Health Query Chatbot using LLM (Mistral-7B-Instruct)

Overview

This project is a General Health Query Chatbot built using a Large Language Model (LLM).
It provides friendly and safe health-related information based on user queries.

Features

1. LLM-powered responses
2. Safety filter (blocks harmful medical advice)
3. Fast inference using 4-bit quantization
4. Fully local (no paid API required)

Model Used

• Mistral-7B-Instruct (Quantized 4-bit version from Hugging Face)

How It Works

1. User enters a health-related query
2. Backend sends prompt to LLM
3. Model generates response
4. Safety filter ensures safe output
5. Response displayed