test-cpython.yml

name: Test with CPython

on: [push, pull_request]

jobs:
  test:
    runs-on: ubuntu-22.04
    timeout-minutes: 10
    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: '3.10'

      - name: Get and build llama.cpp
        run: git clone https://github.com/ggerganov/llama.cpp.git && cd llama.cpp && make

      - name: Download Phi 2 model
        run: curl -OL https://huggingface.co/TheBloke/dolphin-2_6-phi-2-GGUF/resolve/main/dolphin-2_6-phi-2.Q3_K_M.gguf

      - name: Run llama.cpp with Phi 2
        run: ./llama.cpp/server --host 0.0.0.0 -m ./dolphin-2_6-phi-2.Q3_K_M.gguf &

      - name: Wait until the API server is ready
        run: while ! curl -s 'http://localhost:8080/health' | grep 'ok'; do sleep 1; done
        timeout-minutes: 3

      - run: echo 'Which planet in our solar system is the largest?' | python3 ./ask-llm.py | grep -i jupiter
        timeout-minutes: 7
        env:
          LLM_API_BASE_URL: 'http://127.0.0.1:8080/v1'
          LLM_DEBUG: 1