ContentAnalyzerConfig Class

Definition

Configuration settings for an analyzer.

public class ContentAnalyzerConfig : System.ClientModel.Primitives.IJsonModel<Azure.AI.ContentUnderstanding.ContentAnalyzerConfig>, System.ClientModel.Primitives.IPersistableModel<Azure.AI.ContentUnderstanding.ContentAnalyzerConfig>
type ContentAnalyzerConfig = class
    interface IJsonModel<ContentAnalyzerConfig>
    interface IPersistableModel<ContentAnalyzerConfig>
Public Class ContentAnalyzerConfig
Implements IJsonModel(Of ContentAnalyzerConfig), IPersistableModel(Of ContentAnalyzerConfig)
Inheritance
ContentAnalyzerConfig
Implements

Constructors

Name Description
ContentAnalyzerConfig()

Initializes a new instance of ContentAnalyzerConfig.

Properties

Name Description
AllowInPageSegments

Enable sub-page segmentation. When true, segments may cover a portion of a page instead of full pages.

AllowInputTruncation

When true, input that exceeds the service's processable-unit limit is truncated to the limit and returned as a partial result with a warning, instead of failing. Field extraction and segmentation, where configured, run over the processed content and may be inaccurate. Defaults to false. Overridable per request by the allowInputTruncation query parameter.

AnnotationFormat

Representation format of annotations in analyze result markdown.

ChartFormat

Representation format of charts in analyze result markdown.

ChunkingStrategy

Strategy for chunking document content into smaller units for RAG scenarios. When omitted, chunking is disabled.

ContentCategories

Map of categories to classify the input content(s) against.

DisableFaceBlurring

Disable the default blurring of faces for privacy while processing the content.

EnableFigureAnalysis

Enable analysis of figures, such as charts and diagrams.

EnableFigureDescription

Enable generation of figure description.

EnableFormula

Enable mathematical formula detection.

EnableLayout

Enable layout analysis.

EnableOcr

Enable optical character recognition (OCR).

EnableSegment

Enable segmentation of the input by contentCategories.

EstimateFieldSourceAndConfidence

Return field grounding source and confidence.

Locales

List of locale hints for speech transcription.

SegmentPerPage

Force segmentation of document content by page.

ShouldOmitContent

Omit the content for this analyzer from analyze result. Only return content(s) from additional analyzers specified in contentCategories, if any.

ShouldReturnDetails

Return all content details.

TableFormat

Representation format of tables in analyze result markdown.

Workflow

Workflow used for content analysis.

Methods

Name Description
JsonModelCreateCore(Utf8JsonReader, ModelReaderWriterOptions)
JsonModelWriteCore(Utf8JsonWriter, ModelReaderWriterOptions)
PersistableModelCreateCore(BinaryData, ModelReaderWriterOptions)
PersistableModelWriteCore(ModelReaderWriterOptions)

Explicit Interface Implementations

Name Description
IJsonModel<ContentAnalyzerConfig>.Create(Utf8JsonReader, ModelReaderWriterOptions)
IJsonModel<ContentAnalyzerConfig>.Write(Utf8JsonWriter, ModelReaderWriterOptions)
IPersistableModel<ContentAnalyzerConfig>.Create(BinaryData, ModelReaderWriterOptions)
IPersistableModel<ContentAnalyzerConfig>.GetFormatFromOptions(ModelReaderWriterOptions)
IPersistableModel<ContentAnalyzerConfig>.Write(ModelReaderWriterOptions)

Applies to