AutoRAG and Blended-RAG

AutoRAG provides a framework for systematically evaluating and optimizing RAG pipelines through automated experimentation, while Blended RAG offers a specific retrieval technique (hybrid semantic and query-based search) that could be integrated as a component within AutoRAG's evaluation and optimization workflows.

AutoRAG
67
Established
Blended-RAG
39
Emerging
Maintenance 13/25
Adoption 10/25
Maturity 25/25
Community 19/25
Maintenance 2/25
Adoption 9/25
Maturity 16/25
Community 12/25
Stars: 4,609
Forks: 381
Downloads:
Commits (30d): 4
Language: Python
License: Apache-2.0
Stars: 86
Forks: 8
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License:
No risk flags
Stale 6m No Package No Dependents

About AutoRAG

Marker-Inc-Korea/AutoRAG

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

This tool helps AI developers and researchers find the best Retrieval-Augmented Generation (RAG) pipeline for their specific data and use case. You provide your documents and an evaluation dataset (questions and their correct answers), and AutoRAG automatically tests various RAG components and configurations. The output is an optimized RAG pipeline that performs best for your application.

AI development RAG systems LLM application model optimization natural language processing

About Blended-RAG

ibm-self-serve-assets/Blended-RAG

Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers

This project helps you build better question-answering systems by more accurately finding the right information from your own large collection of documents. It takes your extensive document library and user questions, then uses advanced search techniques to retrieve the most relevant sections, producing highly accurate answers. This is ideal for knowledge managers, researchers, or anyone building an intelligent Q&A system from a vast internal knowledge base.

knowledge-management information-retrieval generative-AI enterprise-search Q&A-systems

Scores updated daily from GitHub, PyPI, and npm data. How scores work