A production-ready Retrieval-Augmented Generation (RAG) system that lets you query your documents using Google's cutting-edge Gemini AI model.
- Document Processing: Upload and chunk PDF documents
- Smart Search: Semantic retrieval using Gemini embeddings
- AI Answers: Natural language responses with Gemini Pro
- REST API: FastAPI backend with Swagger docs
- Persistent Storage: ChromaDB vector store
- Easy Deployment: Docker container support
- Backend: FastAPI
- AI Models: Google Gemini (embeddings & chat)
- Vector DB: ChromaDB
- Orchestration: LangChain
- Containerization: Docker
- Python 3.9+
- Google API key (for Gemini)
- Docker (optional)
git clone https://github.com/AbuZar-Ansarii/Rag---FastAPI.git
cd rag-gemini
# Create and activate virtual environment
python -m venv venv
source venv/bin/activate # Linux/Mac
# venv\Scripts\activate # Windows
# Install dependencies
pip install -r requirements.txt
# Set up environment
cp .env.example .env
# Add your Google API key to .env