POST
/
documents
/
v2
/
classify
cURL
curl --request POST \
  --url https://api.tensorlake.ai/documents/v2/classify \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "page_range": "1-5,8,10",
  "file_name": "document.pdf",
  "file_id": "file_abc123xyz",
  "mime_type": "application/pdf",
  "page_classifications": [
    {
      "name": "<string>",
      "description": "<string>"
    }
  ],
  "labels": {
    "priority": "high",
    "source": "email"
  }
}'
{
  "parse_id": "<string>",
  "created_at": "<string>"
}
Submit a uploaded file, an internet-reachable URL, or any kind of raw text for document parsing. If you have configured a webhook, we will notify you when the job is complete, be it a success or a failure. Once submitted, the API will return a parse response with a parse_id field. You can query the status and results of the parse operation with the Get Parse Result endpoint.

Using page classes

For this operation, you must pass in an array of categories along with their descriptions to guide the classifier in the page_classifications field. The API will return the page class for each page of the document. Each page class name must be unique within the document, and should be descriptive enough to convey the content of the page.

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

File source - must be exactly one of: file_id, file_url, or raw_text

Response

200
application/json

Created parse job details

The response is of type object.