README.md

---
title: Ollama FastAPI Streaming
emoji: 🚀
colorFrom: blue
colorTo: green
sdk: docker
pinned: false
---

# Ollama FastAPI Streaming Server

This Space runs an Ollama server with a FastAPI wrapper to provide real-time streaming for the model `aiasistentworld/Kimi-VL-A3B-Thinking-2506-LLM:latest`.

## API Usage

The API is available directly at the Space URL.

**Endpoint:** `POST /`

**Payload:**
```json
{
  "prompt": "Your question here",
  "key": "connectkey"
}
```

**Response:** Real-time text stream.