创建响应

from openai import OpenAI
import json
import os
import random

# 初始化客户端
client = OpenAI(
    # 若没有配置环境变量，请用阿里云百炼API Key将下行替换为：api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)
# 模拟用户问题
USER_QUESTION = "北京天气咋样"
# 定义工具列表
tools = [
    {
        "type": "function",
        "name": "get_current_weather",
        "description": "当你想查询指定城市的天气时非常有用。",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "城市或县区，比如北京市、杭州市、余杭区等。",
                }
            },
            "required": ["location"],
        },
    }
]

# 模拟天气查询工具
def get_current_weather(arguments):
    weather_conditions = ["晴天", "多云", "雨天"]
    random_weather = random.choice(weather_conditions)
    location = arguments["location"]
    return f"{location}今天是{random_weather}。"

# 封装模型响应函数
def get_response(input_data):
    response = client.responses.create(
        model="qwen3.8-max",
        input=input_data,
        tools=tools,
    )
    return response

# 维护对话上下文
conversation = [{"role": "user", "content": USER_QUESTION}]

response = get_response(conversation)
function_calls = [item for item in response.output if item.type == "function_call"]
# 如果不需要调用工具，直接输出内容
if not function_calls:
    print(f"助手最终回复：{response.output_text}")
else:
    # 进入工具调用循环
    while function_calls:
        for fc in function_calls:
            func_name = fc.name
            arguments = json.loads(fc.arguments)
            print(f"正在调用工具 [{func_name}]，参数：{arguments}")
            # 执行工具
            tool_result = get_current_weather(arguments)
            print(f"工具返回：{tool_result}")
            # 将工具调用和结果成对追加到上下文中
            conversation.append(
                {
                    "type": "function_call",
                    "name": fc.name,
                    "arguments": fc.arguments,
                    "call_id": fc.call_id,
                }
            )
            conversation.append(
                {
                    "type": "function_call_output",
                    "call_id": fc.call_id,
                    "output": tool_result,
                }
            )
        # 携带完整上下文再次调用模型
        response = get_response(conversation)
        function_calls = [
            item for item in response.output if item.type == "function_call"
        ]
    print(f"助手最终回复：{response.output_text}")

import os
from openai import OpenAI

client = OpenAI(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)

response = client.responses.create(
    model="qwen3.5-ocr",
    input=[
        {
            "role": "user",
            "content": [
                {
                    "type": "input_file",
                    "file_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260616/qmycjl/1506.02640v5.pdf",
                },
                {
                    "type": "input_text",
                    "text": "Read all the text in the file.",
                },
            ],
        }
    ],
    extra_body={
        "ocr_options": {"task": "document_parsing"}
    },
)

print(response.output_text)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
    # 通过 default_headers 开启 Session 缓存
    default_headers={"x-dashscope-session-cache": "enable"}
)

# 构造超过 1024 Token 的长文本，确保能触发缓存创建（若未达到1024 Token，后续累积对话上下文超过1024 Token时将触发缓存创建）
long_context = "人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。" * 50

# 第一轮对话
response1 = client.responses.create(
    model="qwen3.8-max",
    input=long_context + "\n\n基于以上背景知识，请简短介绍机器学习中的随机森林算法。",
)
print(f"第一轮回复: {response1.output_text}")

# 第二轮对话：通过 previous_response_id 关联上下文，缓存由服务端自动处理
response2 = client.responses.create(
    model="qwen3.8-max",
    input="它和 GBDT 有什么主要区别？",
    extra_body={"previous_response_id": response1.id},
)
print(f"第二轮回复: {response2.output_text}")

# 查看缓存命中情况
usage = response2.usage
print(f"输入 Token: {usage.input_tokens}")
print(f"缓存命中 Token: {usage.input_tokens_details.cached_tokens}")