leon0204/fast-rag
LLM Rag Intelligent Q&A Robot
Combines vector and lexical retrieval (pgvector + pg_trgm) for hybrid semantic search, with LangGraph orchestration and multi-format document ingestion via Docling (PDF, DOCX, PPTX, images, HTML, markdown). Built on FastAPI with PostgreSQL backend, streams responses via SSE, and supports local Ollama models or OpenAI APIs while maintaining privacy-first architecture.
No commits in the last 6 months.
Stars
86
Forks
12
Language
Python
License
MIT
Category
Last pushed
Sep 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/leon0204/fast-rag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
gpt-open/rag-gpt
RAG-GPT, leveraging LLM and RAG technology, learns from user-customized knowledge bases to...
LexiestLeszek/scrapeGPT
ScrapeGPT is a RAG-based Telegram bot designed to scrape and analyze websites, then answer...
PatentTRIZbasedAI20260226110030/Patent-GPT
Patent-GPT is an Agentic RAG-based invention copilot combining TRIZ methodology with LLMs. It...
SujalKamate/Intel-Unnati-Industrial-Training-2025--Slot-3
Problem Statement-1: Multilingual NCERT Doubt-Solver using OPEA-based RAG Pipeline. A...
gptscript-ai/gptparse
Document parser for RAG