Nightly production evaluation #34
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: Nightly production evaluation | |
| on: | |
| schedule: | |
| - cron: "0 6 * * *" | |
| workflow_dispatch: | |
| permissions: | |
| id-token: write | |
| issues: write | |
| jobs: | |
| monitor: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Set up Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.12" | |
| cache: pip | |
| - name: Install dependencies | |
| run: pip install -r requirements.txt | |
| - uses: azure/login@v2 | |
| with: | |
| client-id: ${{ vars.AZURE_CLIENT_ID }} | |
| tenant-id: ${{ vars.AZURE_TENANT_ID }} | |
| subscription-id: ${{ vars.AZURE_SUBSCRIPTION_ID }} | |
| - name: Get latest agent version | |
| id: agent | |
| env: | |
| FOUNDRY_PROD_ENDPOINT: ${{ vars.FOUNDRY_PROD_ENDPOINT }} | |
| run: | | |
| VERSION=$(python3 -c " | |
| import os | |
| from azure.ai.projects import AIProjectClient | |
| from azure.identity import DefaultAzureCredential | |
| client = AIProjectClient(endpoint=os.environ['FOUNDRY_PROD_ENDPOINT'], credential=DefaultAzureCredential()) | |
| versions = client.agents.list_versions(agent_name='tech-trends-agent') | |
| latest = max(versions, key=lambda v: int(v.version)) | |
| print(latest.version) | |
| ") | |
| echo "version=$VERSION" >> $GITHUB_OUTPUT | |
| - name: Run evaluation against production agent | |
| id: eval | |
| uses: microsoft/ai-agent-evals@v3-beta | |
| with: | |
| azure-ai-project-endpoint: ${{ vars.FOUNDRY_PROD_ENDPOINT }} | |
| deployment-name: ${{ vars.GPT_DEPLOYMENT }} | |
| agent-ids: "tech-trends-agent:${{ steps.agent.outputs.version }}" | |
| data-path: "./evals/golden-dataset.json" | |
| evaluation-result-view: "default" | |
| - name: Open GitHub issue if scores degraded | |
| if: failure() | |
| uses: actions/github-script@v7 | |
| with: | |
| script: | | |
| github.rest.issues.create({ | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| title: `Production agent eval degraded - ${new Date().toISOString().split('T')[0]}`, | |
| body: 'Nightly evaluation scored below threshold. Check the [Actions run](' + | |
| `${context.serverUrl}/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}).`, | |
| labels: ['agent-quality', 'alert'] | |
| }); |