Insurance Policy RAG Chatbot

A portfolio-ready Retrieval-Augmented Generation chatbot for insurance policies, handbooks, and FAQs.

Users can upload PDFs and ask questions such as:

• Am I covered?
• Does collision include hail?
• How much is my deductible?
• Can I rent a replacement car?

Stack

• FastAPI
• LangChain
• Gemini
• FAISS or Chroma
• PDF ingestion
• Vector search
• RAG prompt with source references

Setup

cd insurance_policy_rag_chatbot
python -m venv .venv
source .venv/bin/activate   # Windows: .venv\Scripts\activate
pip install -r requirements.txt
cp .env.example .env

Add your Gemini API key to .env:

GOOGLE_API_KEY=your_api_key_here
VECTOR_DB=faiss

Run the API

uvicorn app.main:app --reload

Open:

http://127.0.0.1:8000/docs

Usage

1. Upload one or more PDFs using /upload
2. Ask a question using /chat

Example /chat body:

{
  "question": "Does collision coverage include hail damage?"
}

Optional Streamlit UI

In another terminal:

streamlit run streamlit_app.py

Portfolio Value

This project demonstrates:

• RAG
• LLM API integration
• Vector search
• PDF ingestion
• Insurance-domain question answering
• FastAPI backend development
• LangChain orchestration