# 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

Repository: https://github.com/chatchat-space/Langchain-Chatchat
Canonical: https://ross.abutalabs.com/products/langchain-chatchat
Language: Python
License: Apache-2.0
License Family: permissive
Topics: chatglm, langchain, llm, knowledge-base, llama, chatbot, chatgpt, embedding, faiss, fastchat, gpt, milvus, streamlit, chatchat, langchain-chatglm, qwen, rag, retrieval-augmented-generation, xinference, ollama
Last push: 2025-11-10T09:27:42+00:00

## Health v2 (maintenance only)
Score: 44/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 51, release rhythm 8, longevity 89
- inputs: {"age_days": 1251, "days_push": 296, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 38581, forks 6268 (observed 2026-08-28T04:12:07.569074+00:00)

## What it is
Langchain-Chatchat is an open-source, offline-deployable RAG and Agent application built on Langchain and LLMs such as ChatGLM, Qwen, and Llama. It provides local knowledge-base question answering with support for multiple model inference frameworks and vector stores.

## Use cases
- build a local knowledge base chatbot
- question answering over my own documents with an llm
- run a private offline rag application
- chat with pdfs and documents locally
- deploy a self-hosted chatgpt alternative with local models
- build an agent app on top of chatglm or qwen

## When to choose
- you need fully offline/private deployment of a knowledge-base QA system
- you want Chinese-language-friendly RAG with open-source models
- you want pluggable model backends like Ollama, Xinference, or FastChat
- you prefer a ready-made application over building RAG from scratch

## When to avoid
- you need a lightweight library to embed RAG into your own codebase
- you require managed cloud RAG services
- you only need simple prompt-based chat without document retrieval

## Facets
- artifact type: application
- maturity: active
- function: rag, chatbot, agent-framework, llm-inference, search-engine, web-framework
- domain: large-language-models, chatbots, self-hosted
- platform: python, self-hosted, cross-platform
- tags: local-knowledge-base, chatglm, qwen, llama, langchain, offline-deployment, vector-store, embeddings, streamlit, xinference, ollama, faiss, milvus, retrieval-augmented-generation, ai-agents, natural-language-processing, docker

## Member repositories
- chatchat-space/Langchain-Chatchat (main) score 44

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:07.569074+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:24:50.511622+00:00, confidence not recorded.
  - readme: https://github.com/chatchat-space/Langchain-Chatchat (fetched 2026-08-28T04:12:07.569074+00:00, sha ceca1ad4cbcc)
- Data as of 2026-08-30T08:39:29.467469+00:00.