wzdavid/ThinkRAG
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。企业级SaaS版本请访问：
Integrates LlamaIndex framework with Streamlit for the UI layer, supporting both local file storage (development mode) and vector databases like Chroma/LanceDB (production mode). Optimized for Chinese text processing with Spacy-based splitting, title enhancement, and Chinese prompt templates, while supporting Ollama for local model deployment and multiple LLM APIs (OpenAI-compatible, DeepSeek, Moonshot, ZhiPu). Includes document management for PDFs, DOCX, PPTX files and supports bilingual embedding models from BAAI.
319 stars.
Stars
319
Forks
50
Language
Python
License
MIT
Category
Last pushed
Jan 28, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/wzdavid/ThinkRAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
brevia-ai/brevia
Extensible API and framework to build your Retrieval Augmented Generation (RAG) and Information...
swirlai/swirl-search
AI Search & RAG Without Moving Your Data. Get instant answers from your company's knowledge...
thinkany-ai/rag-search
RAG Search API
sankalp1999/code_qa
RAG on codebases using treesitter and LanceDB
Piazza-tech/Piazza-Updater
Piazza-Updater automates updates to a Weaviate database with real-time vectorial data. By...