Share via

DocumentIntelligenceLayoutSkill interface

Package:
@azure/search-documents

A skill that extracts content and layout information, via Azure AI Services, from files within the enrichment pipeline.

Extends
BaseSearchIndexerSkill

Properties

chunkingProperties

Controls the cardinality for chunking the content.
extractionOptions

Controls the cardinality of the content extracted from the document by the skill
markdownHeaderDepth

The depth of headers in the markdown output. Default is h6.
odatatype

Polymorphic discriminator, which specifies the different types this object can be
outputFormat

Controls the cardinality of the output format. Default is 'markdown'.
outputMode

Controls the cardinality of the output produced by the skill. Default is 'oneToMany'.

Inherited Properties

context

Represents the level at which operations take place, such as the document root or document content (for example, /document or /document/content). The default is /document.
description

The description of the skill which describes the inputs, outputs, and usage of the skill.
inputs

Inputs of the skills could be a column in the source data set, or the output of an upstream skill.
name

The name of the skill which uniquely identifies it within the skillset. A skill with no name defined will be given a default name of its 1-based index in the skills array, prefixed with the character '#'.
outputs

The output of a skill is either a field in a search index, or a value that can be consumed as an input by another skill.

Property Details

chunkingProperties

Controls the cardinality for chunking the content.

chunkingProperties?: DocumentIntelligenceLayoutSkillChunkingProperties

Property Value

DocumentIntelligenceLayoutSkillChunkingProperties

extractionOptions

Controls the cardinality of the content extracted from the document by the skill

extractionOptions?: string[]

Property Value

string[]

markdownHeaderDepth

The depth of headers in the markdown output. Default is h6.

markdownHeaderDepth?: string

Property Value

string

odatatype

Polymorphic discriminator, which specifies the different types this object can be

odatatype: "#Microsoft.Skills.Util.DocumentIntelligenceLayoutSkill"

Property Value

"#Microsoft.Skills.Util.DocumentIntelligenceLayoutSkill"

outputFormat

Controls the cardinality of the output format. Default is 'markdown'.

outputFormat?: string

Property Value

string

outputMode

Controls the cardinality of the output produced by the skill. Default is 'oneToMany'.

outputMode?: string

Property Value

string

Inherited Property Details

context

Represents the level at which operations take place, such as the document root or document content (for example, /document or /document/content). The default is /document.

context?: string

Property Value

string

Inherited From SearchIndexerSkill.context

description

The description of the skill which describes the inputs, outputs, and usage of the skill.

description?: string

Property Value

string

Inherited From SearchIndexerSkill.description

inputs

Inputs of the skills could be a column in the source data set, or the output of an upstream skill.

inputs: InputFieldMappingEntry[]

Property Value

InputFieldMappingEntry[]

Inherited From SearchIndexerSkill.inputs

name

The name of the skill which uniquely identifies it within the skillset. A skill with no name defined will be given a default name of its 1-based index in the skills array, prefixed with the character '#'.

name?: string

Property Value

string

Inherited From SearchIndexerSkill.name

outputs

The output of a skill is either a field in a search index, or a value that can be consumed as an input by another skill.

outputs: OutputFieldMappingEntry[]

Property Value

OutputFieldMappingEntry[]

Inherited From SearchIndexerSkill.outputs