exactlab/exact-rag
AI-augmented, conversational information retrieval and data exploration
Supports multimodal input including text, images, and audio through optional integrations with OpenAI Whisper and Hugging Face transformers, enabling unified retrieval across diverse content types. Built as a Python server (with optional Streamlit UI) that connects to Elasticsearch for vector search and plugs into OpenAI or local Ollama LLMs for generation. Architecture separates modality preprocessing, retrieval, and LLM reasoning into configurable pipeline stages managed through a settings file.
No commits in the last 6 months.
Stars
37
Forks
4
Language
Python
License
MIT
Category
Last pushed
Mar 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/exactlab/exact-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...
leon0204/fast-rag
LLM Rag Intelligent Q&A Robot
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...