MrRezaeiUofT/AT-RAG
AT-RAG (Adaptive Retrieval-Augmented Generation) is a novel RAG model developed to address the challenges of complex multi-hop queries
This tool helps researchers, analysts, and domain experts get precise answers to complex, multi-step questions from large amounts of text data. You input a question, and it processes your documents, identifies key topics, and then provides a direct, accurate answer, even for questions requiring several steps of reasoning. It is designed for anyone needing to extract specific information from extensive datasets like medical texts or detailed knowledge bases.
No commits in the last 6 months.
Use this if you frequently ask intricate questions that require pulling information from multiple places within large document collections.
Not ideal if your questions are simple or if you are working with small datasets that don't require advanced topic filtering or iterative reasoning.
Stars
10
Forks
—
Language
Python
License
—
Category
Last pushed
Jul 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/MrRezaeiUofT/AT-RAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
HKUDS/LightRAG
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
beir-cellar/beir
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across...
HKUDS/RAG-Anything
"RAG-Anything: All-in-One RAG Framework"
superlinear-ai/raglite
🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL
illuin-tech/vidore-benchmark
Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.