How athish2211/ptaiv3 works
PTAI is an AI-native electronic health record and clinical analytics platform. Its documented workflows cover clinical records and prescription safety, uploaded prescription processing, dataset profiling and analytics, and clinician queries handled by a multi-agent AI layer. The sampled backend shows API routing, query orchestration, safety checks, local-model calls, and analytics-agent dispatch; the README documents additional product capabilities. Frontend-to-backend request wiring and several unsampled subsystems are not shown, so those connections are omitted.
Main entry points: main.py FastAPI application · client.py Local model client · prescription_upload_service.py Prescription ingestion · database.py Database setup
Components 28
Clinician experience
- EHR screens
frontend/src/app/(app)/patients/page.tsx - Prescription builder
frontend/src/app/(app)/prescriptions/new/page.tsx - Analytics screens
frontend/src/app/(app)/analytics/page.tsx - Reports hub
frontend/src/app/(app)/reports/page.tsx
Clinical services
- Clinical API routes
backend/app/api - Document endpoint
backend/app/api/documents.py - Prescription ingestion
backend/app/services/prescription_upload_service.py - Documentation assistant
backend/app/ai/agents/documentation_agent.py - Clinical data models
backend/app/models
AI and analytics
- AI query endpoint
backend/app/api/ai_query.py - Analytics endpoint
backend/app/api/analytics.py - Dataset endpoints
backend/app/api/datasets.py - Dataset profiling
backend/app/services/dataset_upload_service.py - Analytics service
backend/app/services/analytics_service.py - Analysis pipeline
backend/app/utils/core_pipeline.py - Data profiling
backend/app/utils/data_profiling.py - Clinical analysis agents
backend/app/agents - AI orchestrator
backend/app/ai/supervisor/orchestrator.py - Safety guardrail
backend/app/ai/agents/safety_agent.py - Document retrieval
backend/app/ai/rag - Local model client
backend/app/ai/llm/client.py
Platform foundation
- FastAPI application
backend/app/main.py - PostgreSQL / pgvector
- Database setup
backend/app/core/database.py - User and tokens
backend/app/models/user.py - Runtime configuration
backend/app/core/config.py
Other components
- Clinician
- Ollama
Connections 27
- FastAPI application → Clinical API routes: routes requests
backend/app/main.py - FastAPI application → AI query endpoint: routes requests
backend/app/main.py - FastAPI application → Analytics endpoint: routes requests
backend/app/main.py - FastAPI application → Dataset endpoints: routes requests
backend/app/main.py - FastAPI application → Document endpoint: routes requests
backend/app/main.py - AI query endpoint → AI orchestrator: routes query
backend/app/api/ai_query.py - AI orchestrator → Safety guardrail: checks safety
backend/app/ai/supervisor/orchestrator.py - AI orchestrator → Local model client: generates response
backend/app/ai/supervisor/orchestrator.py - Local model client → Ollama: sends prompts
backend/app/ai/llm/client.py - Analytics endpoint → Analytics service: calls analytics
backend/app/api/analytics.py - Analytics endpoint → Clinical analysis agents: runs analysis
backend/app/api/analytics.py - Dataset endpoints → Dataset profiling: calls service
backend/app/api/datasets.py - Dataset profiling → Clinical data models: stores dataset
backend/app/services/dataset_upload_service.py - Document endpoint → Documentation assistant: uses assistant
backend/app/api/documents.py - Prescription ingestion → Document retrieval: creates chunks
backend/app/services/prescription_upload_service.py - Prescription ingestion → Clinical data models: creates records
backend/app/services/prescription_upload_service.py - Prescription ingestion → Local model client: embeds text
backend/app/services/prescription_upload_service.py - Analysis pipeline → Data profiling: uses profiling
backend/app/utils/core_pipeline.py - Analysis pipeline → Clinical analysis agents: dispatches analysis
backend/app/utils/core_pipeline.py - Database setup → Runtime configuration: reads settings
backend/app/core/database.py - Database setup → Clinical data models: initializes schema
backend/app/core/database.py - Database setup → PostgreSQL / pgvector: creates tables
backend/app/core/database.py - Local model client → Runtime configuration: reads model settings
backend/app/ai/llm/client.py - Clinician → EHR screens: uses
- Clinician → Prescription builder: uses
- Clinician → Analytics screens: uses
- Clinician → Reports hub: uses