Langchain-Chatchat and Chatchat-Lite
Chatchat-Lite is a simplified educational reimplementation of Langchain-Chatchat's core RAG/Agent architecture using LangGraph and Streamlit instead of the original's broader LangChain ecosystem, making them competitors targeting different complexity levels rather than complements.
About Langchain-Chatchat
chatchat-space/Langchain-Chatchat
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain
Supports flexible model deployment via Xinference, Ollama, and LocalAI frameworks with OpenAI API compatibility, enabling unified LLM and embedding model integration. Implements end-to-end RAG with hybrid retrieval methods (BM25+KNN), multi-modal image understanding, and agent-based tool orchestration for tasks like database queries, web search, and ArXiv paper analysis. Built on FastAPI backend and Streamlit frontend, supporting both local offline deployment and API-based access across diverse open-source models.
About Chatchat-Lite
imClumsyPanda/Chatchat-Lite
从零开始基于 LangGraph 和 Streamlit 实现基于本地模型的 RAG、Agent 应用
Leverages Ollama for local model inference, supporting multi-model configurations through a dedicated settings interface, with architecture built on LangGraph's agentic workflows for complex reasoning tasks. The Streamlit-based UI enables real-time conversation and model management, while RAG pipelines integrate document retrieval with Chinese language embeddings (BGE) for domain-specific knowledge augmentation.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work