Kimi

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # China North 2 (Beijing). For another region, replace cn-beijing in the URL.
    # API keys are region-specific. See https://docs.qwencloud.com/developer-guides/getting-started/regions
    base_url="https://cn-beijing.maas.qwencloudapi.com/compatible-mode/v1",
)

# Single-image input example (thinking mode enabled)
completion = client.chat.completions.create(
    model="kimi-k2.6",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What scene is depicted in the image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
                    }
                }
            ]
        }
    ],
    extra_body={"enable_thinking":True}  # Enable thinking mode
)

# Print the thinking process
if hasattr(completion.choices[0].message, 'reasoning_content') and completion.choices[0].message.reasoning_content:
    print("\n" + "=" * 20 + "Thinking Process" + "=" * 20 + "\n")
    print(completion.choices[0].message.reasoning_content)

# Print the complete response
print("\n" + "=" * 20 + "Complete Response" + "=" * 20 + "\n")
print(completion.choices[0].message.content)

# Multi-image input example (thinking mode enabled, uncomment to use)
# completion = client.chat.completions.create(
#     model="kimi-k2.6",
#     messages=[
#         {
#             "role": "user",
#             "content": [
#                 {"type": "text", "text": "What do these images depict?"},
#                 {
#                     "type": "image_url",
#                     "image_url": {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"}
#                 },
#                 {
#                     "type": "image_url",
#                     "image_url": {"url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"}
#                 }
#             ]
#         }
#     ],
#     extra_body={"enable_thinking":True}
# )
#
# # Print the thinking process and complete response
# if hasattr(completion.choices[0].message, 'reasoning_content') and completion.choices[0].message.reasoning_content:
#     print("\nThinking Process:\n" + completion.choices[0].message.reasoning_content)
# print("\nComplete Response:\n" + completion.choices[0].message.content)

from openai import OpenAI
import os
import base64

# Encoding function: Converts a local file to a Base64-encoded string.
def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")

# Replace "xxx/eagle.png" with the absolute path to your local image.
base64_image = encode_image("xxx/eagle.png")

client = OpenAI(
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    # China North 2 (Beijing). For another region, replace cn-beijing in the URL.
    # API keys are region-specific. See https://docs.qwencloud.com/developer-guides/getting-started/regions
    base_url="https://cn-beijing.maas.qwencloudapi.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
    model="kimi-k2.6",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/png;base64,{base64_image}"},
                },
                {"type": "text", "text": "What scene is depicted in the image?"},
            ],
        }
    ],
)
print(completion.choices[0].message.content)

# The following examples show how to pass a local video file and a local image list.

# [Local video file] Encode the local video as a Data URL and pass it to the video_url parameter:
#   def encode_video_to_data_url(video_path):
#       with open(video_path, "rb") as f:
#           return "data:video/mp4;base64," + base64.b64encode(f.read()).decode("utf-8")

#   video_data_url = encode_video_to_data_url("xxx/local.mp4")
#   content = [{"type": "video_url", "video_url": {"url": video_data_url}, "fps": 2}, {"type": "text", "text": "What is the content of this video?"}]

# [Local image list] Encode multiple local images with Base64 and pass them as a list to the video parameter:
#   image_data_urls = [f"data:image/jpeg;base64,{encode_image(p)}" for p in ["xxx/f1.jpg", "xxx/f2.jpg", "xxx/f3.jpg", "xxx/f4.jpg"]]
#   content = [{"type": "video", "video": image_data_urls, "fps": 2}, {"type": "text", "text": "Describe the sequence of events in this video."}]