Kimi-K2.5

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}')

import openai
import base64
import requests

def chat_with_image(client: openai.OpenAI, model_name: str):
    url = 'https://huggingface.co/moonshotai/Kimi-K2.5/resolve/main/figures/kimi-logo.png'
    image_base64 = base64.b64encode(requests.get(url).content).decode()
    messages = [
        {
            'role': 'user',
            'content': [
                {
                    'type': 'image_url',
                    'image_url': {'url': f'data:image/png;base64, {image_base64}'},
                },
                {'type': 'text', 'text': 'Describe this image in detail.'},
            ],
        }
    ]

    response = client.chat.completions.create(
        model=model_name, messages=messages, stream=False, max_tokens=8192
    )
    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}')

    # Also support instant mode if you 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}')

    return response.choices[0].message.content

import openai
import base64
import requests

def chat_with_video(client: openai.OpenAI, model_name:str):
    url = 'https://huggingface.co/moonshotai/Kimi-K2.5/resolve/main/figures/demo_video.mp4'
    video_base64 = base64.b64encode(requests.get(url).content).decode()
    messages = [
        {
            "role": "user",
            "content": [
                {
                    "type": "video_url",
                    "video_url": {"url": f"data:video/mp4;base64,{video_base64}"},
                },
                {"type": "text","text": "Describe the video in detail."},
            ],
        }
    ]

    response = client.chat.completions.create(model=model_name, messages=messages)
    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}')

    # Also support instant mode if 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}')
    return response.choices[0].message.content