ethicalByte1443/Insurance-AI-Agent-RAG-Based

An intelligent full-stack insurance claim decision-making system that combines FastAPI backend with React TypeScript frontend, powered by Hugging Face Transformers and Gemma LLM. This AI agent analyzes insurance clauses and customer queries to predict whether a claim should be Approved or Rejected, along with justification and estimated amounts.

17
/ 100
Experimental

Implements a **RAG (Retrieval-Augmented Generation) pipeline** using FAISS vector search with Sentence Transformers to match user queries against policy clauses before LLM processing, enabling offline operation with local Gemma models or fallback to Groq's ultra-fast inference API. The backend exposes clean REST endpoints for PDF ingestion (via PyMuPDF parsing) and structured claim decisions, while the frontend provides drag-and-drop document upload and real-time visualization of matched clauses alongside AI reasoning.

No License No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 1 / 25
Community 4 / 25

How are scores calculated?

Stars

21

Forks

1

Language

TypeScript

License

Last pushed

Oct 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/ethicalByte1443/Insurance-AI-Agent-RAG-Based"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.