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.
About AutoRAG
Marker-Inc-Korea/AutoRAG
AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation
Provides end-to-end RAG pipeline optimization through YAML-driven configuration, encompassing document parsing, semantic chunking, and QA dataset generation with support for multiple parsing/chunking strategies simultaneously. Uses grid-search and metric-driven evaluation across retriever-generator combinations to identify optimal module configurations, with results tracked in a dashboard for deployment-ready pipeline export. Integrates with LlamaIndex, LangChain, and local embedding models, supporting both cloud APIs (OpenAI) and GPU-accelerated inference for custom models.
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
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work