feat: Extractive QA answer deduplication #10638
Workflow file for this run
This file contains 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
| # If you change this name also do it in tests_skipper.yml and ci_metrics.yml | |
| name: Tests | |
| on: | |
| workflow_dispatch: # Activate this workflow manually | |
| push: | |
| branches: | |
| - main | |
| # release branches have the form v1.9.x | |
| - "v[0-9].*[0-9].x" | |
| - "!haystack/core/**/*.py" | |
| pull_request: | |
| types: | |
| - opened | |
| - reopened | |
| - synchronize | |
| - ready_for_review | |
| paths: | |
| - "haystack/**/*.py" | |
| - "test/**/*.py" | |
| - "!haystack/core/**/*.py" | |
| env: | |
| OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} | |
| CORE_AZURE_CS_ENDPOINT: ${{ secrets.CORE_AZURE_CS_ENDPOINT }} | |
| CORE_AZURE_CS_API_KEY: ${{ secrets.CORE_AZURE_CS_API_KEY }} | |
| PYTHON_VERSION: "3.8" | |
| jobs: | |
| black: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: ${{ env.PYTHON_VERSION }} | |
| - name: Install Black | |
| run: | | |
| pip install --upgrade pip | |
| pip install .[dev] | |
| - name: Check status | |
| run: | | |
| if ! black . --check; then | |
| git status | |
| exit 1 | |
| fi | |
| - name: Calculate alert data | |
| id: calculator | |
| shell: bash | |
| if: (success() || failure()) && github.ref_name == 'main' | |
| run: | | |
| if [ "${{ job.status }}" = "success" ]; then | |
| echo "alert_type=success" >> "$GITHUB_OUTPUT"; | |
| else | |
| echo "alert_type=error" >> "$GITHUB_OUTPUT"; | |
| fi | |
| - name: Send event to Datadog | |
| if: (success() || failure()) && github.ref_name == 'main' | |
| uses: masci/datadog@v1 | |
| with: | |
| api-key: ${{ secrets.CORE_DATADOG_API_KEY }} | |
| api-url: https://api.datadoghq.eu | |
| events: | | |
| - title: "${{ github.workflow }} workflow" | |
| text: "Job ${{ github.job }} in branch ${{ github.ref_name }}" | |
| alert_type: "${{ steps.calculator.outputs.alert_type }}" | |
| source_type_name: "Github" | |
| host: ${{ github.repository_owner }} | |
| tags: | |
| - "project:${{ github.repository }}" | |
| - "job:${{ github.job }}" | |
| - "run_id:${{ github.run_id }}" | |
| - "workflow:${{ github.workflow }}" | |
| - "branch:${{ github.ref_name }}" | |
| - "url:https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}" | |
| unit-tests: | |
| name: Unit / ${{ matrix.os }} | |
| needs: black | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| os: | |
| - ubuntu-latest | |
| - windows-latest | |
| - macos-latest | |
| runs-on: ${{ matrix.os }} | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: ${{ env.PYTHON_VERSION }} | |
| - name: Install Haystack | |
| run: pip install .[dev,audio] langdetect transformers[torch,sentencepiece]==4.35.2 'sentence-transformers>=2.2.0' pypdf markdown-it-py mdit_plain tika 'azure-ai-formrecognizer>=3.2.0b2' boilerpy3 | |
| - name: Run | |
| run: pytest -m "not integration" test | |
| - name: Calculate alert data | |
| id: calculator | |
| shell: bash | |
| if: (success() || failure()) && github.ref_name == 'main' | |
| run: | | |
| if [ "${{ job.status }}" = "success" ]; then | |
| echo "alert_type=success" >> "$GITHUB_OUTPUT"; | |
| else | |
| echo "alert_type=error" >> "$GITHUB_OUTPUT"; | |
| fi | |
| - name: Send event to Datadog | |
| if: (success() || failure()) && github.ref_name == 'main' | |
| uses: masci/datadog@v1 | |
| with: | |
| api-key: ${{ secrets.CORE_DATADOG_API_KEY }} | |
| api-url: https://api.datadoghq.eu | |
| events: | | |
| - title: "${{ github.workflow }} workflow" | |
| text: "Job ${{ github.job }} in branch ${{ github.ref_name }}" | |
| alert_type: "${{ steps.calculator.outputs.alert_type }}" | |
| source_type_name: "Github" | |
| host: ${{ github.repository_owner }} | |
| tags: | |
| - "project:${{ github.repository }}" | |
| - "job:${{ github.job }}" | |
| - "run_id:${{ github.run_id }}" | |
| - "workflow:${{ github.workflow }}" | |
| - "branch:${{ github.ref_name }}" | |
| - "url:https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}" | |
| integration-tests-linux: | |
| name: Integration / ubuntu-latest | |
| needs: unit-tests | |
| runs-on: ubuntu-latest | |
| services: | |
| tika: | |
| image: apache/tika:2.9.0.0 | |
| ports: | |
| - 9998:9998 | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: ${{ env.PYTHON_VERSION }} | |
| - name: Install dependencies | |
| run: | | |
| sudo apt update | |
| sudo apt install ffmpeg # for local Whisper tests | |
| - name: Install Haystack | |
| run: pip install .[dev,audio] langdetect transformers[torch,sentencepiece]==4.35.2 'sentence-transformers>=2.2.0' pypdf markdown-it-py mdit_plain tika 'azure-ai-formrecognizer>=3.2.0b2' boilerpy3 | |
| - name: Run | |
| run: pytest --maxfail=5 -m "integration" test | |
| - name: Calculate alert data | |
| id: calculator | |
| shell: bash | |
| if: (success() || failure()) && github.ref_name == 'main' | |
| run: | | |
| if [ "${{ job.status }}" = "success" ]; then | |
| echo "alert_type=success" >> "$GITHUB_OUTPUT"; | |
| else | |
| echo "alert_type=error" >> "$GITHUB_OUTPUT"; | |
| fi | |
| - name: Send event to Datadog | |
| if: (success() || failure()) && github.ref_name == 'main' | |
| uses: masci/datadog@v1 | |
| with: | |
| api-key: ${{ secrets.CORE_DATADOG_API_KEY }} | |
| api-url: https://api.datadoghq.eu | |
| events: | | |
| - title: "${{ github.workflow }} workflow" | |
| text: "Job ${{ github.job }} in branch ${{ github.ref_name }}" | |
| alert_type: "${{ steps.calculator.outputs.alert_type }}" | |
| source_type_name: "Github" | |
| host: ${{ github.repository_owner }} | |
| tags: | |
| - "project:${{ github.repository }}" | |
| - "job:${{ github.job }}" | |
| - "run_id:${{ github.run_id }}" | |
| - "workflow:${{ github.workflow }}" | |
| - "branch:${{ github.ref_name }}" | |
| - "url:https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}" | |
| integration-tests-macos: | |
| name: Integration / macos-latest | |
| needs: unit-tests | |
| runs-on: macos-latest | |
| env: | |
| HAYSTACK_MPS_ENABLED: false | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: ${{ env.PYTHON_VERSION }} | |
| - name: Install dependencies | |
| run: | | |
| brew install ffmpeg # for local Whisper tests | |
| brew install docker | |
| colima start | |
| - name: Install Haystack | |
| run: pip install .[dev,audio] langdetect transformers[torch,sentencepiece]==4.35.2 'sentence-transformers>=2.2.0' pypdf markdown-it-py mdit_plain tika 'azure-ai-formrecognizer>=3.2.0b2' boilerpy3 | |
| - name: Run Tika | |
| run: docker run -d -p 9998:9998 apache/tika:2.9.0.0 | |
| - name: Run | |
| run: pytest --maxfail=5 -m "integration" test | |
| - name: Calculate alert data | |
| id: calculator | |
| shell: bash | |
| if: (success() || failure()) && github.ref_name == 'main' | |
| run: | | |
| if [ "${{ job.status }}" = "success" ]; then | |
| echo "alert_type=success" >> "$GITHUB_OUTPUT"; | |
| else | |
| echo "alert_type=error" >> "$GITHUB_OUTPUT"; | |
| fi | |
| - name: Send event to Datadog | |
| if: (success() || failure()) && github.ref_name == 'main' | |
| uses: masci/datadog@v1 | |
| with: | |
| api-key: ${{ secrets.CORE_DATADOG_API_KEY }} | |
| api-url: https://api.datadoghq.eu | |
| events: | | |
| - title: "${{ github.workflow }} workflow" | |
| text: "Job ${{ github.job }} in branch ${{ github.ref_name }}" | |
| alert_type: "${{ steps.calculator.outputs.alert_type }}" | |
| source_type_name: "Github" | |
| host: ${{ github.repository_owner }} | |
| tags: | |
| - "project:${{ github.repository }}" | |
| - "job:${{ github.job }}" | |
| - "run_id:${{ github.run_id }}" | |
| - "workflow:${{ github.workflow }}" | |
| - "branch:${{ github.ref_name }}" | |
| - "url:https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}" | |
| integration-tests-windows: | |
| name: Integration / windows-latest | |
| needs: unit-tests | |
| runs-on: windows-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: ${{ env.PYTHON_VERSION }} | |
| - name: Install Haystack | |
| run: pip install .[dev,audio] langdetect transformers[torch,sentencepiece]==4.35.2 'sentence-transformers>=2.2.0' pypdf markdown-it-py mdit_plain tika 'azure-ai-formrecognizer>=3.2.0b2' boilerpy3 | |
| - name: Run | |
| run: pytest --maxfail=5 -m "integration" test -k 'not tika' | |
| - name: Calculate alert data | |
| id: calculator | |
| shell: bash | |
| if: (success() || failure()) && github.ref_name == 'main' | |
| run: | | |
| if [ "${{ job.status }}" = "success" ]; then | |
| echo "alert_type=success" >> "$GITHUB_OUTPUT"; | |
| else | |
| echo "alert_type=error" >> "$GITHUB_OUTPUT"; | |
| fi | |
| - name: Send event to Datadog | |
| if: (success() || failure()) && github.ref_name == 'main' | |
| uses: masci/datadog@v1 | |
| with: | |
| api-key: ${{ secrets.CORE_DATADOG_API_KEY }} | |
| api-url: https://api.datadoghq.eu | |
| events: | | |
| - title: "${{ github.workflow }} workflow" | |
| text: "Job ${{ github.job }} in branch ${{ github.ref_name }}" | |
| alert_type: "${{ steps.calculator.outputs.alert_type }}" | |
| source_type_name: "Github" | |
| host: ${{ github.repository_owner }} | |
| tags: | |
| - "project:${{ github.repository }}" | |
| - "job:${{ github.job }}" | |
| - "run_id:${{ github.run_id }}" | |
| - "workflow:${{ github.workflow }}" | |
| - "branch:${{ github.ref_name }}" | |
| - "url:https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}" | |
| catch-all: | |
| name: Catch-all check | |
| runs-on: ubuntu-latest | |
| # This job will be executed only after all the other tests | |
| # are successful. | |
| # This way we'll be able to mark only this test as required | |
| # and skip it accordingly. | |
| needs: | |
| - integration-tests-linux | |
| - integration-tests-macos | |
| - integration-tests-windows | |
| steps: | |
| - name: Finisher | |
| run: echo "Finish him!" |