OSS Alternative - Discover Top Open Source Alternatives to Popular Software

Marker-Inc-Korea/AutoRAG

An open-source framework that automates the evaluation and optimization of Retrieval-Augmented Generation (RAG) pipelines using AutoML-style automation for specific datasets.

Core Features

Automated RAG pipeline optimization for custom data.

Comprehensive evaluation of various RAG modules.

Tools for creating QA and corpus datasets.

Support for custom Large Language Models (LLMs) and embedding models.

Interactive dashboard for RAG optimization results.

Quick Start

pip install AutoRAG

Detailed Introduction

Building an effective Retrieval-Augmented Generation (RAG) system often involves complex choices among numerous RAG pipelines and modules, making it challenging to identify the optimal configuration for specific data and use cases. AutoRAG addresses this by providing an open-source framework that automates the evaluation and optimization process. Leveraging AutoML-style automation, it allows users to systematically test and compare different RAG module combinations with their own evaluation data, significantly reducing the time and effort required to discover the best-performing RAG pipeline. This ensures tailored and efficient RAG solutions.