PApatsnap
Others

L017 Layout-only Parsing (No OCR)

Run layout detection only, without OCR. Every results.content value is null and markdown is not returned. Supported types: png, jpg, jpeg, pdf, doc, docx, ppt, pptx, xls, and xlsx. include_crop_urls is optional and defaults to true.

post/rd-llm/v1/documents/layout_parsing

Request

Request body multipart/form-data

filestring required

File to analyze for layout.

Example request

{
  "file": "maximum 20MB"
}

Response

Successful l017 layout-only parsing (no ocr) response.

statusstring required

The request completed successfully.

error_msgstring required

Always success on success.

error_codeinteger required

Always 0 on success.

Example response

{
  "data": {
    "state": "success",
    "results": [
      {
        "url": "https://oss.example.com/doc/0_2.png?sign=...",
        "bbox": [
          0.16,
          0.18,
          0.37,
          0.2,
          0.9
        ],
        "type": "figure",
        "content": "null"
      }
    ],
    "file_type": "png",
    "total_pages": 1
  },
  "status": "success",
  "error_msg": "success"
}

Changes

No recorded changes to this operation across all 1 revision of this API.