What it does
Langchain-Chatchat builds a question-and-answer system over your own files, a "knowledge base". It splits your documents into pieces, finds the pieces most related to your question, and passes them to an AI model to write the answer.
It is designed to work well with Chinese and with open-source models such as GLM, Qwen and Llama, and can run entirely on your own machines without the internet. It can also connect to online services like OpenAI.
You use it through a simple web page or through an API, a doorway for other programs. Newer versions also include agent features that can call tools.
Who it's for
Teams and developers, especially Chinese-speaking ones, who want a private document Q&A system.
Can I use it without coding?
With some setup. Installed with Python commands, plus a separate tool to run the AI model; then used in a web page. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Windows, Mac, Linux
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Not needed
Try it
- Install Langchain-Chatchat with Python's package installer.
- Start a model tool such as Xinference or Ollama and load a model.
- Configure Chatchat to use that model, then open its web interface.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe