SRAurora Tech Logo
Back to Home

Personal AI Health Assistant

LLM-Powered Health Agent with RAG System

🩺

Project Mockup

Current Scope

βœ…Multi-language (EN / বাংলা)
βœ…Gemma 4 & Qwen Integration
🟑Conversation AI, Chat Memory & History
⏳RAG System
⏳Voice Integration
⏳Web Search Fallback
⏳Query Suggestions
⏳Knowledge Base Search
⏳Source Citation
⏳Admin Dashboard & Analytics
⏳Feedback System
AIHealth

Personal AI Health Assistant

Client: SR Aurora Tech (Internal Product)
Year: 2025
Duration: Ongoing

We are building a comprehensive Personal AI Health Assistant Agent that empowers users with instant, intelligent health guidance across four specialised AI agents: Doctor AI for symptom checking and urgency detection, Fitness AI for personalized workout plans and exercise form analysis, Nutrition AI for meal planning and calorie estimation from food photos, and Converse AI for general wellness conversations. The platform is powered by Gemma 4 and Qwen LLMs with a full RAG (Retrieval-Augmented Generation) system that grounds responses in a curated medical and fitness knowledge base β€” minimising hallucinations and ensuring accuracy. Built with bilingual support (English / বাংলা), voice input, chat memory and history, multi-account management, query suggestions, source citation, and a real-time admin dashboard with analytics and feedback tracking.

Tech Stack

Gemma 4QwenLLM RAGPythonNext.jsPostgreSQL

Challenge & Solution

Challenge

  • Ensuring medical accuracy with LLM hallucination risk
  • Bilingual NLP for English and Bengali
  • Real-time voice-to-text integration
  • RAG pipeline with domain-specific knowledge base
  • Multi-agent context isolation and memory management

Solution

  • RAG system grounding responses in verified medical/fitness knowledge
  • Gemma 4 & Qwen LLM integration with fine-tuned prompts
  • Bilingual tokenization and language detection pipeline
  • WebSocket-based voice streaming with Web Speech API
  • Per-user conversation memory with PostgreSQL session store

Key Results

Bilingual EN/BN support live
Gemma 4 & Qwen integrated
4 specialised AI agents deployed
Admin dashboard with real-time analytics
Multi-account & conversation history
RAG system in active development
Voice integration in progress
Feedback system implemented

πŸ—ΊοΈ Recommended MVP Roadmap

βœ…
Step 1Multi-language Support
βœ…
Step 2Conversation AI
βœ…
Step 3Chat Memory & History
βœ…
Step 4RAG System
βœ…
Step 5Knowledge Base Search
βœ…
Step 6Web Search Fallback
βœ…
Step 7Voice Integration
βœ…
Step 8Query Suggestions
βœ…
Step 9User-Friendly UI
βœ…
Step 10Admin Dashboard
βœ…
Step 11Feedback System
βœ…
Step 12Analytics & Reporting
βœ… Done🟑 In Progress⏳ Planned