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...

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 52 minutes ago
Added to GitGenius on August 31st, 2026
Created on March 31st, 2023
Open Issues & Pull Requests: 24 (+0)
Number of forks: 6,269
Total Stargazers: 38,597 (-1)
Total Subscribers: 288 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 13.7 hours
Mean response time: 6.6 days
90th percentile: 14.4 days
Tracked items: 507

How this project is maintained

Around half of the issues opened in the past year never receive a reply. Only 7% of issues opened in the past year have been closed. Three people close 55% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 5
New in 7 days: 1
Closed in 7 days: 1
Avg open age: 292 days
Stale 30+ days: 0
Stale 90+ days: 0

Recent activity

Opened in 7 days: 1
Closed in 7 days: 1
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • stale (484)
  • bug (463)
  • enhancement (122)
  • 0.2.x (1)
  • question (1)

Detailed Description

Langchain-Chatchat is a retrieval-augmented generation and agent application framework that enables local knowledge base question-answering using open-source language models.

The tool addresses the need for offline, privacy-preserving question-answering systems that work well with Chinese language content and open-source models. It implements a retrieval-augmented generation pipeline: documents are loaded, text is extracted and split, chunks are vectorized, user queries are vectorized, the system retrieves the top matching text chunks, and these are combined with the query in a prompt sent to a language model for response generation. The framework integrates with LangChain and supports multiple model inference systems including Xinference and Ollama, allowing users to deploy models like GLM-4-Chat, Qwen2-Instruct, and Llama3. It provides both a FastAPI-based service interface and a Streamlit-based web interface.

Developers should choose this tool if they need a fully open-source, offline-deployable knowledge base system with strong support for Chinese language scenarios. It suits projects requiring private deployment without reliance on external APIs, though it also supports OpenAI GPT API integration for those who prefer it. The project supports mainstream open-source language models, embedding models, and vector databases including FAISS and Milvus, enabling complete end-to-end deployment using only open-source components. The tool does not include model fine-tuning or training capabilities, though users can optimize results through those means independently.

Development activity shows consistent engagement with the codebase through regular updates and maintenance. The project maintains active documentation and deployment examples, including Docker support and cloud platform integration. Community contributions are tracked and acknowledged, with the project evolving to support new model releases and inference frameworks as they emerge. The maintainers continue expanding model and API integrations based on ecosystem developments.