# 推理服务_HTTP协议

from openai import OpenAI  

# 必填：从服务管控页面获取对应服务的APIKey和API Base
api_key = "<YOUR_API_KEY>"
api_base = "http://maas-api.cn-huabei-1.xf-yun.com/v1"

client = OpenAI(api_key=api_key, base_url=api_base)

def unified_chat_test(model_id, messages, use_stream=False, extra_body={}):
    """
    一个统一的函数，用于演示多种调用场景。

    :param model_id: 要调用的模型ID。
    :param messages: 对话消息列表。
    :param use_stream: 是否使用流式输出。
    :param extra_body: 包含额外请求参数的字典，如 response_format。
    """
    try:
        response = client.chat.completions.create(
            model=model_id,
            messages=messages,
            stream=use_stream,
            temperature=0.7,
            max_tokens=4096,
            extra_headers={"lora_id": "0"},  # 调用微调大模型时,对应替换为模型服务卡片上的resourceId
            stream_options={"include_usage": True},
            extra_body=extra_body
        )

        if use_stream:
            # 处理流式响应
            full_response = ""
            print("--- 流式输出 ---")
            for chunk in response:
                if hasattr(chunk.choices[0].delta, 'content') and chunk.choices[0].delta.content:
                    content = chunk.choices[0].delta.content
                    print(content, end="", flush=True)
                    full_response += content
            print("\n\n--- 完整响应 ---")
            print(full_response)
        else:
            # 处理非流式响应
            print("--- 非流式输出 ---")
            message = response.choices[0].message
            print(message.content)

    except Exception as e:
        print(f"请求出错: {e}")

if __name__ == "__main__":
    model_id = "<YOUR_MODEL_ID>" # 必填：从服务管控获取要访问服务的modelID

    # 1. 普通非流式调用
    print("********* 1. 普通非流式调用 *********")
    plain_messages = [{"role": "user", "content": "你好，请介绍一下自己。"}]
    unified_chat_test(model_id, plain_messages, use_stream=False)

    # 2. 普通流式调用
    print("\n********* 2. 普通流式调用 *********")
    stream_messages = [{"role": "user", "content": "写一首关于夏天的诗。"}]
    unified_chat_test(model_id, stream_messages, use_stream=True)

    # 3. JSON Mode 调用
    print("\n********* 3. JSON Mode 调用 *********")
    json_messages = [{"role": "user", "content": "请给我一个关于上海的JSON对象，包含城市名称(city)和人口数量(population)。"}]
    json_extra_body = {
        "response_format": {"type": "json_object"},
        "search_disable": True # JSON Mode下建议关闭搜索
    }
    unified_chat_test(model_id, json_messages, use_stream=False, extra_body=json_extra_body)

Response: ChatCompletion(
    id='cht000b920a@dx194e0205ccbb8f3700',
    choices=[
        Choice(
            finish_reason='stop',
            index=0,
            logprobs=None,
            message=ChatCompletionMessage(
                content='大模型回复',
                refusal=None,
                role='assistant',
                audio=None,
                function_call=None,
                tool_calls=None
            )
        )
    ],
    created=1738927005,
    model=None,
    object='chat.completion',
    service_tier=None,
    system_fingerprint=None,
    usage=CompletionUsage(
        completion_tokens=42,
        prompt_tokens=44,
        total_tokens=86,
        completion_tokens_details=None,
        prompt_tokens_details=None
    )

ChatCompletion(
    id='cht000b8e42@dx19590107ba3b8f2700', 
    choices=[
        Choice(
            finish_reason='stop', 
            index=0, 
            logprobs=None, 
            message=ChatCompletionMessage(
                content='大模型回复', 
                refusal=None, 
                role='assistant', 
                audio=None, 
                function_call=None, 
                tool_calls=None, 
                reasoning_content='', 
                plugins_content=[
                    {
                        'name': 'ifly_search', 
                        'content': '[{"index":1,"url":"https://xxx.com/xxx/doc.html","title":"信源标题"}]'
                    }
                ]
            )
        )
    ], 
    created=1741878776, 
    model='xdeepseekv3', 
    object='chat.completion', 
    service_tier=None, 
    system_fingerprint=None, 
    usage=CompletionUsage(
        completion_tokens=346, 
        prompt_tokens=1124, 
        total_tokens=1470, 
        completion_tokens_details=None, 
        prompt_tokens_details=None
    )
)