SensAI-PT/RAGMeUp

Generic rag framework to apply the power of LLMs on any given dataset

What it solves

RAG Me Up is a modular framework designed to accelerate the development of Retrieval-Augmented Generation (RAG) applications. It removes the need to write repetitive boilerplate code, allowing developers to focus on the core RAG logic and customization.

How it works

The project provides a plug-and-play architecture that allows users to integrate their own chunkers, vector stores, and retrievers. It is deployed via Docker Compose, featuring a React UI, a Node.js API server, and a Python RAG server. For performance, it supports a "hybrid mode" where the Python server runs on the host machine to leverage GPU/CUDA acceleration for embeddings and inference.

Who it’s for

Developers who want to build and prototype RAG applications quickly without starting from scratch, as well as those needing a production-ready framework that is extensible enough for large-scale settings.

Highlights

  • Modular design for custom chunkers, vectorstores, and retrievers.
  • Comprehensive deployment options including full Docker or hybrid GPU-enabled mode.
  • Includes a built-in React UI and Node.js API server.
  • Production-tested in large-scale applications like SensAI.PT.

Related

  • Project
    ray-project/llm-applications

    A comprehensive guide and implementation for building, scaling, and productionizing RAG-based LLM applications using the Ray framework.

  • Project
    weiwill88/Local_Pdf_Chat_RAG

    A modular Python implementation of a RAG pipeline designed for learning and experimentation, featuring hybrid retrieval and support for multiple LLM backends.

  • Project
    OpenBMB/UltraRAG

    A lightweight RAG development framework based on the Model Context Protocol (MCP) that enables low-code orchestration of complex retrieval-augmented generation workflows.

  • Project
    DataScienceUIBK/Rankify

    A comprehensive Python toolkit for retrieval, re-ranking, and RAG, providing a unified interface to experiment with and deploy state-of-the-art models.

  • Project
    rag-web-ui/rag-web-ui

    An intelligent dialogue system that allows users to build custom Q&A services by combining their own document knowledge bases with LLMs using Retrieval-Augmented Generation.