DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5
209 stars · Python

How to use RAG Re Act Agent: what you can do with it

What is RAG Re Act Agent? RAG-ReActAgent is an open source, local-first document Q&A app that combines hybrid search, a ReAct agent loop, and citation checks, built with a FastAPI backend and React frontend.

How do I use it? git clone https://github.com/MoMoM101/RAG-ReActAgent.git; then cd RAG-ReActAgent; cp backend/.env.example backend/.env (Windows PowerShell: Copy-Item backend/.env.example backend/.env). Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

3 use cases

  • Answer questions over your own documents with citations

    Run a self-hosted knowledge base that answers from uploaded PDF, Word, text, and spreadsheet files.

    View prompt
    Clone https://github.com/MoMoM101/RAG-ReActAgent, copy backend/.env.example to backend/.env, and start it with docker compose --env-file backend/.env -f docker-compose.ghcr.yml up -d. Then upload the files in <path-to-document-folder> and ask the question <question>. Expected output: a streamed answer with inline citations and source cards. Verify that the cited file names come from <path-to-document-folder> before reporting the result.

  • Run the backend and frontend from source on your machine

    Start the FastAPI backend and React frontend without Docker so you can change the code.

    View prompt
    Clone https://github.com/MoMoM101/RAG-ReActAgent, create a Python 3.12 virtual environment, install backend/requirements.txt, run npm install in frontend, then run python main.py. Expected output: the launcher output with the Web, settings, and API docs addresses. Verify that the backend health check responds before reporting success.

  • Study how hybrid retrieval and citation checks are built

    Read the retrieval, agent, and evaluation code to reuse the design in your own RAG project.

    View prompt
    Clone https://github.com/MoMoM101/RAG-ReActAgent and read backend/rag, backend/agent, and docs/EVALUATION_REPRODUCIBILITY.md. Produce a summary of how Qdrant and SQLite BM25 results are fused with weighted RRF and how answer citations are checked, with a file path for each claim. Expected output: the summary as a short list. Verify that every file path exists before reporting.

Quick start with RAG Re Act Agent

  1. Check you have what it needs: Docker and Docker Compose, or Python 3.12 and Node.js 22.22 or newer for a source install; An OpenAI-compatible LLM service and an Embedding service, with an API key, for full knowledge Q&A.
  2. Open MoMoM101/RAG-ReActAgent on GitHub and read the README and license.
  3. git clone https://github.com/MoMoM101/RAG-ReActAgent.git
  4. cd RAG-ReActAgent
  5. cp backend/.env.example backend/.env (Windows PowerShell: Copy-Item backend/.env.example backend/.env)
  6. docker compose --env-file backend/.env -f docker-compose.ghcr.yml up -d

These steps come from our top use case, Answer questions over your own documents with citations, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for MoMoM101/RAG-ReActAgent

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Best AI repos for Work and operations

About this repo

Requirements

  • Docker and Docker Compose, or Python 3.12 and Node.js 22.22 or newer for a source install
  • An OpenAI-compatible LLM service and an Embedding service, with an API key, for full knowledge Q&A

Add this badge to your README

Maintain RAG Re Act Agent? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/MoMoM101/RAG-ReActAgent.svg)](https://dedupedai.com/use-cases/momom101-rag-reactagent/?utm_source=github&utm_medium=badge&utm_campaign=MoMoM101-RAG-ReActAgent)

HTML 

<a href="https://dedupedai.com/use-cases/momom101-rag-reactagent/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=MoMoM101-RAG-ReActAgent"><img src="https://dedupedai.com/badge/MoMoM101/RAG-ReActAgent.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about RAG Re Act Agent

What is RAG Re Act Agent?

RAG-ReActAgent is an open source, local-first document Q&A app that combines hybrid search, a ReAct agent loop, and citation checks, built with a FastAPI backend and React frontend. It is an open-source project on GitHub: https://github.com/MoMoM101/RAG-ReActAgent.

How do I use RAG Re Act Agent?

git clone https://github.com/MoMoM101/RAG-ReActAgent.git; then cd RAG-ReActAgent; cp backend/.env.example backend/.env (Windows PowerShell: Copy-Item backend/.env.example backend/.env). The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is RAG Re Act Agent for?

Teams with internal manuals, policies, or product documents that need sourced answers, and developers who want a self-hosted RAG reference.

What can I do with RAG Re Act Agent?

3 use cases so far, for example: Answer questions over your own documents with citations; Run the backend and frontend from source on your machine; Study how hybrid retrieval and citation checks are built. Each has steps and a copy-paste agent prompt.

What do I need to run RAG Re Act Agent?

Docker and Docker Compose, or Python 3.12 and Node.js 22.22 or newer for a source install; An OpenAI-compatible LLM service and an Embedding service, with an API key, for full knowledge Q&A.

What are alternatives to RAG Re Act Agent?

Other hot AI repos in Work and operations: Agno, n8n MCP, Kestra, Paper Pilot, Solidcraft.

Is RAG Re Act Agent safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.