Image content extraction

Prerequisites

Before you begin, make sure you have:

• An activated AI Search Open Platform — see Activate AI Search Open Platform

• An API key for authentication — see Manage API key

How it works

Image content extraction uses an asynchronous task model:

1. Submit an image to the service by calling create_image_analyze_task. The image can be a publicly accessible URL or a base64-encoded local file.

2. Receive a task_id from the response.

3. Poll get_image_analyze_task_status with the task_id until the task completes.

4. Read the extracted text from result.data.content in the final response.

Task status values:

The request body cannot exceed 8 MB. For full parameter details, see Image content extraction API.

Extract image content

The following examples use the Python SDK (alibabacloud_searchplat20240529). Both examples call create_image_analyze_task to submit the task and get_image_analyze_task_status to retrieve the result.

Replace the placeholder values before running:

import time
from alibabacloud_tea_openapi.models import Config
from alibabacloud_searchplat20240529.client import Client
from alibabacloud_searchplat20240529.models import (
    CreateImageAnalyzeTaskRequestDocument,
    CreateImageAnalyzeTaskRequest,
    CreateImageAnalyzeTaskResponse,
    GetImageAnalyzeTaskStatusRequest,
    GetImageAnalyzeTaskStatusResponse,
)

# Configure the client
config = Config(
    bearer_token="<your-api-key>",
    endpoint="<your-endpoint>",  # Do not include http://
    protocol="http",
)
client = Client(config=config)

# Submit the image by URL
document = CreateImageAnalyzeTaskRequestDocument(
    url="https://help-static-aliyun-doc.aliyuncs.com/assets/img/zh-CN/6802494071/p756843.png",
)
request = CreateImageAnalyzeTaskRequest(document=document)
response: CreateImageAnalyzeTaskResponse = client.create_image_analyze_task(
    "<your-workspace>", "<your-service-id>", request
)
task_id = response.body.result.task_id
print("task_id:", task_id)

# Poll until complete
poll_request = GetImageAnalyzeTaskStatusRequest(task_id=task_id)
while True:
    response: GetImageAnalyzeTaskStatusResponse = client.get_image_analyze_task_status(
        "<your-workspace>", "<your-service-id>", poll_request
    )
    status = response.body.result.status
    print("status:", status)

    if status == "PENDING":
        time.sleep(5)
    elif status == "SUCCESS":
        print("content:\n" + response.body.result.data.content)
        print("usage:", response.body.usage)
        break
    else:
        print("error:", response.body.result.error)
        break

import base64
import os
import time
from alibabacloud_tea_openapi.models import Config
from alibabacloud_searchplat20240529.client import Client
from alibabacloud_searchplat20240529.models import (
    CreateImageAnalyzeTaskRequestDocument,
    CreateImageAnalyzeTaskRequest,
    CreateImageAnalyzeTaskResponse,
    GetImageAnalyzeTaskStatusRequest,
    GetImageAnalyzeTaskStatusResponse,
)

# Configure the client
config = Config(
    bearer_token="<your-api-key>",
    endpoint="<your-endpoint>",  # Do not include http://
    protocol="http",
)
client = Client(config=config)

# Submit the image from a local file
file_path = "path/to/your/image.jpg"
with open(file_path, "rb") as f:
    encoded = base64.b64encode(f.read()).decode()

document = CreateImageAnalyzeTaskRequestDocument(
    content=encoded,
    file_name=os.path.basename(file_path),
)
request = CreateImageAnalyzeTaskRequest(document=document)
response: CreateImageAnalyzeTaskResponse = client.create_image_analyze_task(
    "<your-workspace>", "<your-service-id>", request
)
task_id = response.body.result.task_id
print("task_id:", task_id)

# Poll until complete
poll_request = GetImageAnalyzeTaskStatusRequest(task_id=task_id)
while True:
    response: GetImageAnalyzeTaskStatusResponse = client.get_image_analyze_task_status(
        "<your-workspace>", "<your-service-id>", poll_request
    )
    status = response.body.result.status
    print("status:", status)

    if status == "PENDING":
        time.sleep(5)
    elif status == "SUCCESS":
        print("content:\n" + response.body.result.data.content)
        print("usage:", response.body.usage)
        break
    else:
        print("error:", response.body.result.error)
        break

What's next

• Image content extraction API reference — full list of request parameters and response fields

• Manage API key — create, rotate, or revoke your API keys