Skip to content

Conversation

@saksham-jain177
Copy link

Pull Request

Description

Expands the configuration layer to support additional LLM providers using DSPy/LiteLLM.
This change is configuration- and documentation-only and does not modify agent or workflow logic.

Type of Change

  • 🐛 Bug fix (non-breaking change which fixes an issue)
  • ✨ New feature (non-breaking change which adds functionality)
  • 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • 📝 Documentation update
  • ♻️ Code refactoring
  • ⚡ Performance improvement
  • ✅ Test addition or update

Changes Made

  • Added configuration support for Google Gemini, Cohere, Azure OpenAI, Together AI, Replicate, and LM Studio.
  • Extended provider validation and initialization logic in config.py.
  • Added usage examples and provider notes to .env.example, README.md, and docs/getting-started/configuration.md.

Related Issues

Closes #18

Documentation

  • Updated relevant documentation in docs/
  • Updated README.md
  • Updated docstrings and type hints
  • No documentation changes needed

Checklist

  • My code follows the project's code style
  • I have performed a self-review of my code
  • I have commented my code, particularly in hard-to-understand areas
  • My changes generate no new warnings or errors
  • I have added tests that prove my fix is effective or that my feature works
  • New and existing unit tests pass locally with my changes

Additional Notes

This PR is intentionally limited to configuration and documentation changes.
Provider-specific runtime behavior is handled by DSPy/LiteLLM and underlying providers, and is not exercised in CI to avoid API-key and network-dependent tests.

@Dan-StrategicAutomation
Copy link
Collaborator

Will review in detail post release of v0.1.3

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants