README.md

---
title: Code 1B Chat API
emoji: 💻
colorFrom: blue
colorTo: indigo
sdk: docker
pinned: false
license: apache-2.0
---

# code-1b-chat-v2 — Inference API

OpenAI-compatible REST API for the code-1b-chat-v2 model.
Built with FastAPI + llama-cpp-python. Runs on CPU.

## Endpoints

| Method | Path | Description |
|--------|------|-------------|
| GET | `/health` | Health check |
| GET | `/v1/models` | List available models |
| POST | `/v1/chat/completions` | Chat (OpenAI-compatible) |

## Example

```python
import requests

resp = requests.post(
    "https://rovdetection-code-1b-chat-space.hf.space/v1/chat/completions",
    json={
        "model": "code-1b-chat-v2",
        "messages": [{"role": "user", "content": "Write a Python fibonacci function."}],
        "max_tokens": 200,
        "temperature": 0.7,
    }
)
print(resp.json()["choices"][0]["message"]["content"])
```

## Streaming

Add `"stream": true` to the request body for SSE streaming.