Add semantic similarity score to TestEvalLLMs
#120
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
| name: CI | |
| on: | |
| push: | |
| branches: | |
| - main | |
| pull_request: | |
| branches: | |
| - main | |
| workflow_dispatch: | |
| schedule: | |
| - cron: "7 0 * * 2" | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref_name }} | |
| cancel-in-progress: ${{ github.ref_name != 'main' }} | |
| jobs: | |
| test: | |
| name: Test | |
| runs-on: ubuntu-latest | |
| services: | |
| llama32-1b: | |
| image: "maragudk/llama-3.2-1b-instruct-q4_k_m" | |
| ports: | |
| - 8090:8080 | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Setup Go | |
| uses: actions/setup-go@v5 | |
| with: | |
| go-version-file: go.mod | |
| check-latest: true | |
| - name: Build | |
| run: go build -v ./... | |
| - name: Test | |
| run: go test -v -coverprofile=cover.out -shuffle on ./... | |
| env: | |
| OPENAI_KEY: ${{ secrets.OPENAI_KEY }} | |
| ANTHROPIC_KEY: ${{ secrets.ANTHROPIC_KEY }} | |
| GOOGLE_KEY: ${{ secrets.GOOGLE_KEY }} | |
| evaluate: | |
| name: Evaluate | |
| runs-on: ubuntu-latest | |
| if: ${{ github.triggering_actor != 'dependabot[bot]' }} | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Setup Go | |
| uses: actions/setup-go@v5 | |
| with: | |
| go-version-file: go.mod | |
| check-latest: true | |
| - name: Get dependencies | |
| run: go mod download | |
| - name: Install evals | |
| run: go install maragu.dev/evals | |
| - name: Download evals.db | |
| id: download-artifact | |
| uses: dawidd6/action-download-artifact@v7 | |
| with: | |
| name: evals.db | |
| branch: main | |
| if_no_artifact_found: warn | |
| - name: Evaluate | |
| run: | | |
| go test -run TestEval ./... | |
| evals | tee evals.txt >> $GITHUB_STEP_SUMMARY | |
| env: | |
| OPENAI_KEY: ${{ secrets.OPENAI_KEY }} | |
| ANTHROPIC_KEY: ${{ secrets.ANTHROPIC_KEY }} | |
| GOOGLE_KEY: ${{ secrets.GOOGLE_KEY }} | |
| - name: Upload evals.db | |
| uses: actions/upload-artifact@v4 | |
| id: evalsdb | |
| with: | |
| name: evals.db | |
| path: evals.db | |
| if-no-files-found: error | |
| - name: Add evals comment to PR | |
| uses: actions/github-script@v7 | |
| if: ${{ github.event_name == 'pull_request' }} | |
| with: | |
| script: | | |
| const fs = require('fs') | |
| const table = fs.readFileSync('evals.txt', 'utf8') | |
| github.rest.issues.createComment({ | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| issue_number: context.issue.number, | |
| body: `# Evals\n\n${table}\n\n[Download evals.db](${{ steps.evalsdb.outputs.artifact-url }})` | |
| }) | |
| lint: | |
| name: Lint | |
| runs-on: ubuntu-latest | |
| if: ${{ github.triggering_actor != 'dependabot[bot]' }} | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Setup Go | |
| uses: actions/setup-go@v5 | |
| with: | |
| go-version-file: go.mod | |
| check-latest: true | |
| - name: Lint | |
| uses: golangci/golangci-lint-action@v6 | |
| with: | |
| version: latest |