README.md

🚀 RAG API with FastAPI

A local Retrieval-Augmented Generation (RAG) API built with Python and FastAPI.

This project implements a complete RAG pipeline that retrieves relevant information from a custom knowledge base and uses a local LLM to generate grounded answers — running entirely on the local machine with zero cloud/API costs.

---

🧠 How It Works

Documents
    ↓
Text Chunking
    ↓
Vector Embeddings
    ↓
ChromaDB
    ↓
Semantic Retrieval
    ↓
Relevant Context
    ↓
Prompt Augmentation
    ↓
Qwen LLM
    ↓
AI-Generated Answer