How sezginpaydas/llm-pulse-visualize works
Visual LLM Dashboard accepts prompts through a FastAPI backend, streams generation from local Ollama, and broadcasts request, thinking, and output status to connected dashboard clients over WebSockets. The backend and UI are the main internal layers; Ollama is an external inference service. The HTML template was not excerpted, so its specific interactions are not asserted.
Main entry points: main.py Prompt Workflow · index.html Dashboard UI
Components 9
Dashboard
- Dashboard UI
templates/index.html
Application Backend
- FastAPI Routes
main.py - Prompt Workflow
main.py - Request Stage
main.py - Thinking Stage
main.py - Output Stage
main.py - WebSocket Broadcast
main.py
Inference Service
- Ollama Inference
Other components
- User Browser
Connections 12
- User Browser → Dashboard UI: opens dashboard
README.md - FastAPI Routes → Dashboard UI: serves HTML
main.py - Dashboard UI → FastAPI Routes: submits prompt
- FastAPI Routes → Prompt Workflow: routes prompt
main.py - Prompt Workflow → Request Stage: broadcasts request
main.py - Prompt Workflow → Ollama Inference: streams generation
main.py - Prompt Workflow → Thinking Stage: broadcasts thinking
main.py - Prompt Workflow → Output Stage: broadcasts output
main.py - Request Stage → WebSocket Broadcast: sends event
main.py - Thinking Stage → WebSocket Broadcast: sends event
main.py - Output Stage → WebSocket Broadcast: sends event
main.py - WebSocket Broadcast → Dashboard UI: pushes updates