［開発者向け］Qwen3.8-27B徹底解説:27B級デンスモデルで画像・動画理解とエージェントタスクを両立する方法

# OpenAI SDKを最新版にアップグレードしてインストールします
pip install -U openai

# 使用する推論サーバーやQwen CloudのベースURLを設定します
export OPENAI_BASE_URL='your-base-url'

# 認証用のAPIキーを設定します
export OPENAI_API_KEY='your-api-key'

from openai import OpenAI

# 環境変数(OPENAI_BASE_URL, OPENAI_API_KEY)から設定を読み込みます
client = OpenAI()

# ユーザーからのメッセージを定義します
messages = [{"role": "user", "content": "Write a Python function to merge two sorted linked lists."}]

completion = client.chat.completions.create(
    model="Qwen/Qwen3.8-27B",
    messages=messages,
    extra_body={
        "chat_template_kwargs": {
            "enable_thinking": True,   # デフォルトで思考モードON
            "preserve_thinking": True, # デフォルトで思考内容を保持
        },
    },
    reasoning_effort="xhigh",  # デフォルトはxhigh。xhigh/medium/lowから選択
    stream=True,
    stream_options={"include_usage": True},
)

reasoning_content = ""
answer_content = ""
is_answering = False
print("\n" + "=" * 20 + "Reasoning" + "=" * 20 + "\n")

for chunk in completion:
    if not chunk.choices:
        # usage情報のみのチャンクはここで表示します
        print("\nUsage:")
        print(chunk.usage)
        continue

    delta = chunk.choices[0].delta

    if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
        if not is_answering:
            print(delta.reasoning_content, end="", flush=True)
        reasoning_content += delta.reasoning_content
    elif hasattr(delta, "reasoning") and delta.reasoning is not None:
        if not is_answering:
            print(delta.reasoning, end="", flush=True)
        reasoning_content += delta.reasoning

    if hasattr(delta, "content") and delta.content:
        if not is_answering:
            # 思考部分が終わり、最終回答が始まったことを示します
            print("\n" + "=" * 20 + "Answer" + "=" * 20 + "\n")
            is_answering = True
        print(delta.content, end="", flush=True)
        answer_content += delta.content

# 次のターンに向けて、思考内容も含めた応答履歴を追加します
messages.append({
    "role": "assistant",
    "content": answer_content,
    "reasoning_content": reasoning_content,
    "reasoning": reasoning_content,
})

from openai import OpenAI

client = OpenAI()

messages = [
    {
        "role": "user",
        "content": [
            {
                # 解析対象の画像URLを指定します
                "type": "image_url",
                "image_url": {
                    "url": "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/CI_Demo/mathv-1327.jpg"
                }
            },
            {
                # 画像に対する質問文をテキストで指定します
                "type": "text",
                "text": "The centres of the four illustrated circles are in the corners of the square. The two big circles touch each other and also the two little circles. With which factor do you have to multiply the radii of the little circles to obtain the radius of the big circles?"
            }
        ]
    }
]

chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.8-27B",
    messages=messages,
)
print("Chat response:", chat_response)

from openai import OpenAI

client = OpenAI()

messages = [
    {
        "role": "user",
        "content": [
            {
                # 解析対象の動画URLを指定します
                "type": "video_url",
                "video_url": {
                    "url": "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/video/N1cdUjctpG8.mp4"
                }
            },
            {
                "type": "text",
                "text": "How many porcelain jars were discovered in the niches located in the primary chamber of the tomb?"
            }
        ]
    }
]

chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.8-27B",
    messages=messages,
)

# vLLMでは、extra_bodyでフレームサンプリングのfps等を調整できます(vLLM限定の機能です)
print("Chat response:", chat_response)

from openai import OpenAI

client = OpenAI()

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image_url",
                "image_url": {
                    "url": "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/RealWorld/RealWorld-04.png"
                }
            },
            {
                "type": "text",
                "text": "Where is this?"
            }
        ]
    }
]

chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.8-27B",
    messages=messages,
    temperature=0.7,
    top_p=0.8,
    presence_penalty=1.5,
    extra_body={
        "top_k": 20,
        # 思考モードをOFFにして、直接回答を得ます
        "chat_template_kwargs": {"enable_thinking": False},
    },
)
print("Chat response:", chat_response)

from openai import OpenAI

client = OpenAI()
messages = [...]  # これまでの会話履歴を格納します

chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.8-27B",
    messages=messages,
    extra_body={
        # 最新のユーザーメッセージ以外の思考内容を保持しない設定です
        "chat_template_kwargs": {"preserve_thinking": False},
    },
)
print("Chat response:", chat_response)