LangChain-Chatchat: Your Private Document Q&A System
Build a fully private, self-hosted document Q&A system with LangChain-Chatchat. Supports ChatGLM, Qwen, Llama and more.
What Is LangChain-Chatchat?
LangChain-Chatchat (formerly known as LangChain-ChatGLM) is an open-source RAG (Retrieval-Augmented Generation) and Agent platform that lets you build a fully private, self-hosted document Q&A system. With over 38,000 GitHub stars, it is one of the most popular knowledge base applications built on the LangChain framework. The project supports a wide range of large language models including ChatGLM, Qwen, Llama, and GPT-compatible APIs, making it versatile for both Chinese and English document processing.
Key Features
LangChain-Chatchat provides a complete pipeline from document ingestion to intelligent Q&A. It supports multiple document formats (PDF, Word, Excel, TXT, Markdown, and more), processes them through embedding models into vector stores (FAISS, Milvus, PGVector), and enables natural language queries over your private knowledge base.
Why Self-Host LangChain-Chatchat?
Running LangChain-Chatchat locally gives you complete data privacy. Your documents and queries never leave your infrastructure. This is critical for enterprises dealing with confidential information, legal documents, or proprietary research. The Docker image makes deployment straightforward, and the intuitive WebUI makes it accessible to non-technical users.
Supported LLMs
The platform supports: ChatGLM, Qwen2.5, Llama3, Baichuan, InternLM, DeepSeek, Yi, and OpenAI-compatible APIs. This flexibility means you can choose the best model for your use case.
Conclusion
LangChain-Chatchat is a mature, actively maintained RAG platform that bridges the gap between powerful LLMs and your private data. A top choice for self-hosted knowledge management.