# AI use cases for RAG Re Act Agent (MoMoM101/RAG-ReActAgent) Repo: [MoMoM101/RAG-ReActAgent](https://github.com/MoMoM101/RAG-ReActAgent) | Use cases: 3 | Page: https://dedupedai.com/use-cases/momom101-rag-reactagent/ 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. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Answer questions over your own documents with citations: https://dedupedai.com/use-cases/momom101-rag-reactagent/sourced-qa-over-own-documents/ - Run the backend and frontend from source on your machine: https://dedupedai.com/use-cases/momom101-rag-reactagent/run-from-source-for-local-development/ - Study how hybrid retrieval and citation checks are built: https://dedupedai.com/use-cases/momom101-rag-reactagent/study-hybrid-retrieval-and-citation-checks/ ## How to answer questions over your own documents with citations with RAG Re Act Agent Repo: [MoMoM101/RAG-ReActAgent](https://github.com/MoMoM101/RAG-ReActAgent) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Run a self-hosted knowledge base that answers from uploaded PDF, Word, text, and spreadsheet files. **Who it is for:** A team lead or ops staff member with internal manuals, policies, or product files who needs answers that point back to the source. **The problem:** Finding one answer across scattered files is slow, and general chatbots do not cite your documents. **The outcome:** Uploaded files become searchable, and each answer shows inline citations and source cards. ### Steps 1. `git clone https://github.com/MoMoM101/RAG-ReActAgent.git` 2. `cd RAG-ReActAgent` 3. `cp backend/.env.example backend/.env` (Windows PowerShell: `Copy-Item backend/.env.example backend/.env`) 4. `docker compose --env-file backend/.env -f docker-compose.ghcr.yml up -d` 5. Log in as admin, change the default password, then fill in the LLM and Embedding settings on the settings page. 6. Upload your .pdf, .docx, .txt, .md, .csv, or .xlsx files and ask a question in the chat. ### Prompt to paste into your agent ```text 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 and ask the question . Expected output: a streamed answer with inline citations and source cards. Verify that the cited file names come from before reporting the result. ``` ### Caveat Full answers need an LLM and an Embedding service configured in the settings page, and the README's benchmark figures come from a synthetic set that may not match your documents. Risk, credentials: The README publishes a default admin password, so change it right after the first login and before exposing the service. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/momom101-rag-reactagent/sourced-qa-over-own-documents/ ## How to run the backend and frontend from source on your machine with RAG Re Act Agent Repo: [MoMoM101/RAG-ReActAgent](https://github.com/MoMoM101/RAG-ReActAgent) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Start the FastAPI backend and React frontend without Docker so you can change the code. **Who it is for:** A developer who wants to modify the agent, retrieval, or frontend and test changes locally. **The problem:** Docker images do not show the code you are editing, so you need a source setup for development. **The outcome:** The backend, frontend, and settings page run locally, and the launcher prints the local addresses. ### Steps 1. `git clone https://github.com/MoMoM101/RAG-ReActAgent.git` 2. `cd RAG-ReActAgent` 3. `cp backend/.env.example backend/.env` (Windows PowerShell: `Copy-Item backend/.env.example backend/.env`) 4. `python -m venv .venv` 5. `pip install -r backend/requirements.txt` 6. `cd frontend`, then `npm install`, then `cd ..` 7. `python main.py` ### Prompt to paste into your agent ```text 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. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/momom101-rag-reactagent/run-from-source-for-local-development/ ## How to study how hybrid retrieval and citation checks are built with RAG Re Act Agent Repo: [MoMoM101/RAG-ReActAgent](https://github.com/MoMoM101/RAG-ReActAgent) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Read the retrieval, agent, and evaluation code to reuse the design in your own RAG project. **Who it is for:** A developer building a RAG system who wants a worked reference for merging search results and verifying answer citations. **The problem:** Reading a RAG design from a blog post hides the details of fusion, deduplication, and citation checks. **The outcome:** A file-by-file summary of how semantic and keyword results are merged and how answers are verified. ### Steps 1. `git clone https://github.com/MoMoM101/RAG-ReActAgent.git` 2. `cd RAG-ReActAgent` 3. Read backend/rag for loading, chunking, query classification, and retrieval, and backend/agent for the ReAct loop and answer verification. 4. `pip install -r backend/requirements-dev.txt` 5. Read docs/EVALUATION_REPRODUCIBILITY.md to see how the evaluation numbers were produced. 6. Run the tests in backend/tests with pytest after the dev install. (inferred, check the README) ### Prompt to paste into your agent ```text 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. ``` ### Caveat Reading the code does not reproduce the reported numbers, which come from a fixed synthetic benchmark that includes a development subset rather than a strictly held-out test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/momom101-rag-reactagent/study-hybrid-retrieval-and-citation-checks/