Skip to content

Standardize LLM configuration and improve environment setup - #177

Closed
kahnu044 wants to merge 3 commits into
VectifyAI:mainfrom
kahnu044:feature/llm-config-standardization
Closed

Standardize LLM configuration and improve environment setup#177
kahnu044 wants to merge 3 commits into
VectifyAI:mainfrom
kahnu044:feature/llm-config-standardization

Conversation

@kahnu044

Copy link
Copy Markdown

Summary

This PR improves the LLM configuration and developer experience by introducing a more flexible and provider-agnostic environment setup.

Changes

1. LLM Configuration

  • Added LLM_MODEL environment variable

    • Allows overriding the default model from config.yaml without modifying source code

2. API Key Standardization

  • Renamed CHATGPT_API_KEYOPENAI_API_KEY

  • Aligned API key naming with provider-specific conventions:

    • OPENAI_API_KEY
    • ANTHROPIC_API_KEY
    • OPENROUTER_API_KEY
  • Ensures compatibility with LiteLLM multi-provider routing

3. Project Setup Improvements

  • Updated .gitignore:

    • Ignore virtual environments (.venv)
    • Ignore generated results/output files

4. Documentation Updates

  • Added virtual environment setup instructions
  • Documented usage of LLM_MODEL for overriding default models
  • Clarified provider-based API key naming conventions with LiteLLM

Impact

  • Improves flexibility for switching models and providers
  • Removes the need to modify source code for configuration changes
  • Aligns project with industry-standard LLM environment practices
  • Enhances onboarding experience for new developers

Notes

  • Existing setups using CHATGPT_API_KEY will need to migrate to OPENAI_API_KEY
  • No breaking changes to core functionality

@claude claude Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Claude Code Review

This repository is configured for manual code reviews. Comment @claude review to trigger a review.

Tip: disable this comment in your organization's Code Review settings.

@kahnu044

Copy link
Copy Markdown
Author

@claude review

@saccharin98

Copy link
Copy Markdown
Collaborator

⏺ Hi @kahnu044, thanks for the contribution!

We're closing this PR as the codebase has diverged since it was opened. The LiteLLM integration (#168) is
already in place — users familiar with LiteLLM can configure providers and models directly via config.yaml or
the model parameter, following standard LiteLLM conventions.

Thanks again for the effort!

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