ragflow/.github/workflows/tests.yml

name: tests

on:
  push:
    branches:
      - 'main'
      - '*.*.*'
    paths-ignore:
      - 'docs/**'
      - '*.md'
      - '*.mdx'
  pull_request:
    types: [ opened, synchronize, reopened, labeled ]
    paths-ignore:
      - 'docs/**'
      - '*.md'
      - '*.mdx'
  schedule:
    - cron: '0 16 * * *'  # This schedule runs every 16:00:00Z(00:00:00+08:00)

# https://docs.github.com/en/actions/using-jobs/using-concurrency
concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true

jobs:
  ragflow_tests:
    name: ragflow_tests
    # https://docs.github.com/en/actions/using-jobs/using-conditions-to-control-job-execution
    # https://github.com/orgs/community/discussions/26261
    if: ${{ github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'ci') }}
    runs-on: [ "self-hosted", "debug" ]
    steps:
      # https://github.com/hmarr/debug-action
      #- uses: hmarr/debug-action@v2

      - name: Ensure workspace ownership
        run: |
          echo "Workflow triggered by ${{ github.event_name }}"
          echo "chown -R $USER $GITHUB_WORKSPACE" && sudo chown -R $USER $GITHUB_WORKSPACE

      # https://github.com/actions/checkout/issues/1781
      - name: Check out code
        uses: actions/checkout@v4
        with:
          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
        with:
          version: ">=0.11.x"
          args: "check"

      - name: Build ragflow:nightly
        run: |
          RUNNER_WORKSPACE_PREFIX=${RUNNER_WORKSPACE_PREFIX:-$HOME}
          sudo docker pull ubuntu:22.04
          sudo DOCKER_BUILDKIT=1 docker build --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly .
          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

      - name: Start ragflow:nightly
        run: |
          echo -e "\nCOMPOSE_PROFILES=\${COMPOSE_PROFILES},tei-cpu" >> docker/.env
          echo -e "\nTEI_MODEL=BAAI/bge-small-en-v1.5" >> docker/.env
          echo -e "\nRAGFLOW_IMAGE=infiniflow/ragflow:nightly" >> docker/.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

      - name: Run sdk tests against Elasticsearch
        run: |
          export http_proxy=""; export https_proxy=""; export no_proxy=""; export HTTP_PROXY=""; export HTTPS_PROXY=""; export NO_PROXY=""
          export HOST_ADDRESS=http://host.docker.internal:9380
          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
            echo "Waiting for service to be available..."
            sleep 5
          done
          source .venv/bin/activate && pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_sdk_api

      - name: Run frontend api tests against Elasticsearch
        run: |
          export http_proxy=""; export https_proxy=""; export no_proxy=""; export HTTP_PROXY=""; export HTTPS_PROXY=""; export NO_PROXY=""
          export HOST_ADDRESS=http://host.docker.internal:9380
          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
            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
          
      - name: Run http api tests against Elasticsearch
        run: |
          export http_proxy=""; export https_proxy=""; export no_proxy=""; export HTTP_PROXY=""; export HTTPS_PROXY=""; export NO_PROXY=""
          export HOST_ADDRESS=http://host.docker.internal:9380
          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
            echo "Waiting for service to be available..."
            sleep 5
          done
          source .venv/bin/activate && pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_http_api

      - 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

      - 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

      - name: Run sdk tests against Infinity
        run: |
          export http_proxy=""; export https_proxy=""; export no_proxy=""; export HTTP_PROXY=""; export HTTPS_PROXY=""; export NO_PROXY=""
          export HOST_ADDRESS=http://host.docker.internal:9380
          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
            echo "Waiting for service to be available..."
            sleep 5
          done
          source .venv/bin/activate && DOC_ENGINE=infinity pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_sdk_api

      - name: Run frontend api tests against Infinity
        run: |
          export http_proxy=""; export https_proxy=""; export no_proxy=""; export HTTP_PROXY=""; export HTTPS_PROXY=""; export NO_PROXY=""
          export HOST_ADDRESS=http://host.docker.internal:9380
          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
            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

      - name: Run http api tests against Infinity
        run: |
          export http_proxy=""; export https_proxy=""; export no_proxy=""; export HTTP_PROXY=""; export HTTPS_PROXY=""; export NO_PROXY=""
          export HOST_ADDRESS=http://host.docker.internal:9380
          until sudo docker exec ${RAGFLOW_CONTAINER} curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do
            echo "Waiting for service to be available..."
            sleep 5
          done
          source .venv/bin/activate && DOC_ENGINE=infinity pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_http_api

      - 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