PredictModel

The BinaryToText parameter is optional.

Specify either the Content parameter for an image URL or the Body parameter for base64-encoded content. If you use Body, you must also set BinaryToText to true.

PDF files cannot exceed 20 MB or 10 pages. For model prediction types other than long document information extraction, the service processes only the first page of the document.

Description of fields in the Data object for long document information extraction models

originalFileUrl: The URL of the original file.
predictFile: A collection of image URLs, created by parsing the original file, used for prediction.
data: The specific prediction results.
angle: The rotation angle of the image. This field is returned only when `NeedRotate` is set to `true`. A value of 0 indicates the original orientation, 90 indicates a clockwise rotation, 180 indicates a 180-degree rotation, and 270 indicates a counterclockwise rotation. If `NeedRotate` is `true`, you must rotate the image according to this angle to use the returned coordinates.
content: A summary of the text blocks recognized in the image.
height: The height of the image after algorithmic correction.
width: The width of the image after algorithmic correction.
orgHeight: The height of the original image.
orgWidth: The width of the original image.
prism_wnum: The number of recognized text blocks. This value matches the size of the `prism_wordsInfo` array.

Description of fields in the prism_wordsInfo array

angle: The rotation angle of the text block. This angle only affects the `width` and `height` values. If the angle is -90, 90, -270, or 270, you must swap the `width` and `height` values.
height: The height of the text block.
width: The width of the text block.
pos: The four corner coordinates of the text block's bounding box, listed clockwise: top-left, top-right, bottom-right, and bottom-left. If `NeedRotate` is `true` and the top-level `angle` is not 0, you must rotate the image according to the top-level angle to use these coordinates.
word: The text content of the block.
tableId: The ID of the table containing this text block. This ID matches a `tableId` in the `prism_tablesInfo` array. Returned only if `OutputTable` is `true` and the text block is in a table.
tableCellId: The ID of the cell containing this text block. This ID matches a `tableCellId` in the `cellInfos` array. Returned only if `OutputTable` is `true` and the text block is in a table cell.

charInfo: Individual character information

word: The character.
x: The x-coordinate of the character's top-left corner.
y: The y-coordinate of the character's top-left corner.
w: The width of the character.
h: The height of the character.

Description of fields in the prism_tablesInfo array

tableId: The unique ID for the table. This ID is referenced by the `tableId` field in `prism_wordsInfo` objects.
xCellSize: The number of cells along the x-axis (columns) in the table.
yCellSize: The number of cells along the y-axis (rows) in the table.

cellInfos: Information about table cells, including their layout and structure.

tableCellId: The unique ID for the cell. This ID is referenced by the `tableCellId` field in `prism_wordsInfo` objects.
word: The text content of the cell.
xsc: Abbreviation for `xStartCell`. The starting column index for the cell, where the first column is 0.
xec: Abbreviation for `xEndCell`. The ending column index for the cell, where the first column is 0. If `xsc` and `xec` are both 0, this indicates a single cell in the first column.
ysc: Abbreviation for `yStartCell`. The starting row index for the cell, where the first row is 0.
yec: Abbreviation for `yEndCell`. The ending row index for the cell, where the first row is 0.
pos: The coordinates of the cell's corners, listed in clockwise order: top-left (X, Y), top-right (X, Y), bottom-right (X, Y), and bottom-left (X, Y).