Langchain-Chatchat

What is Langchain-Chatchat?

Langchain-Chatchat (formerly Langchain-ChatGLM) is a RAG application with a web UI and an API for question answering over your own documents, plus agent tool calling, search-engine chat and database chat. Since version 0.3 it no longer loads models itself: it connects to a model server such as Xinference, Ollama, LocalAI, FastChat or One API for the LLM, embedding and reranker models. The docs and community are mainly in Chinese.

Where it fits in a 10–200 person business

• Internal Q&A over Chinese policy, product or technical documents with local models
• Offline knowledge assistant when documents may not leave the company network
• Starting point for teams that want to customize a LangChain-based RAG stack in Python

These use cases are our editorial suggestions, not claims made by the project.

Can a business use Langchain-Chatchat? (license)

This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.

Data & compliance: does Langchain-Chatchat phone home?

Checked against the project's own docs and repository on Oct 31, 2026. "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.

What hardware does Langchain-Chatchat need?

The project does not publish a minimum CPU/RAM figure, so we leave the official value blank rather than guess.

GPU: Not required by the app itself. Since 0.3.0 hardware depends on the model server you connect; the docs say it can run on CPU, GPU, NPU or MPS. The Docker Compose guide pairs it with Xinference and assumes the NVIDIA Container Toolkit.

No official CPU, RAM or disk figure is published. Software requirement is Python 3.8–3.11 (Windows, macOS and Linux tested).

Source: github.com/chatchat-space/Langchain-Chatchat#0-软硬件要求

How much does it cost to host Langchain-Chatchat per month?

How to deploy Langchain-Chatchat

Method: pip (or Docker Compose with Xinference)

pip install langchain-chatchat -U
# start a model server first (e.g. Xinference or Ollama) and load an LLM + embedding model
export CHATCHAT_ROOT=/path/to/chatchat_data
chatchat init      # creates data dirs and default yaml config
# edit model_settings.yaml for your model server, then:
chatchat kb -r     # build the sample knowledge base
chatchat start -a  # starts the API server and web UI

From the official instructions: github.com/chatchat-space/Langchain-Chatchat#pip-安装部署. Always check the source for the current version before you run it.

Known gotchas when self-hosting Langchain-Chatchat

• The published Docker image is chatimage/chatchat:0.3.1.3 from August 2024 and the README still says the image "will be updated soon"; the pip package is the maintained install path. source
• An embedding model must already be running and configured in model_settings.yaml before `chatchat kb -r`, or knowledge-base initialization fails. source
• Install it in a separate virtual environment from the model server (e.g. Xinference) to avoid dependency conflicts. source
• 0.3.x changed the architecture heavily; upgrading from 0.2.x means redeploying and copying the knowledge_base folder over, with no guarantee of compatibility. Back up first. source
• The default listen address (DEFAULT_BIND_HOST) is 127.0.0.1, so other machines can't reach it until you change it to 0.0.0.0 in basic_settings.yaml; put authentication in front before doing that. source

Alternatives in Knowledge base & RAG

• RAGFlow RAG engine with deep document parsing (OCR, layout and tables) and cited answers. Compare Langchain-Chatchat vs RAGFlow
• AFFiNE Notion- and Miro-style workspace (docs, whiteboards, databases) with built-in AI, self-hostable with Docker. Compare AFFiNE vs Langchain-Chatchat
• AnythingLLM All-in-one private chat with your documents, agents and an embeddable widget. Compare AnythingLLM vs Langchain-Chatchat
• PrivateGPT API-first private document Q&A that sits on top of your own LLM server. Compare Langchain-Chatchat vs PrivateGPT
• Open Notebook Private, self-hosted alternative to Google NotebookLM with your choice of AI models. Compare Langchain-Chatchat vs Open Notebook
• LightRAG Graph-based RAG server that builds a knowledge graph from your documents, with a web UI and REST API. Compare Langchain-Chatchat vs LightRAG
• WeKnora Tencent's open-source knowledge-base and agent platform with document parsing, RAG and team workspaces. Compare Langchain-Chatchat vs WeKnora
• Onyx (formerly Danswer) AI chat and enterprise search connected to 50+ workplace apps. Compare Langchain-Chatchat vs Onyx (formerly Danswer)
• FastGPT Knowledge-base Q&A and visual AI workflow platform. Compare FastGPT vs Langchain-Chatchat
• kotaemon Open-source RAG web app for chatting with your documents, with citations and GraphRAG. Compare kotaemon vs Langchain-Chatchat
• MaxKB Enterprise knowledge-base and agent platform with RAG and workflows. Compare Langchain-Chatchat vs MaxKB
• DocsGPT Open-source platform for AI agents and assistants that answer from your documents with sources. Compare DocsGPT vs Langchain-Chatchat
• PipesHub Self-hosted workplace search and AI answers across 50+ connected apps, filtered by each user's permissions. Compare Langchain-Chatchat vs PipesHub

Sources

• GitHub repository: github.com/chatchat-space/Langchain-Chatchat
• Official documentation: github.com/chatchat-space/Langchain-Chatchat#readme
• License text: github.com/chatchat-space/Langchain-Chatchat/blob/master/LICENSE
• Hardware requirements: github.com/chatchat-space/Langchain-Chatchat#0-软硬件要求
• Deploy instructions: github.com/chatchat-space/Langchain-Chatchat#pip-安装部署
• Gotcha 1: github.com/chatchat-space/Langchain-Chatchat#docker-部署
• Gotcha 2: github.com/chatchat-space/Langchain-Chatchat#4-初始化知识库
• Gotcha 3: github.com/chatchat-space/Langchain-Chatchat#2-模型推理框架并加载模型
• Gotcha 4: github.com/chatchat-space/Langchain-Chatchat#旧版本迁移
• Gotcha 5: github.com/chatchat-space/Langchain-Chatchat#5-启动项目
• Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
• GitHub stars, commits and releases: GitHub REST API, fetched Oct 31, 2026