| # AskBuddyX Usage | |
| ## Quick Start | |
| ### 1. Install dependencies | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ### 2. Start the server | |
| ```bash | |
| # Using the base model with this adapter | |
| python -m mlx_lm.server \ | |
| --model mlx-community/Qwen2.5-Coder-0.5B-Instruct-4bit \ | |
| --adapter-path . \ | |
| --host 127.0.0.1 \ | |
| --port 8080 | |
| ``` | |
| ### 3. Test with curl | |
| ```bash | |
| curl http://127.0.0.1:8080/v1/chat/completions \ | |
| -H 'Content-Type: application/json' \ | |
| -d '{ | |
| "model": "AskBuddyX", | |
| "messages": [ | |
| {"role": "user", "content": "Write a Python function to add two numbers"} | |
| ], | |
| "max_tokens": 256 | |
| }' | |
| ``` | |
| ## Response Format | |
| AskBuddyX provides runnable-first responses with these sections: | |
| - **Solution**: Main implementation | |
| - **Usage**: Smallest runnable example | |
| - **Sanity test**: Tiny test snippet (when appropriate) | |