detect_entities async ¶

async def detect_entities(
    self,
    *,
    config_overrides: Optional[AsyncComprehendClientConfig] = None,
    text: Optional[
        "capo_comprehend.types.customer_input_string.CustomerInputString"
    ] = None,
    language_code: Optional[
        "capo_comprehend.types.language_code.LanguageCode"
    ] = None,
    endpoint_arn: Optional[
        "capo_comprehend.types.entity_recognizer_endpoint_arn.EntityRecognizerEndpointArn"
    ] = 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.detect_entities_response.DetectEntitiesResponse":
    """<p>Detects named entities in input text when you use the pre-trained model. Detects custom entities if you have a custom entity recognition model. </p> <p> When detecting named entities using the pre-trained model, use plain text as the input. For more information about named entities, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/how-entities.html">Entities</a> in the Comprehend Developer Guide.</p> <p>When you use a custom entity recognition model, you can input plain text or you can upload a single-page input document (text, PDF, Word, or image). </p> <p>If the system detects errors while processing a page in the input document, the API response includes an entry in <code>Errors</code> for each error. </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>A UTF-8 text string. The maximum string size is 100 KB. If you enter text using this parameter, do not use the <code>Bytes</code> parameter.</p>
        language_code: <p>The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. If your request includes the endpoint for a custom entity recognition model, Amazon Comprehend uses the language of your custom model, and it ignores any language code that you specify here.</p> <p>All input documents must be in the same language.</p>
        endpoint_arn: <p>The Amazon Resource Name of an endpoint that is associated with a custom entity recognition model. Provide an endpoint if you want to detect entities by using your own custom model instead of the default model that is used by Amazon Comprehend.</p> <p>If you specify an endpoint, Amazon Comprehend uses the language of your custom model, and it ignores any language code that you provide in your request.</p> <p>For information about endpoints, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/manage-endpoints.html">Managing endpoints</a>.</p>
        bytes: <p>This field applies only when you use a custom entity recognition model that was trained with PDF annotations. For other cases, enter your text input in the <code>Text</code> field.</p> <p> Use the <code>Bytes</code> parameter to input a text, PDF, Word or image file. Using a plain-text file in the <code>Bytes</code> parameter is equivelent to using the <code>Text</code> parameter (the <code>Entities</code> field in the response is identical).</p> <p>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>Provide the input document as a sequence of base64-encoded bytes. If your code uses an Amazon Web Services SDK to detect entities, 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.unsupported_language_exception.UnsupportedLanguageException: <p>Amazon Comprehend can't process the language of the input text. For a list of supported languages, <a href="https://docs.aws.amazon.com/comprehend/latest/dg/supported-languages.html">Supported languages</a> in the Comprehend Developer Guide. </p>
        capo_comprehend.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    async def _handler(
        req: "AsyncOperationRequest[capo_comprehend.types.detect_entities_request.DetectEntitiesRequest]",
    ) -> AsyncOperationResponse[
        "capo_comprehend.types.detect_entities_response.DetectEntitiesResponse"
    ]:
        import capo_comprehend._operations.comprehend_20171127.detect_entities

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

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

        return capo_comprehend.types.detect_entities_request.redact_sensitive(
            input_
        )

    interceptors_, options_ = self.operation_options(
        config_overrides,
        OperationLogging("DetectEntities", redact_input=_redact_input),
    )
    input_: capo_comprehend.types.detect_entities_request.DetectEntitiesRequest = {}
    if text is not None:
        input_["text"] = text
    if language_code is not None:
        input_["language_code"] = language_code
    if endpoint_arn is not None:
        input_["endpoint_arn"] = endpoint_arn
    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