app.py

import openai
import base64
import requests
def simple_chat(client: openai.OpenAI, model_name: str):
    messages = [
        {'role': 'system', 'content': 'You are Kimi, an AI assistant created by Moonshot AI.'},
        {
            'role': 'user',
            'content': [
                {'type': 'text', 'text': 'which one is bigger, 9.11 or 9.9? think carefully.'}
            ],
        },
    ]
    response = client.chat.completions.create(
        model=model_name, messages=messages, stream=False, max_tokens=4096
    )
    print('====== Below is reasoning_content in Thinking Mode ======')
    print(f'reasoning content: {response.choices[0].message.reasoning_content}')
    print('====== Below is response in Thinking Mode ======')
    print(f'response: {response.choices[0].message.content}')

    # To use instant mode, pass {"thinking" = {"type":"disabled"}}
    response = client.chat.completions.create(
        model=model_name,
        messages=messages,
        stream=False,
        max_tokens=4096,
        extra_body={'thinking': {'type': 'disabled'}},  # this is for official API
        # extra_body= {'chat_template_kwargs': {"thinking": False}}  # this is for vLLM/SGLang
    )
    print('====== Below is response in Instant Mode ======')
    print(f'response: {response.choices[0].message.content}')