RAG / local knowledge base Q&A
Open-source local knowledge base Q&A and agent application built on LangChain, supporting multiple LLMs, embeddings, vector stores, with WebUI and API.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
MIT-licensed lightweight RAG system for laptops; choose for simpler setup and same core functionality if you don't need the seed's many model/database integrations.
A LLM RAG system runs on your laptop. 大模型检索增强生成系统，可以轻松部署在笔记本电脑上，实现本地知识库智能问答。
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Local QA with likely OCR-centric pipeline from RapidAI; choose if you need document OCR combined with RAG in a simpler package.
QA based on local knowledge and LLM.
Go-based personal AI assistant with RAG and agent loops; choose if you prefer an agent-first assistant over a knowledge-base web app.
⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org
Private on-device RAG with storage-optimized indexing (97% savings); choose if you need efficient storage and fast local retrieval.
[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Older LangChain+ChatGLM webui limited to ChatGLM-6B; choose if you need a lightweight legacy UI for that specific model.
基于LangChain和ChatGLM-6B等系列LLM的针对本地知识库的自动问答
Older FastAPI+Vue3 ChatGLM webui with knowledge base support; choose only if you want ChatGLM-specific minimal deployment.
用 FastAPI 和 Vue3 搭建的 ChatGLM 网页 (前端样式仿照chatgpt-web, 支持chatglm流式输出、前端调整参数、上下文选择、保存图片、知识库问答等功能)
Old LlamaIndex-based RAG starter from 2022; choose if you want a minimal example in the LlamaIndex ecosystem.
Build ChatGPT over your data, all with natural language
PDF-focused RAG reference with hybrid retrieval and reranking; choose if you only need PDF Q&A and want transparent FAISS/BM25 internals.
Transparent Python RAG reference with FAISS + BM25 hybrid retrieval, reranking, Gradio UI, and FastAPI.
These projects were analysed and named Langchain-Chatchat among their alternatives. The relationship is not symmetric — how Langchain-Chatchat rates them is a separate judgement, made when Langchain-Chatchat is analysed in its own right.
calls Langchain-Chatchat “pick it when you want a self-hosted RAG knowledge-base built on local models rather than a multi-provider chat client”
GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.
calls Langchain-Chatchat “choose if you need a local-knowledge RAG app with support for local Chinese LLMs.”
Build ChatGPT over your data, all with natural language
calls Langchain-Chatchat “Choose over Khoj if you need a Langchain-based local knowledge chat for Chinese-friendly LLMs, but it is narrower and less active.”
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.