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.
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.
Stars
21
Forks
1
Language
TypeScript
License
—
Category
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.
Higher-rated alternatives
masterFoad/NanoSage
Local LLM Powered Recursive Search & Smart Knowledge Explorer
LeDat98/NexusRAG
Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder...
Zakk-Yang/nexusync
Intuitive RAG system on top of LllamaIndex
Serhii2009/brix-protocol
Runtime Reliability Infrastructure for LLM Pipelines — enforce deterministic rules, measure the...
Ambuj123-lab/agentic-rag-financial-parser
Enterprise RAG ecosystem managing 15,000+ semantic chunks. Features hybrid parsing...