How gitakhileshyadav/ai-medical-assistant works
This is a FastAPI medical-image analysis assistant. The documented user journey is image upload and optimization, backend validation and session handling, AI interpretation, and a structured response that users can discuss in follow-up turns. The graph preserves those product stages and the JSON-processing module. Relationship evidence is limited: the README documents the workflow, and app.py’s indexed references include json_pipeline.py and Pillow; other implementation details were not shown.
Main entry points: app.py FastAPI application · app.js Web interface · json_pipeline.py JSON processing
Components 9
Client experience
- Web interface
static/js/app.js - Image preparation
static/js/app.js
Request handling
- FastAPI application
app.py - Image validation
app.py
AI analysis
- JSON processing
json_pipeline.py - Groq LLM
- Structured insights
app.py
Conversation state
- Session conversation
app.py
Other components
- Healthcare professional
Connections 11
- Healthcare professional → Web interface: submits image
- Web interface → Image preparation: prepares image
static/js/app.js - Image preparation → FastAPI application: uploads image
- FastAPI application → Image validation: validates input
app.py - FastAPI application → Session conversation: manages session
app.py - FastAPI application → JSON processing: processes JSON
app.py - FastAPI application → Groq LLM: requests analysis
- Groq LLM → Structured insights: returns insights
- Structured insights → Web interface: shows results
- Web interface → FastAPI application: sends follow-up
- FastAPI application → Session conversation: uses context
app.py