{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hallo! Gerne helfe ich Ihnen. Worum geht es?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

import requests
import os
import time
from typing import Optional

class LocalmindClient:
    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.getenv("LOCALMIND_API_KEY")
        self.base_url = "https://api.localmind.ai/v1"
        if not self.api_key:
            raise ValueError("LOCALMIND_API_KEY muss gesetzt sein")
    
    def chat(self, message: str, model: str = "gpt-4", max_retries: int = 3):
        """Sende eine Chat-Nachricht mit Retry-Logik."""
        url = f"{self.base_url}/chat/completions"
        headers = {
            "Authorization": f"Bearer {self.api_key}",
            "Content-Type": "application/json"
        }
        data = {
            "model": model,
            "messages": [{"role": "user", "content": message}]
        }
        
        for attempt in range(max_retries):
            try:
                response = requests.post(url, json=data, headers=headers, timeout=30)
                response.raise_for_status()
                return response.json()
            except requests.exceptions.RequestException as e:
                if attempt == max_retries - 1:
                    raise
                time.sleep(2 ** attempt)  # Exponential backoff
        
        return None

# Verwendung
client = LocalmindClient()
response = client.chat("Hallo, Localmind!")
print(response["choices"][0]["message"]["content"])