#1717th of 17 in RAG and knowledge
langchain-chatchat
Local knowledge-base Q&A and agent app built on LangChain
- Stars
- 38.7k
- License
- Apache-2.0
- Last commit
- Nov 2025
- Last release
- Jul 2024
- Language
- Python
37,134 on 24 Mar 202638,681 on 13 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Chatchat answers questions over your own files by splitting, embedding and retrieving text, then passing the top-k matches to an LLM. It does not load models itself: it connects to Xinference, Ollama, LocalAI, FastChat or One API through OpenAI-compatible endpoints. It ships a FastAPI backend and a Streamlit WebUI, and installs with pip install langchain-chatchat.
Who it is for: Chinese-language users self-hosting offline document Q&A with local LLMs
Strengths
- Connects to Xinference, Ollama, LocalAI, FastChat and One API via OpenAI-compatible endpoints
- FAISS by default, other vector stores selectable in kb_settings.yaml
- YAML config reloads without restart (0.3.1+)
- Also has agent tools, search-engine chat, database chat and image chat with qwen-vl-chat
Weaknesses
- Needs a separate model server running before the knowledge base can be built
- Last release 2024-07-12; README Docker image tag is dated 2024-08-29
- Default bind is 127.0.0.1; remote access requires editing basic_settings.yaml
- 0.3.x differs a lot from 0.2.x; migration is not guaranteed to work
What it needs
- GPU optional
- Docker + Compose
- Needs Xinference, Ollama, LocalAI, FastChat or One API, FAISS (default vector store), SQLite (default database)
- Models: GLM-4-Chat, Qwen2-Instruct, Llama3, bge-large-zh-v1.5, qwen-vl-chat
Also in RAG and knowledge
See all 17| Rank | Project | Score |
|---|---|---|
| 1 | LightRAGGraph-based RAG framework with a REST API server and web UI | 75 out of 100 |
| 2 | Open NotebookSelf-hosted NotebookLM alternative with podcasts and 20+ model providers | 74 out of 100 |
| 3 | RAGFlowRAG engine with document parsing, agentic retrieval and citations | 73 out of 100 |
| #4 | MaxKBEnterprise knowledge-base agent platform with RAG, workflows and MCP tools | 71 out of 100 |
| #5 | SurfSenseDesktop agent that researches and edits your local documents with cited answers | 68 out of 100 |