Create a response

from openai import OpenAI
import json
import os
import random

# Initialize the client.
client = OpenAI(
    # If the environment variable is not set, replace with: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)
# Simulate a user question.
USER_QUESTION = "What's the weather like in Beijing?"
# Define the list of tools.
tools = [
    {
        "type": "function",
        "name": "get_current_weather",
        "description": "Useful for getting the weather in a specific city.",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city or district, such as Beijing or Hangzhou.",
                }
            },
            "required": ["location"],
        },
    }
]

# Simulate the weather query tool.
def get_current_weather(arguments):
    weather_conditions = ["sunny", "cloudy", "rainy"]
    random_weather = random.choice(weather_conditions)
    location = arguments["location"]
    return f"Today in {location} it is {random_weather}."

# Wrap the model response function.
def get_response(input_data):
    response = client.responses.create(
        model="qwen3.8-max",
        input=input_data,
        tools=tools,
    )
    return response

# Maintain the conversation context.
conversation = [{"role": "user", "content": USER_QUESTION}]

response = get_response(conversation)
function_calls = [item for item in response.output if item.type == "function_call"]
# If no tool call is needed, output the content directly.
if not function_calls:
    print(f"Final assistant response: {response.output_text}")
else:
    # Enter the tool-calling loop.
    while function_calls:
        for fc in function_calls:
            func_name = fc.name
            arguments = json.loads(fc.arguments)
            print(f"Calling tool [{func_name}] with arguments: {arguments}")
            # Execute the tool.
            tool_result = get_current_weather(arguments)
            print(f"Tool returned: {tool_result}")
            # Append the tool call and its result to the context as a pair.
            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,
                }
            )
        # Call the model again with the full context.
        response = get_response(conversation)
        function_calls = [
            item for item in response.output if item.type == "function_call"
        ]
    print(f"Final assistant response: {response.output_text}")

import os
from openai import OpenAI

client = OpenAI(
    # If you have not configured an environment variable, replace the next line with: 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": {}
    },
)

print(response.output_text)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
    # Enable the session cache via default_headers.
    default_headers={"x-dashscope-session-cache": "enable"}
)

# Construct a long text over 1024 tokens to trigger cache creation.
# If not, caching is triggered when the cumulative context exceeds 1024 tokens.
long_context = "Artificial intelligence (AI) is a major branch of computer science, dedicated to researching and developing theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence." * 50

# First turn
response1 = client.responses.create(
    model="qwen3.8-max",
    input=long_context + "\n\nBased on this context, briefly introduce the Random Forest algorithm in machine learning.",
)
print(f"First response: {response1.output_text}")

# Second turn: Link context using previous_response_id. The cache is handled automatically by the server.
response2 = client.responses.create(
    model="qwen3.8-max",
    input="What are the main differences between it and GBDT?",
    extra_body={"previous_response_id": response1.id}
)
print(f"Second response: {response2.output_text}")

# Check the cache hit status.
usage = response2.usage
print(f"Input tokens: {usage.input_tokens}")
print(f"Cached tokens: {usage.prompt_tokens_details.cached_tokens}")