# The non-obvious parts — the rest is standard Actions boilerplate
- name: Cache Ollama model
  uses: actions/cache@v4
  with:
    path: ~/.ollama/models
    key: ollama-qwen2.5-7b-q4

- name: Pull SLM model
  # Can't docker exec into service containers — use the API
  run: |
    curl -s http://localhost:11434/api/pull \
      -d '{"name": "qwen2.5:7b-instruct-q4_K_M"}' \
      --max-time 300

- name: Warm up model
  run: |
    curl -s http://localhost:11434/api/generate \
      -d '{"model": "qwen2.5:7b-instruct-q4_K_M", "prompt": "hello", "stream": false}' \
      > /dev/null

- name: Run ingestion pipeline
  run: python pipeline/run_ingestion.py
  env:
    OLLAMA_URL: "http://localhost:11434"
    MODEL_NAME: "qwen2.5:7b-instruct-q4_K_M"