classify_document async ¶

async def classify_document(
    self,
    endpoint_arn: "capo_comprehend.types.document_classifier_endpoint_arn.DocumentClassifierEndpointArn",
    *,
    config_overrides: Optional[AsyncComprehendClientConfig] = None,
    text: Optional[
        "capo_comprehend.types.customer_input_string.CustomerInputString"
    ] = None,
    bytes: Optional[
        "capo_comprehend.types.semi_structured_document_blob.SemiStructuredDocumentBlob"
    ] = None,
    document_reader_config: Optional[
        "capo_comprehend.types.document_reader_config.DocumentReaderConfig"
    ] = None,
) -> "capo_comprehend.types.classify_document_response.ClassifyDocumentResponse":
    """<p>Creates a classification request to analyze a single document in real-time. <code>ClassifyDocument</code> supports the following model types:</p> <ul> <li> <p>Custom classifier - a custom model that you have created and trained. For input, you can provide plain text, a single-page document (PDF, Word, or image), or Amazon Textract API output. For more information, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/how-document-classification.html">Custom classification</a> in the <i>Amazon Comprehend Developer Guide</i>.</p> </li> <li> <p>Prompt safety classifier - Amazon Comprehend provides a pre-trained model for classifying input prompts for generative AI applications. For input, you provide English plain text input. For prompt safety classification, the response includes only the <code>Classes</code> field. For more information about prompt safety classifiers, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/trust-safety.html#prompt-classification">Prompt safety classification</a> in the <i>Amazon Comprehend Developer Guide</i>.</p> </li> </ul> <p>If the system detects errors while processing a page in the input document, the API response includes an <code>Errors</code> field that describes the errors.</p> <p>If the system detects a document-level error in your input document, the API returns an <code>InvalidRequestException</code> error response. For details about this exception, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/idp-inputs-sync-err.html"> Errors in semi-structured documents</a> in the Comprehend Developer Guide. </p>

    Args:
        text: <p>The document text to be analyzed. If you enter text using this parameter, do not use the <code>Bytes</code> parameter.</p>
        endpoint_arn: <p>The Amazon Resource Number (ARN) of the endpoint. </p> <p>For prompt safety classification, Amazon Comprehend provides the endpoint ARN. For more information about prompt safety classifiers, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/trust-safety.html#prompt-classification">Prompt safety classification</a> in the <i>Amazon Comprehend Developer Guide</i> </p> <p>For custom classification, you create an endpoint for your custom model. For more information, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/using-endpoints.html">Using Amazon Comprehend endpoints</a>.</p>
        bytes: <p>Use the <code>Bytes</code> parameter to input a text, PDF, Word or image file.</p> <p>When you classify a document using a custom model, you can also use the <code>Bytes</code> parameter to input an Amazon Textract <code>DetectDocumentText</code> or <code>AnalyzeDocument</code> output file.</p> <p>To classify a document using the prompt safety classifier, use the <code>Text</code> parameter for input.</p> <p>Provide the input document as a sequence of base64-encoded bytes. If your code uses an Amazon Web Services SDK to classify documents, the SDK may encode the document file bytes for you. </p> <p>The maximum length of this field depends on the input document type. For details, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/idp-inputs-sync.html"> Inputs for real-time custom analysis</a> in the Comprehend Developer Guide. </p> <p>If you use the <code>Bytes</code> parameter, do not use the <code>Text</code> parameter.</p>
        document_reader_config: <p>Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.</p>

    Raises:
        capo_comprehend.errors.internal_server_exception.InternalServerException: <p>An internal server error occurred. Retry your request.</p>
        capo_comprehend.errors.invalid_request_exception.InvalidRequestException: <p>The request is invalid.</p>
        capo_comprehend.errors.resource_unavailable_exception.ResourceUnavailableException: <p>The specified resource is not available. Check the resource and try your request again.</p>
        capo_comprehend.errors.text_size_limit_exceeded_exception.TextSizeLimitExceededException: <p>The size of the input text exceeds the limit. Use a smaller document.</p>
        capo_comprehend.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    async def _handler(
        req: "AsyncOperationRequest[capo_comprehend.types.classify_document_request.ClassifyDocumentRequest]",
    ) -> AsyncOperationResponse[
        "capo_comprehend.types.classify_document_response.ClassifyDocumentResponse"
    ]:
        import capo_comprehend._operations.comprehend_20171127.classify_document

        (
            output,
            http_response,
        ) = await capo_comprehend._operations.comprehend_20171127.classify_document.async_classify_document(
            req.options, req.input
        )
        return AsyncOperationResponse(output=output, response=http_response)

    def _redact_input(
        input_: "capo_comprehend.types.classify_document_request.ClassifyDocumentRequest",
    ) -> dict[str, Any]:
        import capo_comprehend.types.classify_document_request

        return capo_comprehend.types.classify_document_request.redact_sensitive(
            input_
        )

    interceptors_, options_ = self.operation_options(
        config_overrides,
        OperationLogging("ClassifyDocument", redact_input=_redact_input),
    )
    input_: capo_comprehend.types.classify_document_request.ClassifyDocumentRequest = {
        "endpoint_arn": endpoint_arn
    }
    if text is not None:
        input_["text"] = text
    if bytes is not None:
        input_["bytes"] = bytes
    if document_reader_config is not None:
        input_["document_reader_config"] = document_reader_config

    response = await aexecute_pipeline(
        AsyncOperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    await response.response.aclose()
    return response.output