Search by image

import os
import json
from openai import OpenAI

client = OpenAI(
    # If you have not configured the environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following URL is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
)

input_content = [
    {"type": "input_text", "text": "Find landscape images with a style similar to this one"},
    # Replace image_url with the actual public URL of the image
    {"type": "input_image", "image_url": "https://img.alicdn.com/imgextra/i4/O1CN01YbrnSS1qtmsAkw0Ud_!!6000000005554-2-tps-788-450.png"}
]

response = client.responses.create(
    model="qwen3.8-max",
    input=[{"role": "user", "content": input_content}],
    tools=[
        {
            "type": "image_search"
        }
    ]
)

# Traverse the output to display each step
for item in response.output:
    if item.type == "image_search_call":
        print(f"[Tool Call] Search by image (status: {item.status})")
        # Parse and display the list of searched images
        if item.output:
            images = json.loads(item.output)
            print(f"  Found {len(images)} images:")
            for img in images[:5]:  # Display the first 5 images
                print(f"  [{img['index']}] {img['title']}")
                print(f"      {img['url']}")
            if len(images) > 5:
                print(f"  ... {len(images)} images in total")
    elif item.type == "message":
        print(f"\n[Model Response]")
        print(response.output_text)

# Display token usage and tool call statistics
print(f"\n[Token Usage] Input: {response.usage.input_tokens}, Output: {response.usage.output_tokens}, Total: {response.usage.total_tokens}")
if hasattr(response.usage, 'x_tools') and response.usage.x_tools:
    for tool_name, info in response.usage.x_tools.items():
        print(f"[Tool Statistics] {tool_name} call count: {info.get('count', 0)}")

import os
import json
from openai import OpenAI

client = OpenAI(
    # If you have not configured the environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following URL is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
)

input_content = [
    {"type": "input_text", "text": "Find landscape images with a style similar to this one"},
    # Replace image_url with the actual public URL of the image
    {"type": "input_image", "image_url": "https://img.alicdn.com/imgextra/i4/O1CN01YbrnSS1qtmsAkw0Ud_!!6000000005554-2-tps-788-450.png"}
]

stream = client.responses.create(
    model="qwen3.8-max",
    input=[{"role": "user", "content": input_content}],
    tools=[{"type": "image_search"}],
    stream=True
)

for event in stream:
    # Tool call starts
    if event.type == "response.output_item.added":
        if event.item.type == "image_search_call":
            print("[Tool Call] Searching by image...")
    # Tool call is complete. Parse and display the list of searched images.
    elif event.type == "response.output_item.done":
        if event.item.type == "image_search_call":
            print(f"[Tool Call] Search by image complete (status: {event.item.status})")
            if event.item.output:
                images = json.loads(event.item.output)
                print(f"  Found {len(images)} images:")
                for img in images[:5]:  # Display the first 5 images
                    print(f"  [{img['index']}] {img['title']}")
                    print(f"      {img['url']}")
                if len(images) > 5:
                    print(f"  ... {len(images)} images in total")
    # Model response starts
    elif event.type == "response.content_part.added":
        print(f"\n[Model Response]")
    # Streamed text output
    elif event.type == "response.output_text.delta":
        print(event.delta, end="", flush=True)
    # Response is complete. Output the usage.
    elif event.type == "response.completed":
        usage = event.response.usage
        print(f"\n\n[Token Usage] Input: {usage.input_tokens}, Output: {usage.output_tokens}, Total: {usage.total_tokens}")
        if hasattr(usage, 'x_tools') and usage.x_tools:
            for tool_name, info in usage.x_tools.items():
                print(f"[Tool Statistics] {tool_name} call count: {info.get('count', 0)}")