https://github.com/leon0204/fast-rag
LLM Rag Intelligent Q&A Robot
https://github.com/leon0204/fast-rag
fastapi full-stack llm ollama rag
Last synced: 5 months ago
JSON representation
LLM Rag Intelligent Q&A Robot
- Host: GitHub
- URL: https://github.com/leon0204/fast-rag
- Owner: leon0204
- License: mit
- Created: 2025-08-27T03:07:13.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2025-09-05T07:53:07.000Z (10 months ago)
- Last Synced: 2025-09-05T09:12:43.692Z (10 months ago)
- Topics: fastapi, full-stack, llm, ollama, rag
- Language: Python
- Homepage:
- Size: 21.7 MB
- Stars: 20
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.MD
- License: LICENSE
Awesome Lists containing this project
README
# Fast RAG
[中文](README.zh-CN.md) | English
> Local, privacy-first RAG using PostgreSQL + pgvector and Ollama. Streams responses via SSE. Simple, fast, hackable.
## Features
- Process management 【LangGraph】
- Documents transform core tools 【Docling】、supprt PDF、DOCX、PPTX、Image、HTML、AsciiDoc、Markdown
- Semantic search with pgvector (768-dim `nomic-embed-text`)
- REST + Streaming responses via SSE
- Optional frontend: React + Vite + TypeScript
- Local models via Ollama or openai api
## Table of Contents
- [Local Setup](#local-setup)
- [Run](#run)
- [Frontend (optional)](#frontend-optional)
- [License](#license)
---
- env configure
---
## Local Setup
```bash
pip install -r requirements.txt
docling-tools models download
cp env.example .env # edit DB_* for your environment
#python scripts/init_db.py # if not using docker init
```
---
## Run
```bash
python main.py
```
App: http://localhost:8000
- Swagger UI: http://localhost:8000/docs
- ReDoc: http://localhost:8000/redoc
---
## Frontend
React + Vite + TypeScript app lives in `frontend-app/`.
Dev
```bash
cd frontend-app
npm install # or: pnpm i / yarn
npm run dev # http://localhost:5173
```
---
## License
MIT. See `LICENSE`.