llm-eval-notes/.github/workflows/ci.yml at main · maxpetrusenko/llm-eval-notes · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
name: CI

on:
  push:
    branches: [main]
  pull_request:
    branches: [main]

jobs:
  test:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Install uv
        uses: astral-sh/setup-uv@v1

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"

      - name: Install dependencies
        run: uv sync

      - name: Run ruff
        run: uv run ruff check src/ tests/

      - name: Run mypy
        run: uv run mypy src/llm_eval/

      - name: Run pytest
        run: uv run pytest -v

  test-real-apis:
    runs-on: ubuntu-latest
    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
    needs: test
    steps:
      - uses: actions/checkout@v4

      - name: Install uv
        uses: astral-sh/setup-uv@v1

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"

      - name: Install dependencies
        run: uv sync

      - name: Run evals on real models
        env:
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
        run: |
          if [ -n "$OPENAI_API_KEY" ]; then
            uv run llm-eval run all --provider openai --model gpt-4o || true
          fi