Fix: order chunks from docx by positions. (#7979) #7124
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| 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: Show who triggered this workflow | |
| run: | | |
| echo "Workflow triggered by ${{ github.event_name }}" | |
| - name: Ensure workspace ownership | |
| run: echo "chown -R $USER $GITHUB_WORKSPACE" && sudo chown -R $USER $GITHUB_WORKSPACE | |
| # https://github.com/actions/checkout/issues/1781 | |
| - name: Check out code | |
| uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 | |
| fetch-tags: true | |
| # https://github.com/astral-sh/ruff-action | |
| - name: Static check with Ruff | |
| uses: astral-sh/ruff-action@v3 | |
| with: | |
| version: ">=0.11.x" | |
| args: "check" | |
| - name: Build ragflow:nightly-slim | |
| run: | | |
| RUNNER_WORKSPACE_PREFIX=${RUNNER_WORKSPACE_PREFIX:-$HOME} | |
| sudo docker pull ubuntu:22.04 | |
| 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: | | |
| 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: | | |
| 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="" | |
| 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 | |
| cd sdk/python && uv sync --python 3.10 --group test --frozen && uv pip install . && source .venv/bin/activate && cd test/test_sdk_api && pytest -s --tb=short get_email.py t_dataset.py t_chat.py t_session.py t_document.py t_chunk.py | |
| - 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-server curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do | |
| echo "Waiting for service to be available..." | |
| sleep 5 | |
| done | |
| cd sdk/python && uv 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="" | |
| 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 | |
| if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then | |
| export HTTP_API_TEST_LEVEL=p3 | |
| else | |
| export HTTP_API_TEST_LEVEL=p2 | |
| fi | |
| cd sdk/python && uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_http_api && pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} | |
| - name: Stop ragflow:nightly | |
| if: always() # always run this step even if previous steps failed | |
| run: | | |
| sudo docker compose -f docker/docker-compose.yml down -v | |
| - name: Start ragflow:nightly | |
| run: | | |
| 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="" | |
| 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 | |
| cd sdk/python && uv sync --python 3.10 --group test --frozen && uv pip install . && source .venv/bin/activate && cd test/test_sdk_api && pytest -s --tb=short get_email.py t_dataset.py t_chat.py t_session.py t_document.py t_chunk.py | |
| - 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-server curl -s --connect-timeout 5 ${HOST_ADDRESS} > /dev/null; do | |
| echo "Waiting for service to be available..." | |
| sleep 5 | |
| done | |
| cd sdk/python && uv 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="" | |
| 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 | |
| if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then | |
| export HTTP_API_TEST_LEVEL=p3 | |
| else | |
| export HTTP_API_TEST_LEVEL=p2 | |
| fi | |
| cd sdk/python && uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_http_api && DOC_ENGINE=infinity pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} | |
| - name: Stop ragflow:nightly | |
| if: always() # always run this step even if previous steps failed | |
| run: | | |
| sudo DOC_ENGINE=infinity docker compose -f docker/docker-compose.yml down -v |