Using LLM with Python (Code)

1import requests
2
3API_URL = "http://localhost:11434/v1/chat/completions"
4MODEL   = "gemma3:1b"
5
6def chat_with_gemma3(prompt: str, max_tokens: int = 80) -> str:
7    payload = {
8        "model": MODEL,
9        "messages": [
10            {"role": "system", "content": "You are a helpful assistant."},
11            {"role": "user",   "content": prompt}
12        ],
13        "max_tokens": max_tokens,
14        "temperature": 0.7
15    }
16    r = requests.post(API_URL, json=payload)
17    r.raise_for_status()
18    data = r.json()
19    # The generated text is in choices[0].message.content
20    return data["choices"][0]["message"]["content"]
21
22if __name__ == "__main__":
23    user_prompt = "What hardware specs are ideal for running Gemma3?"
24    print("Gemma3 says:", chat_with_gemma3(user_prompt, max_tokens=100))