Skip to content

Latest commit

 

History

History
77 lines (58 loc) · 3.75 KB

CONTRIBUTING.md

File metadata and controls

77 lines (58 loc) · 3.75 KB
Raw

Contributing to phidata

Phidata is an open-source project and we welcome contributions.

👩‍💻 How to contribute

Please follow the fork and pull request workflow:

  • Fork the repository.
  • Create a new branch for your feature.
  • Add your feature or improvement.
  • Send a pull request.
  • We appreciate your support & input!

Development setup

  1. Clone the repository.
  2. Create a virtual environment:
    • For Unix, use ./scripts/create_venv.sh.
    • For Windows, use .\scripts\create_venv_win.bat.
    • This setup will:
      • Create a phienv virtual environment in the current directory.
      • Install the required packages.
      • Install the phidata package in editable mode.
  3. Activate the virtual environment:
    • On Unix: source phienv/bin/activate
    • On Windows: phienv\Scripts\activate

Formatting and validation

Ensure your code meets our quality standards by running the appropriate formatting and validation script before submitting a pull request:

  • For Unix: ./scripts/format.sh
  • For Windows: .\scripts\format.bat These scripts will perform code formatting with ruff, static type checks with mypy, and run unit tests with pytest.

Adding a new Vector Database

  1. Setup your local environment by following the Development setup.
  2. Create a new directory under phi/vectordb for the new vector database.
  3. Create a Class for your VectorDb that implements the VectorDb interface
    • Your Class will be in the phi/vectordb/<your_db>/<your_db>.py file.
    • The VectorDb interface is defined in `phi/vectordb/base
    • Import your VectorDb Class in phi/vectordb/<your_db>/__init__.py.
    • Checkout the phi/vectordb/pgvector/pgvector2 file for an example.
  4. Add a recipe for using your VectorDb under cookbook/<your_db>.
  5. Important: Format and validate your code by running ./scripts/format.sh.
  6. Submit a pull request.

Adding a new LLM provider

  1. Setup your local environment by following the Development setup.
  2. Create a new directory under phi/llm for the new LLM provider.
  3. If the LLM provider supports the OpenAI API spec:
    • Create a Class for your LLM provider that inherits the OpenAILike Class from phi/llm/openai/like.py.
    • Your Class will be in the phi/llm/<your_llm>/<your_llm>.py file.
    • Import your Class in the phi/llm/<your_llm>/__init__.py file.
    • Checkout the phi/llm/together/together.py file for an example.
  4. If the LLM provider does not support the OpenAI API spec:
    • Reach out to us on Discord or open an issue to discuss the best way to integrate your LLM provider.
  5. Add a recipe for using your LLM provider under cookbook/<your_llm>.
  6. Important: Format and validate your code by running ./scripts/format.sh.
  7. Submit a pull request.

Message us on Discord if you have any questions or need help with credits.

📚 Resources

📝 License

This project is licensed under the terms of the MIT license