import json
import urllib.request


def query_model(
    prompt,
    model="gpt-oss:20b",
    # If you used 
    # OLLAMA_HOST=127.0.0.1:11435 ollama serve
    # update the address below
    url="http://localhost:11434/api/chat"
):
    # Create the data payload as a dictionary:
    data = {
        "model": model,
        "messages": [
            {"role": "user", "content": prompt}
        ],
        # Settings required for deterministic responses:
        "options": {
            "seed": 123,
            "temperature": 0,
            "num_ctx": 2048
        }
    }

    # Convert the dictionary to JSON and encode it to bytes
    payload = json.dumps(data).encode("utf-8")

    # Create a POST request and add headers
    request = urllib.request.Request(  
        url,
        data=payload,
        method="POST"
    )
    request.add_header("Content-Type", "application/json")

    response_data = ""

    # Send the request and capture the streaming response
    with urllib.request.urlopen(request) as response:
        while True:
            line = response.readline().decode("utf-8")
            if not line:
                break
            # Parse each line into JSON
            response_json = json.loads(line)
            response_data += response_json["message"]["content"]

    return response_data