Who it is forA developer who wants to modify the agent, retrieval, or frontend and test changes locally.
The problemDocker images do not show the code you are editing, so you need a source setup for development.
The outcomeThe backend, frontend, and settings page run locally, and the launcher prints the local addresses.
What you need first
- 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
Steps
git clone https://github.com/MoMoM101/RAG-ReActAgent.gitcd RAG-ReActAgentcp backend/.env.example backend/.env(Windows PowerShell:Copy-Item backend/.env.example backend/.env)python -m venv .venvpip install -r backend/requirements.txtcd frontend, thennpm install, thencd ..python main.py
Prompt for your agent
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.
Caveat. OCR and the Reranker are off by default, and the Docker base image does not install OCR dependencies, so scanned PDFs need extra setup before they work.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for MoMoM101/RAG-ReActAgent and "Run the backend and frontend from source on your machine"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer