DocumentReaderConfig ¶

class DocumentReaderConfig(TypedDict, closed=True):
    document_read_action: (
        "capo_comprehend.types.document_read_action.DocumentReadAction"
    )
    """<p>This field defines the Amazon Textract API operation that Amazon Comprehend uses to extract text from PDF files and image files. Enter one of the following values:</p> <ul> <li> <p> <code>TEXTRACT_DETECT_DOCUMENT_TEXT</code> - The Amazon Comprehend service uses the <code>DetectDocumentText</code> API operation. </p> </li> <li> <p> <code>TEXTRACT_ANALYZE_DOCUMENT</code> - The Amazon Comprehend service uses the <code>AnalyzeDocument</code> API operation. </p> </li> </ul>"""
    document_read_mode: NotRequired[
        "capo_comprehend.types.document_read_mode.DocumentReadMode"
    ]
    """<p>Determines the text extraction actions for PDF files. Enter one of the following values:</p> <ul> <li> <p> <code>SERVICE_DEFAULT</code> - use the Amazon Comprehend service defaults for PDF files.</p> </li> <li> <p> <code>FORCE_DOCUMENT_READ_ACTION</code> - Amazon Comprehend uses the Textract API specified by DocumentReadAction for all PDF files, including digital PDF files. </p> </li> </ul>"""
    feature_types: NotRequired[
        "capo_comprehend.types.list_of_document_read_feature_types.ListOfDocumentReadFeatureTypes"
    ]
    """<p>Specifies the type of Amazon Textract features to apply. If you chose <code>TEXTRACT_ANALYZE_DOCUMENT</code> as the read action, you must specify one or both of the following values:</p> <ul> <li> <p> <code>TABLES</code> - Returns additional information about any tables that are detected in the input document. </p> </li> <li> <p> <code>FORMS</code> - Returns additional information about any forms that are detected in the input document. </p> </li> </ul>"""