Make TREC CAsT evaluation tractable and publish Gemini baseline #19
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: CI | |
| "on": | |
| push: | |
| branches: [main] | |
| pull_request: | |
| branches: [main] | |
| workflow_dispatch: | |
| permissions: | |
| contents: read | |
| actions: read | |
| concurrency: | |
| group: ci-${{ github.workflow }}-${{ github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| base: | |
| name: base package | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v7 | |
| - uses: actions/setup-python@v6 | |
| with: | |
| python-version: "3.12" | |
| - name: Install | |
| run: | | |
| python -m pip install --upgrade pip | |
| python -m pip install -e ".[dev]" | |
| - name: Test | |
| run: | | |
| python -m pytest \ | |
| tests/test_decoder.py \ | |
| tests/test_graph_and_scoring.py \ | |
| tests/test_retrieval.py \ | |
| tests/test_section_graph.py \ | |
| tests/test_trace_render.py | |
| - name: Examples | |
| run: | | |
| for example in examples/*.py; do | |
| python "$example" | |
| done | |
| test: | |
| name: test (py${{ matrix.python-version }}) | |
| runs-on: ubuntu-latest | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| python-version: ["3.10", "3.11", "3.12"] | |
| steps: | |
| - uses: actions/checkout@v7 | |
| - uses: actions/setup-python@v6 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| cache: pip | |
| cache-dependency-path: pyproject.toml | |
| - name: Install | |
| run: | | |
| python -m pip install --upgrade pip | |
| python -m pip install -e ".[dev,faiss]" | |
| - name: Test | |
| run: python -m pytest | |
| quality: | |
| name: quality | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v7 | |
| - uses: actions/setup-python@v6 | |
| with: | |
| python-version: "3.12" | |
| cache: pip | |
| cache-dependency-path: pyproject.toml | |
| - name: Install | |
| run: | | |
| python -m pip install --upgrade pip | |
| python -m pip install -e ".[dev,faiss]" | |
| - name: Lint | |
| run: python -m ruff check . | |
| - name: Format | |
| run: python -m ruff format --check . | |
| - name: Types | |
| run: python -m mypy | |
| - name: Build | |
| run: python -m build | |
| - name: Examples | |
| run: | | |
| for example in examples/*.py; do | |
| python "$example" | |
| done | |
| cmg-parity: | |
| name: cmg parity | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v7 | |
| - uses: actions/setup-python@v6 | |
| with: | |
| python-version: "3.12" | |
| cache: pip | |
| cache-dependency-path: pyproject.toml | |
| - name: Install | |
| run: | | |
| python -m pip install --upgrade pip | |
| python -m pip install -e ".[dev]" | |
| python -m pip install \ | |
| "composable-model-graph @ git+https://github.com/operatorstack/composable-model-graph.git@62ec13b#subdirectory=python" | |
| - name: Parity test | |
| run: python -m pytest tests/test_decoder.py -k optional_cmg | |
| - name: CMG example | |
| run: python examples/03_cmg_inspectable_run.py | |
| eval-offline: | |
| name: eval offline | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v7 | |
| - uses: actions/setup-python@v6 | |
| with: | |
| python-version: "3.12" | |
| cache: pip | |
| cache-dependency-path: pyproject.toml | |
| - name: Install | |
| run: | | |
| python -m pip install --upgrade pip | |
| python -m pip install -e ".[dev,eval,graph]" | |
| - name: Eval tests | |
| run: python -m pytest tests/test_eval_*.py | |
| - name: Eval demo | |
| run: python examples/05_eval_demo.py |