Multi-Agentic_Health_Assistant

Agentic-AI powered wellness platform with multiple specialized agents for mental health support, diet tracking with vision analysis, and personalized exercise planning. Built with DeepSeek, LLaMA, Google models. Used LangChain, LangGraph, Streamlit & Flask.

📋 Overview

The Multi-Agentic Health Assistant is an innovative wellness platform that combines the power of multiple Large Language Models (LLMs) and vision models to provide personalized support for physical and mental well-being. The system integrates three specialised AI agents that work together to deliver comprehensive health management through diet tracking, exercise planning, and mental health support.

🏗️ System Architecture

The platform utilises a multi-agent architecture with three specialised LLM agents, each designed for specific health domains:

🧠 Mental Health Agent

Knowledge-based system for emotional support and mental wellness.

• Daily check-ins and emotional support
• Guided journaling and motivational prompts
• Sentiment analysis and emotion classification
• Secure conversation memory with a flagging system
• Long-term interaction tracking

🥗 Diet Agent

Vision-enabled system for nutrition analysis and meal planning.

• Meal planning and nutritional suggestions
• Vision-based analysis of food photos
• Nutrient breakdown and diet goal comparison
• Dietary preference accommodation
• Calorie and macro tracking

💪 Exercise Agent

Database-driven system for fitness planning and tracking.

• Personalised workout routine generation
• Workout completion and calorie tracking
• Weekly difficulty and goal adjustments
• Performance data logging
• Progress monitoring and analytics

🌟 Key Features

Unified Web Interface: Streamlit/Flask based frontend with intuitive navigation
Multi-Modal AI: Integration of text and vision models for comprehensive analysis
Personalised Recommendations: Tailored advice based on individual profiles and goals