Extracts key information from documents using KV templates or prompts with the Qwen-VL model, ideal for image extraction. Supports: URL Upload: SubmitVLExtractionTask. Local File Upload: SubmitVLExtractionTaskAdvance
Debugging
Authorization information
Request syntax
POST /api/v2/aidoc/document/submitVLExtractionTask HTTP/1.1
Request parameters
Parameter | Type | Required | Description | Example |
---|---|---|---|---|
fileUrl | string | No | Choose one of fileUrl or fileUrlObject:
Note
The relationship between file parsing methods and supported document types
| |
fileName | string | Yes | The filename must include the file type suffix. | example.pdf |
folderId | string | No |
| xxxxx |
templateId | string | No | Unique parsing template ID, used to specify the key-value pairs to be extracted from the document. You need to configure the template on the template management page and then obtain the corresponding template ID. | 572d24k0c95a |
Response parameters
Examples
Sample success responses
JSON
format
{
"requestId": "83A5A7DD-8974-5769-952E-590A97BEA34E",
"data": {
"taskId": "411ce93a-7eb5-40cf-836a-53c32f097663"
}
}
Error codes
For a list of error codes, visit the Service error codes.