener = pdfplumber.open(fnm) if isinstance(fnm, (str, PathLike)) else pdfplumber.open(BytesIO(fnm))
-            with opener as pdf:
-                pages = pdf.pages[page_from:page_to]
-                self.page_images = [p.to_image(resolution=72 * zoomin, antialias=True).original for p in pages]
-        except Exception as e:
-            self.page_images = []
-            self.logger.exception(e)
-
-    def _make_line_tag(self,bbox: _BBox) -> str:
-        if bbox is None:
-            return ""
-        x0,x1, top, bott = bbox.x0, bbox.x1, bbox.y0, bbox.y1
-        if hasattr(self, "page_images") and self.page_images and len(self.page_images) >= bbox.page_no:
-            _, page_height = self.page_images[bbox.page_no-1].size
-            top, bott = page_height-top ,page_height-bott
-        return "@@{}\t{:.1f}\t{:.1f}\t{:.1f}\t{:.1f}##".format(
-            bbox.page_no, x0,x1, top, bott
-        )
-
-    @staticmethod
-    def extract_positions(txt: str) -> list[tuple[list[int], float, float, float, float]]:
-        poss = []
-        for tag in re.findall(r"@@[0-9-]+\t[0-9.\t]+##", txt):
-            pn, left, right, top, bottom = tag.strip("#").strip("@").split("\t")
-            left, right, top, bottom = float(left), float(right), float(top), float(bottom)
-            poss.append(([int(p) - 1 for p in pn.split("-")], left, right, top, bottom))
-        return poss
-
-    def crop(self, text: str, ZM: int = 1, need_position: bool = False):
-        imgs = []
-        poss = self.extract_positions(text)
-        if not poss:
-            return (None, None) if need_position else None
-
-        GAP = 6
-        pos = poss[0]
-        poss.insert(0, ([pos[0][0]], pos[1], pos[2], max(0, pos[3] - 120), max(pos[3] - GAP, 0)))
-        pos = poss[-1]
-        poss.append(([pos[0][-1]], pos[1], pos[2], min(self.page_images[pos[0][-1]].size[1], pos[4] + GAP), min(self.page_images[pos[0][-1]].size[1], pos[4] + 120)))
-        positions = []
-        for ii, (pns, left, right, top, bottom) in enumerate(poss):
-            if bottom <= top:
-                bottom = top + 4
-            img0 = self.page_images[pns[0]]
-            x0, y0, x1, y1 = int(left), int(top), int(right), int(min(bottom, img0.size[1]))
-            
-            crop0 = img0.crop((x0, y0, x1, y1))
-            imgs.append(crop0)
-            if 0 < ii < len(poss)-1:
-                positions.append((pns[0] + self.page_from, x0, x1, y0, y1))
-            remain_bottom = bottom - img0.size[1]
-            for pn in pns[1:]:
-                if remain_bottom <= 0:
-                    break
-                page = self.page_images[pn]
-                x0, y0, x1, y1 = int(left), 0, int(right), int(min(remain_bottom, page.size[1]))
-                cimgp = page.crop((x0, y0, x1, y1))
-                imgs.append(cimgp)
-                if 0 < ii < len(poss) - 1:
-                    positions.append((pn + self.page_from, x0, x1, y0, y1))
-                remain_bottom -= page.size[1]
-
-        if not imgs:
-            return (None, None) if need_position else None
-
-        height = sum(i.size[1] + GAP for i in imgs)
-        width = max(i.size[0] for i in imgs)
-        pic = Image.new("RGB", (width, int(height)), (245, 245, 245))
-        h = 0
-        for ii, img in enumerate(imgs):
-            if ii == 0 or ii + 1 == len(imgs):
-                img = img.convert("RGBA")
-                overlay = Image.new("RGBA", img.size, (0, 0, 0, 0))
-                overlay.putalpha(128)
-                img = Image.alpha_composite(img, overlay).convert("RGB")
-            pic.paste(img, (0, int(h)))
-            h += img.size[1] + GAP
-
-        return (pic, positions) if need_position else pic
-
-    def _iter_doc_items(self, doc) -> Iterable[tuple[str, Any, Optional[_BBox]]]:
-        for t in getattr(doc, "texts", []):
-            parent=getattr(t, "parent", "")
-            ref=getattr(parent,"cref","")
-            label=getattr(t, "label", "")
-            if (label in ("section_header","text",) and ref in ("#/body",)) or label in ("list_item",):
-                text = getattr(t, "text", "") or ""
-                bbox = None
-                if getattr(t, "prov", None):
-                    pn = getattr(t.prov[0], "page_no", None)
-                    bb = getattr(t.prov[0], "bbox", None)
-                    bb = [getattr(bb, "l", None),getattr(bb, "t", None),getattr(bb, "r", None),getattr(bb, "b", None)]
-                    if pn and bb and len(bb) == 4:
-                        bbox = _BBox(page_no=int(pn), x0=bb[0], y0=bb[1], x1=bb[2], y1=bb[3])
-                yield (DoclingContentType.TEXT.value, text, bbox)
-
-        for item in getattr(doc, "texts", []):
-            if getattr(item, "label", "") in ("FORMULA",):
-                text = getattr(item, "text", "") or ""
-                bbox = None
-                if getattr(item, "prov", None):
-                    pn = getattr(item.prov, "page_no", None)
-                    bb = getattr(item.prov, "bbox", None)
-                    bb = [getattr(bb, "l", None),getattr(bb, "t", None),getattr(bb, "r", None),getattr(bb, "b", None)]
-                    if pn and bb and len(bb) == 4:
-                        bbox = _BBox(int(pn), bb[0], bb[1], bb[2], bb[3])
-                yield (DoclingContentType.EQUATION.value, text, bbox)
-
-    def _transfer_to_sections(self, doc) -> list[tuple[str, str]]:
-        """
-        和 MinerUParser 保持一致：返回 [(section_text, line_tag), ...]
-        """
-        sections: list[tuple[str, str]] = []
-        for typ, payload, bbox in self._iter_doc_items(doc):
-            if typ == DoclingContentType.TEXT.value:
-                section = payload.strip()
-                if not section:
-                    continue
-            elif typ == DoclingContentType.EQUATION.value:
-                section = payload.strip()
-            else:
-                continue
-            
-            tag = self._make_line_tag(bbox) if isinstance(bbox,_BBox) else ""
-            sections.append((section, tag))
-        return sections
-
-    def cropout_docling_table(self, page_no: int, bbox: tuple[float, float, float, float], zoomin: int = 1):
-        if not getattr(self, "page_images", None):
-            return None, ""
-
-        idx = (page_no - 1) - getattr(self, "page_from", 0)
-        if idx < 0 or idx >= len(self.page_images):
-            return None, ""
-
-        page_img = self.page_images[idx]
-        W, H = page_img.size
-        left, top, right, bott = bbox
-
-        x0 = float(left)
-        y0 = float(H-top)
-        x1 = float(right)
-        y1 = float(H-bott)
-
-        x0, y0 = max(0.0, min(x0, W - 1)), max(0.0, min(y0, H - 1))
-        x1, y1 = max(x0 + 1.0, min(x1, W)), max(y0 + 1.0, min(y1, H))
-
-        try:
-            crop = page_img.crop((int(x0), int(y0), int(x1), int(y1))).convert("RGB")
-        except Exception:
-            return None, ""
-
-        pos = (page_no-1 if page_no>0 else 0, x0, x1, y0, y1)
-        return crop, [pos]
-
-    def _transfer_to_tables(self, doc):
-        tables = []
-        for tab in getattr(doc, "tables", []):
-            img = None
-            positions = ""
-            if getattr(tab, "prov", None):
-                pn = getattr(tab.prov[0], "page_no", None)
-                bb = getattr(tab.prov[0], "bbox", None)
-                if pn is not None and bb is not None:
-                    left = getattr(bb, "l", None)
-                    top = getattr(bb, "t", None)
-                    right = getattr(bb, "r", None)
-                    bott = getattr(bb, "b", None)
-                    if None not in (left, top, right, bott):
-                        img, positions = self.cropout_docling_table(int(pn), (float(left), float(top), float(right), float(bott)))
-            html = ""
-            try:
-                html = tab.export_to_html(doc=doc)
-            except Exception:
-                pass
-            tables.append(((img, html), positions if positions else ""))
-        for pic in getattr(doc, "pictures", []):
-            img = None
-            positions = ""
-            if getattr(pic, "prov", None):
-                pn = getattr(pic.prov[0], "page_no", None)
-                bb = getattr(pic.prov[0], "bbox", None)
-                if pn is not None and bb is not None:
-                    left = getattr(bb, "l", None)
-                    top = getattr(bb, "t", None)
-                    right = getattr(bb, "r", None)
-                    bott = getattr(bb, "b", None)
-                    if None not in (left, top, right, bott):
-                        img, positions = self.cropout_docling_table(int(pn), (float(left), float(top), float(right), float(bott)))
-            captions = ""
-            try:
-                captions = pic.caption_text(doc=doc)
-            except Exception:
-                pass
-            tables.append(((img, [captions]), positions if positions else ""))
-        return tables
-
-    def parse_pdf(
-        self,
-        filepath: str | PathLike[str],
-        binary: BytesIO | bytes | None = None,
-        callback: Optional[Callable] = None,
-        *,
-        output_dir: Optional[str] = None, 
-        lang: Optional[str] = None,        
-        method: str = "auto",             
-        delete_output: bool = True,       
-    ):
-
-        if not self.check_installation():
-            raise RuntimeError("Docling not available, please install `docling`")
-
-        if binary is not None:
-            tmpdir = Path(output_dir) if output_dir else Path.cwd() / ".docling_tmp"
-            tmpdir.mkdir(parents=True, exist_ok=True)
-            name = Path(filepath).name or "input.pdf"
-            tmp_pdf = tmpdir / name
-            with open(tmp_pdf, "wb") as f:
-                if isinstance(binary, (bytes, bytearray)):
-                    f.write(binary)
-                else:
-                    f.write(binary.getbuffer())
-            src_path = tmp_pdf
-        else:
-            src_path = Path(filepath)
-            if not src_path.exists():
-                raise FileNotFoundError(f"PDF not found: {src_path}")
-
-        if callback:
-            callback(0.1, f"[Docling] Converting: {src_path}")
-
-        try:
-            self.__images__(str(src_path), zoomin=1)
-        except Exception as e:
-            self.logger.warning(f"[Docling] render pages failed: {e}")
-
-        conv = DocumentConverter()  
-        conv_res = conv.convert(str(src_path))
-        doc = conv_res.document
-        if callback:
-            callback(0.7, f"[Docling] Parsed doc: {getattr(doc, 'num_pages', 'n/a')} pages")
-
-        sections = self._transfer_to_sections(doc)
-        tables = self._transfer_to_tables(doc)
-
-        if callback:
-            callback(0.95, f"[Docling] Sections: {len(sections)}, Tables: {len(tables)}")
-
-        if binary is not None and delete_output:
-            try:
-                Path(src_path).unlink(missing_ok=True)
-            except Exception:
-                pass
-
-        if callback:
-            callback(1.0, "[Docling] Done.")
-        return sections, tables
-
-
-if __name__ == "__main__":
-    logging.basicConfig(level=logging.INFO)
-    parser = DoclingParser()
-    print("Docling available:", parser.check_installation())
-    sections, tables = parser.parse_pdf(filepath="test_docling/toc.pdf", binary=None)
-    print(len(sections), len(tables))

deepdoc/parser/excel_parser.py

@@ -54,8 +54,8 @@ class RAGFlowExcelParser:
             try:
                 file_like_object.seek(0)
                 try:
-                    dfs = pd.read_excel(file_like_object, sheet_name=None)
-                    return RAGFlowExcelParser._dataframe_to_workbook(dfs)
+                    df = pd.read_excel(file_like_object)
+                    return RAGFlowExcelParser._dataframe_to_workbook(df)
                 except Exception as ex:
                     logging.info(f"pandas with default engine load error: {ex}, try calamine instead")
                     file_like_object.seek(0)
@@ -75,10 +75,6 @@ class RAGFlowExcelParser:
 
     @staticmethod
     def _dataframe_to_workbook(df):
-        # if contains multiple sheets use _dataframes_to_workbook
-        if isinstance(df, dict) and len(df) > 1:
-            return RAGFlowExcelParser._dataframes_to_workbook(df)
-
         df = RAGFlowExcelParser._clean_dataframe(df)
         wb = Workbook()
         ws = wb.active
@@ -92,22 +88,6 @@ class RAGFlowExcelParser:
                 ws.cell(row=row_num, column=col_num, value=value)
 
         return wb
-    
-    @staticmethod
-    def _dataframes_to_workbook(dfs: dict):
-        wb = Workbook()
-        default_sheet = wb.active
-        wb.remove(default_sheet)
-        
-        for sheet_name, df in dfs.items():
-            df = RAGFlowExcelParser._clean_dataframe(df)
-            ws = wb.create_sheet(title=sheet_name)
-            for col_num, column_name in enumerate(df.columns, 1):
-                ws.cell(row=1, column=col_num, value=column_name)
-            for row_num, row in enumerate(df.values, 2):
-                for col_num, value in enumerate(row, 1):
-                    ws.cell(row=row_num, column=col_num, value=value)
-        return wb
 
     def html(self, fnm, chunk_rows=256):
         from html import escape
@@ -123,12 +103,7 @@ class RAGFlowExcelParser:
 
         for sheetname in wb.sheetnames:
             ws = wb[sheetname]
-            try:
-                rows = list(ws.rows)
-            except Exception as e:
-                logging.warning(f"Skip sheet '{sheetname}' due to rows access error: {e}")
-                continue
-
+            rows = list(ws.rows)
             if not rows:
                 continue
 
@@ -175,11 +150,7 @@ class RAGFlowExcelParser:
         res = []
         for sheetname in wb.sheetnames:
             ws = wb[sheetname]
-            try:
-                rows = list(ws.rows)
-            except Exception as e:
-                logging.warning(f"Skip sheet '{sheetname}' due to rows access error: {e}")
-                continue
+            rows = list(ws.rows)
             if not rows:
                 continue
             ti = list(rows[0])
@@ -202,14 +173,9 @@ class RAGFlowExcelParser:
         if fnm.split(".")[-1].lower().find("xls") >= 0:
             wb = RAGFlowExcelParser._load_excel_to_workbook(BytesIO(binary))
             total = 0
-            
             for sheetname in wb.sheetnames:
-               try:
-                   ws = wb[sheetname]
-                   total += len(list(ws.rows))
-               except Exception as e:
-                   logging.warning(f"Skip sheet '{sheetname}' due to rows access error: {e}")
-                   continue
+                ws = wb[sheetname]
+                total += len(list(ws.rows))
             return total
 
         if fnm.split(".")[-1].lower() in ["csv", "txt"]: