- Added LLMFactory for provider-agnostic LLM creation - Supports OpenAI, Ollama (local/free), Anthropic, Google, Groq, Azure, Together, HuggingFace, OpenRouter - Updated memory system to be provider-agnostic - Fixed Ollama integration with tool calling support (llama3.2, llama3.1, mistral-nemo, qwen2.5) - Added comprehensive documentation and examples - Updated CLI with new Ollama model selections - 100% backward compatible - OpenAI remains default - Verified working with tests
- Fix typo 'Start' 'End' - Add llama3.1 selection - Use 'quick_think_llm' model instead of hard-coding GPT
This reverts commit 78ea029a0b.
78ea029a0b
- Added support for running CLI and Ollama server via Docker - Introduced tests for local embeddings model and standalone Docker setup - Enabled conditional Ollama server launch via LLM_PROVIDER
This aims to offer alternative OpenAI capable api's. This offers people to experiment with running the application locally
Juan Manuel Béc
Max Wong
Yijia Xiao
Geeta Chauhan
Edward Sun
maxer137
Yijia-Xiao