A sleek, plug-and-play Python AI chat application featuring a FastAPI backend, custom web UI, and generic LLM adapter logic.
graph LR
subgraph Frontend [Presentation Layer]
UI[Templates & Static Assets]
end
subgraph Backend [FastAPI Service Layer]
Router[API Endpoint Router]
Logic[LLM Dispatcher Logic]
end
subgraph Providers [Inference Providers]
Mock[Local Mock Mode]
Remote[External Provider<br/>OpenAI / Ollama / API Gateway]
end
UI <--> Router
Router <--> Logic
Logic <-->|Default| Mock
Logic <-->|Configured| Remote