README.md

metadata

title: Visualisable AI Backend
emoji: 🧠
colorFrom: blue
colorTo: green
sdk: docker
pinned: false
short_description: LLM code generation with real-time trace visualization

Visualisable.ai Backend Service

This is the backend service for Visualisable.ai, providing:

• Real-time model inference with trace extraction
• WebSocket streaming for live visualization
• REST API for model information and generation

API Endpoints

• GET / - Health check
• GET /health - Detailed health status
• GET /model/info - Model architecture details
• POST /generate - Generate text with traces
• WebSocket /ws - Real-time trace streaming

Configuration

Set the following secrets in your Space settings:

• API_KEY (optional) - API key for authentication

Frontend

The frontend is deployed separately on Vercel. Connect it by setting the backend URL in your frontend environment variables.