ContentUnderstandingModelFactory.DocumentContent Method
Definition
Important
Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.
Document content. Ex. text/plain, application/pdf, image/jpeg.
public static Azure.AI.ContentUnderstanding.DocumentContent DocumentContent(string mimeType = default, string analyzerId = default, string category = default, string path = default, string markdown = default, System.Collections.Generic.IDictionary<string,Azure.AI.ContentUnderstanding.ContentField> fields = default, System.Collections.Generic.IDictionary<string,string> metadata = default, int startPageNumber = 0, int endPageNumber = 0, Azure.AI.ContentUnderstanding.LengthUnit? unit = default, System.Collections.Generic.IEnumerable<Azure.AI.ContentUnderstanding.DocumentPage> pages = default, System.Collections.Generic.IEnumerable<Azure.AI.ContentUnderstanding.DocumentParagraph> paragraphs = default, System.Collections.Generic.IEnumerable<Azure.AI.ContentUnderstanding.DocumentSection> sections = default, System.Collections.Generic.IEnumerable<Azure.AI.ContentUnderstanding.DocumentTable> tables = default, System.Collections.Generic.IEnumerable<Azure.AI.ContentUnderstanding.DocumentFigure> figures = default, System.Collections.Generic.IEnumerable<Azure.AI.ContentUnderstanding.DocumentAnnotation> annotations = default, System.Collections.Generic.IEnumerable<Azure.AI.ContentUnderstanding.DocumentSignature> signatures = default, System.Collections.Generic.IEnumerable<Azure.AI.ContentUnderstanding.DocumentHyperlink> hyperlinks = default, System.Collections.Generic.IEnumerable<Azure.AI.ContentUnderstanding.DocumentContentSegment> segments = default, System.Collections.Generic.IEnumerable<Azure.AI.ContentUnderstanding.DocumentChunk> chunks = default);static member DocumentContent : string * string * string * string * string * System.Collections.Generic.IDictionary<string, Azure.AI.ContentUnderstanding.ContentField> * System.Collections.Generic.IDictionary<string, string> * int * int * Nullable<Azure.AI.ContentUnderstanding.LengthUnit> * seq<Azure.AI.ContentUnderstanding.DocumentPage> * seq<Azure.AI.ContentUnderstanding.DocumentParagraph> * seq<Azure.AI.ContentUnderstanding.DocumentSection> * seq<Azure.AI.ContentUnderstanding.DocumentTable> * seq<Azure.AI.ContentUnderstanding.DocumentFigure> * seq<Azure.AI.ContentUnderstanding.DocumentAnnotation> * seq<Azure.AI.ContentUnderstanding.DocumentSignature> * seq<Azure.AI.ContentUnderstanding.DocumentHyperlink> * seq<Azure.AI.ContentUnderstanding.DocumentContentSegment> * seq<Azure.AI.ContentUnderstanding.DocumentChunk> -> Azure.AI.ContentUnderstanding.DocumentContentPublic Shared Function DocumentContent (Optional mimeType As String = Nothing, Optional analyzerId As String = Nothing, Optional category As String = Nothing, Optional path As String = Nothing, Optional markdown As String = Nothing, Optional fields As IDictionary(Of String, ContentField) = Nothing, Optional metadata As IDictionary(Of String, String) = Nothing, Optional startPageNumber As Integer = 0, Optional endPageNumber As Integer = 0, Optional unit As Nullable(Of LengthUnit) = Nothing, Optional pages As IEnumerable(Of DocumentPage) = Nothing, Optional paragraphs As IEnumerable(Of DocumentParagraph) = Nothing, Optional sections As IEnumerable(Of DocumentSection) = Nothing, Optional tables As IEnumerable(Of DocumentTable) = Nothing, Optional figures As IEnumerable(Of DocumentFigure) = Nothing, Optional annotations As IEnumerable(Of DocumentAnnotation) = Nothing, Optional signatures As IEnumerable(Of DocumentSignature) = Nothing, Optional hyperlinks As IEnumerable(Of DocumentHyperlink) = Nothing, Optional segments As IEnumerable(Of DocumentContentSegment) = Nothing, Optional chunks As IEnumerable(Of DocumentChunk) = Nothing) As DocumentContentParameters
- mimeType
- String
Detected MIME type of the content. Ex. application/pdf, image/jpeg, etc.
- analyzerId
- String
The analyzer that generated this content.
- category
- String
Classified content category.
- path
- String
The path of the content in the input.
- markdown
- String
Markdown representation of the content.
- fields
- IDictionary<String,ContentField>
Extracted fields from the content.
- metadata
- IDictionary<String,String>
Metadata extracted from the input as string key/value pairs, such as author, title, creation date, or media properties. Keys and values are strings. Only keys with extracted values are present.
- startPageNumber
- Int32
Start page number (1-indexed) of the content.
- endPageNumber
- Int32
End page number (1-indexed) of the content.
- unit
- Nullable<LengthUnit>
Length unit used by the width, height, and source properties. For images/tiff, the default unit is pixel. For PDF, the default unit is inch.
- pages
- IEnumerable<DocumentPage>
List of pages in the document.
- paragraphs
- IEnumerable<DocumentParagraph>
List of paragraphs in the document. Only if enableOcr and returnDetails are true.
- sections
- IEnumerable<DocumentSection>
List of sections in the document. Only if enableLayout and returnDetails are true.
- tables
- IEnumerable<DocumentTable>
List of tables in the document. Only if enableLayout and returnDetails are true.
- figures
- IEnumerable<DocumentFigure>
List of figures in the document. Only if enableLayout and returnDetails are true.
- annotations
- IEnumerable<DocumentAnnotation>
List of annotations in the document. Only if enableAnnotations and returnDetails are true.
- signatures
- IEnumerable<DocumentSignature>
List of signatures in the document. Only if enableLayout and returnDetails are true.
- hyperlinks
- IEnumerable<DocumentHyperlink>
List of hyperlinks in the document. Only if returnDetails are true.
- segments
- IEnumerable<DocumentContentSegment>
List of detected content segments. Only if enableSegment is true.
- chunks
- IEnumerable<DocumentChunk>
List of document chunks. Only if chunkingStrategy is configured on the analyzer.
Returns
A new DocumentContent instance for mocking.
