chatchat-space

Professional software vendor delivering innovative solutions on the Softono platform. Specialized in both open-source and proprietary software development.

Visit Website

Total Products

Software by chatchat-space

Open Source

Langchain Chatchat

LangChain-Chatchat formerly known as Langchain-ChatGLM is an open-source application for Retrieval-Augmented Generation and Agent workflows built on the LangChain framework. It enables users to deploy local knowledge-based Large Language Model solutions that support offline private deployment. The system is compatible with various open-source models including ChatGLM, Qwen, Llama, and GLM-4, as well as inference frameworks like Xinference and Ollama. It supports multiple popular embedding models and vector databases. Core functionality involves loading documents, reading text, splitting and vectorizing content, matching similarity against user queries, and generating context-aware responses via LLMs. The application offers a web interface powered by Streamlit and API services through FastAPI. It is designed to be friendly for Chinese language scenarios while remaining extensible for other languages. Users can install it via pip, clone the source code, or use Docker images. The project does not require model t

LLM Tools & Chat UIs Knowledge Bases & RAG

38.1K Github Stars

Open Source

LangGraph Chatchat

LangGraph-Chatchat is an open-source, offline-deployable application project for Retrieval-Augmented Generation and Agent workflows, built on the LangGraph framework and supporting large language models like ChatGLM, GLM-4, Qwen2, and Llama3. Designed as a lightweight microservice for developers, it enables private knowledge base Q&A solutions fully compatible with Chinese scenarios and open-source models. The system processes documents through loading, text segmentation, vectorization, and similarity matching to construct prompts for LLMs. Unlike its predecessor LangChain-Chatchat, this version utilizes LangGraph for constructing asymmetric loops and custom agent graphs, offering superior modularity and observability via LangSmith integration. It supports popular embedding models and vector databases while storing conversation history asynchronously in SQLite or PostgreSQL. The project features a Streamlit-based WebUI, supports Docker and source code deployment, and includes registered tool and graph compone

AI Agents LLM Tools & Chat UIs

181 Github Stars