Repolode
Submit
SensAI-PT

SensAI-PT/RAGMeUp

A generic, extensible RAG framework for building LLM applications that answer questions over your own dataset, with a React UI and Python server.

View on GitHub
Stars
678
Forks
98
Open issues
0
Last commit
last month

What is it?

RAG Me Up is a framework for building Retrieval-Augmented Generation applications, where an LLM answers questions using documents or data you supply. It is organized into a Python RAG server, a Node.js API server backed by PostgreSQL, and a React client, so the retrieval logic and the web interface can be developed and run separately.

The project is designed to be modular: chunkers, vector stores, and retrievers can be swapped for your own implementations. It ships with a Docker Compose setup for running the full stack on a single machine. The Python server runs in CPU-only mode inside Docker, and a hybrid mode lets it run directly on the host to use a local GPU for embeddings and inference.

The repository also links to a documentation site covering setup, architecture, and API references. The project is maintained by SensAI.PT, which reports using it in its own AI personal trainer product.

Key features

  • 01Modular design with swappable chunkers, vector stores, and retrievers.
  • 02Docker Compose setup that starts PostgreSQL, the Node.js API, and the React client.
  • 03Hybrid mode that runs the Python RAG server on the host for GPU/CUDA access.
  • 04Includes a React web UI for interacting with the RAG application.
  • 05Uses PostgreSQL (ParadeDB) as the backing database.

Use cases

  • Prototyping a question-answering assistant over your own documents.
  • Building a domain-specific chatbot backed by a custom knowledge base.
  • Running a self-hosted RAG stack with GPU-accelerated embeddings on a local machine.

Quick start

  1. 1

    Clone the repository

    git clone https://github.com/SensAI-PT/RAGMeUp.git
  2. 2

    Enter the project directory

    cd RAGMeUp
  3. 3

    Create the Docker env file from the example and set POSTGRES_PASSWORD and JWT_SECRET in it

    cp docker-compose.env.example docker-compose.env
  4. 4

    Build and start all services with Docker Compose

    docker compose --env-file docker-compose.env up --build -d

Things to know

  • The full Docker setup runs the Python server on CPU only, so GPU use requires a separate hybrid setup.
  • Setup requires Docker and configuring several services and environment variables.

Topics

#rag#llm#retrieval-augmented-generation#python#react#vector-search#docker

FAQ

What is RAGMeUp?
A generic, extensible RAG framework for building LLM applications that answer questions over your own dataset, with a React UI and Python server. RAG Me Up is a framework for building Retrieval-Augmented Generation applications, where an LLM answers questions using documents or data you supply. It is organized into a Python RAG server, a Node.js API server backed by PostgreSQL, and a React client, so the retrieval logic and the web interface can be developed and run separately.
Is RAGMeUp free to use? What license does it have?
RAGMeUp is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is RAGMeUp still maintained?
Updated within 6 months. The last commit to RAGMeUp was on Sep 12, 2026.
What can I use RAGMeUp for?
Prototyping a question-answering assistant over your own documents. Building a domain-specific chatbot backed by a custom knowledge base. Running a self-hosted RAG stack with GPU-accelerated embeddings on a local machine.
How do I install RAGMeUp?
Clone the repository: git clone https://github.com/SensAI-PT/RAGMeUp.git Enter the project directory: cd RAGMeUp Create the Docker env file from the example and set POSTGRES_PASSWORD and JWT_SECRET in it: cp docker-compose.env.example docker-compose.env Build and start all services with Docker Compose: docker compose --env-file docker-compose.env up --build -d
Where can I get RAGMeUp?
The source code and installation instructions are on GitHub: https://github.com/SensAI-PT/RAGMeUp

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects