Full Stack
MyFitnessBuddy – AI Fitness Coach
MyFitnessBuddy acts as a 24/7 personal trainer and nutritionist. Unlike static fitness apps, it uses RAG to pull from a vast database of nutritional science and exercise physiology, tailoring every response to the user's specific biometric data, goals, and limitations.
Project typeIndependent build
StatusCompleted project
FocusFull Stack
Technology
AzureOpenAICosmosDBRAGPythonReact
System approach
- Vector Database: Azure CosmosDB with vector search capabilities.
- LLM Orchestration: Azure Prompt Flow managing OpenAI model calls.
- Frontend: React interface for personalized fitness and nutrition workflows.
Challenges
- Preventing hallucinations in health and fitness advice.
- Handling complex, multi-turn conversations about diet adjustments.
- Ensuring low latency in generating comprehensive weekly plans.
Solutions
- Implemented strict RAG boundaries, forcing the LLM to ground its answers exclusively in the retrieved scientific literature context.
- Used a specialized conversational memory buffer that summarizes past dietary restrictions.
- Pre-computed embeddings for common workout routines to speed up the retrieval process.
Key outcomes
01
RAG-powered personalization
02
Azure AI integration
03
Context-aware health recommendations