Google Cloud Discovery Engine V1 Client - Class LayoutParsingConfig (1.6.0)

Reference documentation and code samples for the Google Cloud Discovery Engine V1 Client class LayoutParsingConfig.

The layout parsing configurations for documents.

Generated from protobuf message google.cloud.discoveryengine.v1.DocumentProcessingConfig.ParsingConfig.LayoutParsingConfig

Namespace

Google \ Cloud \ DiscoveryEngine \ V1 \ DocumentProcessingConfig \ ParsingConfig

Methods

__construct

Constructor.

Parameters
Name	Description
`data`	`array` Optional. Data for populating the Message object.
`↳ enable_table_annotation`	`bool` Optional. If true, the LLM based annotation is added to the table during parsing.
`↳ enable_image_annotation`	`bool` Optional. If true, the LLM based annotation is added to the image during parsing.
`↳ structured_content_types`	`array` Optional. Contains the required structure types to extract from the document. Supported values: * * `shareholder-structure`
`↳ exclude_html_elements`	`array` Optional. List of HTML elements to exclude from the parsed content.
`↳ exclude_html_classes`	`array` Optional. List of HTML classes to exclude from the parsed content.
`↳ exclude_html_ids`	`array` Optional. List of HTML ids to exclude from the parsed content.

getEnableTableAnnotation

Optional. If true, the LLM based annotation is added to the table during parsing.

Returns
Type	Description
`bool`

setEnableTableAnnotation

Optional. If true, the LLM based annotation is added to the table during parsing.

Parameter
Name	Description
`var`	`bool`

Returns
Type	Description
`$this`

getEnableImageAnnotation

Optional. If true, the LLM based annotation is added to the image during parsing.

Returns
Type	Description
`bool`

setEnableImageAnnotation

Optional. If true, the LLM based annotation is added to the image during parsing.

Parameter
Name	Description
`var`	`bool`

Returns
Type	Description
`$this`

getStructuredContentTypes

Optional. Contains the required structure types to extract from the document. Supported values:

shareholder-structure

Returns
Type	Description
`Google\Protobuf\Internal\RepeatedField`

setStructuredContentTypes

Optional. Contains the required structure types to extract from the document. Supported values:

shareholder-structure

Parameter
Name	Description
`var`	`string[]`

Returns
Type	Description
`$this`

getExcludeHtmlElements

Optional. List of HTML elements to exclude from the parsed content.

Returns
Type	Description
`Google\Protobuf\Internal\RepeatedField`

setExcludeHtmlElements