fix: await async memory search endpoint #39
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: runledger | |
| on: | |
| workflow_dispatch: | |
| pull_request: | |
| branches: [ main ] | |
| jobs: | |
| runledger: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.11" | |
| - name: Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| python -m pip install runledger | |
| python -m pip install . | |
| - name: Run deterministic evals (replay) | |
| run: | | |
| runledger run evals/runledger --mode replay --baseline baselines/runledger-openchatbi.json | |
| - name: Upload artifacts | |
| if: always() | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: runledger-artifacts | |
| path: runledger_out/** | |
| judge: | |
| # Non-gating LLM-as-Judge run (manual only). Never blocks PR merges: | |
| # only runs on explicit dispatch, and uploads a report artifact. | |
| if: github.event_name == 'workflow_dispatch' | |
| runs-on: ubuntu-latest | |
| continue-on-error: true | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.11" | |
| - name: Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| python -m pip install ".[eval]" | |
| - name: Run LLM-as-Judge over gold corpus | |
| env: | |
| OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} | |
| run: | | |
| python -m evals.judge.run_judge --cases evals/judge/example_cases --out judge_out/report.json | |
| - name: Upload judge report | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: judge-report | |
| path: judge_out/** |