Skip to content

Latest commit

 

History

History
20 lines (12 loc) · 737 Bytes

README.md

File metadata and controls

20 lines (12 loc) · 737 Bytes
Raw

Ollama GitHub Action

CI

GitHub Action to install ollama, pull a model and run the ollama server.

Both the ollama install and the model are cached between runs.

Example usage:

      - uses: pydantic/ollama-action@v3
        with:
          model: qwen2:0.5b

We can then run tests and connect to http://localhost:11434 to make requests to ollama. Here we use the qwen2:0.5b model as it's very small and therefore quick to download.

This action is used by pydantic-ai.