Smaws_Client_Comprehend.Typestype nonrec warnings_list_item = {warn_message : string_ option;Text message associated with the warning.
*)warn_code : page_based_warning_code option;The type of warning.
*)page : integer option;Page number in the input document.
*)}The system identified one of the following warnings while processing the input document:
type nonrec security_group_ids = security_group_id listtype nonrec subnets = subnet_id listtype nonrec vpc_config = {subnets : subnets;The ID for each subnet being used in your private VPC. This subnet is a subset of the a range of IPv4 addresses used by the VPC and is specific to a given availability zone in the VPC’s Region. This ID number is preceded by "subnet-", for instance: "subnet-04ccf456919e69055". For more information, see VPCs and Subnets.
*)security_group_ids : security_group_ids;The ID number for a security group on an instance of your private VPC. Security groups on your VPC function serve as a virtual firewall to control inbound and outbound traffic and provides security for the resources that you’ll be accessing on the VPC. This ID number is preceded by "sg-", for instance: "sg-03b388029b0a285ea". For more information, see Security Groups for your VPC.
*)}Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for the job. For more information, see Amazon VPC.
type nonrec labels_list = label_list_item listtype nonrec document_classification_config = {labels : labels_list option;One or more labels to associate with the custom classifier.
*)mode : document_classifier_mode;Classification mode indicates whether the documents are MULTI_CLASS or MULTI_LABEL.
}Configuration required for a document classification model.
type nonrec entity_types_list_item = {type_ : entity_type_name;An entity type within a labeled training dataset that Amazon Comprehend uses to train a custom entity recognizer.
Entity types must not contain the following invalid characters: \n (line break), \\n (escaped line break, \r (carriage return), \\r (escaped carriage return), \t (tab), \\t (escaped tab), and , (comma).
*)}An entity type within a labeled training dataset that Amazon Comprehend uses to train a custom entity recognizer.
type nonrec entity_types_list = entity_types_list_item listtype nonrec entity_recognition_config = {entity_types : entity_types_list;Up to 25 entity types that the model is trained to recognize.
*)}Configuration required for an entity recognition model.
type nonrec task_config = {entity_recognition_config : entity_recognition_config option;Configuration required for an entity recognition model.
*)document_classification_config : document_classification_config option;Configuration required for a document classification model.
*)language_code : language_code;Language code for the language that the model supports.
*)}Configuration about the model associated with a flywheel.
type nonrec data_security_config = {vpc_config : vpc_config option;data_lake_kms_key_id : kms_key_id option;ID for the KMS key that Amazon Comprehend uses to encrypt the data in the data lake.
*)volume_kms_key_id : kms_key_id option;ID for the KMS key that Amazon Comprehend uses to encrypt the volume.
*)model_kms_key_id : kms_key_id option;ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"}Data security configuration.
type nonrec flywheel_properties = {latest_flywheel_iteration : flywheel_iteration_id option;The most recent flywheel iteration.
*)last_modified_time : timestamp option;Last modified time for the flywheel.
*)creation_time : timestamp option;Creation time of the flywheel.
*)message : any_length_string option;A description of the status of the flywheel.
*)model_type : model_type option;Model type of the flywheel's model.
*)status : flywheel_status option;The status of the flywheel.
*)data_security_config : data_security_config option;Data security configuration.
*)data_lake_s3_uri : s3_uri option;Amazon S3 URI of the data lake location.
*)task_config : task_config option;Configuration about the model associated with a flywheel.
*)data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend permission to access the flywheel data.
*)active_model_arn : comprehend_model_arn option;The Amazon Resource Number (ARN) of the active model version.
*)flywheel_arn : comprehend_flywheel_arn option;The Amazon Resource Number (ARN) of the flywheel.
*)}The flywheel properties.
type nonrec update_flywheel_response = {flywheel_properties : flywheel_properties option;The flywheel properties.
*)}type nonrec update_data_security_config = {vpc_config : vpc_config option;volume_kms_key_id : kms_key_id option;ID for the KMS key that Amazon Comprehend uses to encrypt the volume.
*)model_kms_key_id : kms_key_id option;ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"}Data security configuration.
type nonrec update_flywheel_request = {data_security_config : update_data_security_config option;Flywheel data security configuration.
*)data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend permission to access the flywheel data.
*)active_model_arn : comprehend_model_arn option;The Amazon Resource Number (ARN) of the active model version.
*)flywheel_arn : comprehend_flywheel_arn;The Amazon Resource Number (ARN) of the flywheel to update.
*)}The number of requests exceeds the limit. Resubmit your request later.
The specified resource ARN was not found. Check the ARN and try your request again.
The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.
type nonrec invalid_request_detail = {reason : invalid_request_detail_reason option;Reason codes include the following values:
}Provides additional detail about why the request failed.
type nonrec invalid_request_exception = {detail : invalid_request_detail option;reason : invalid_request_reason option;message : string_ option;}The request is invalid.
An internal server error occurred. Retry your request.
type nonrec update_endpoint_response = {desired_model_arn : comprehend_model_arn option;The Amazon Resource Number (ARN) of the new model.
*)}type nonrec update_endpoint_request = {flywheel_arn : comprehend_flywheel_arn option;The Amazon Resource Number (ARN) of the flywheel
*)desired_data_access_role_arn : iam_role_arn option;Data access role ARN to use in case the new model is encrypted with a customer CMK.
*)desired_inference_units : inference_units_integer option;The desired number of inference units to be used by the model using this endpoint. Each inference unit represents of a throughput of 100 characters per second.
*)desired_model_arn : comprehend_model_arn option;The ARN of the new model to use when updating an existing endpoint.
*)endpoint_arn : comprehend_endpoint_arn;The Amazon Resource Number (ARN) of the endpoint being updated.
*)}The specified resource is not available. Check the resource and try your request again.
The maximum number of resources per account has been exceeded. Review the resources, and then try your request again.
The specified resource name is already in use. Use a different name and try your request again.
type nonrec tag_key_list = tag_key listtype nonrec untag_resource_request = {tag_keys : tag_key_list;The initial part of a key-value pair that forms a tag being removed from a given resource. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department. Keys must be unique and cannot be duplicated for a particular resource.
*)resource_arn : comprehend_arn;The Amazon Resource Name (ARN) of the given Amazon Comprehend resource from which you want to remove the tags.
*)}The request contains more tag keys than can be associated with a resource (50 tag keys per resource).
Concurrent modification of the tags associated with an Amazon Comprehend resource is not supported.
Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.
type nonrec toxic_content = {score : float_ option;Model confidence in the detected content type. Value range is zero to one, where one is highest confidence.
*)name : toxic_content_type option;The name of the toxic content type.
*)}Toxic content analysis result for one string. For more information about toxicity detection, see Toxicity detection in the Amazon Comprehend Developer Guide
type nonrec list_of_toxic_content = toxic_content listtype nonrec toxic_labels = {toxicity : float_ option;Overall toxicity score for the string. Value range is zero to one, where one is the highest confidence.
*)labels : list_of_toxic_content option;Array of toxic content types identified in the string.
*)}Toxicity analysis result for one string. For more information about toxicity detection, see Toxicity detection in the Amazon Comprehend Developer Guide.
type nonrec list_of_document_read_feature_types =
document_read_feature_types listtype nonrec document_reader_config = {feature_types : list_of_document_read_feature_types option;Specifies the type of Amazon Textract features to apply. If you chose TEXTRACT_ANALYZE_DOCUMENT as the read action, you must specify one or both of the following values:
TABLES - Returns additional information about any tables that are detected in the input document.FORMS - Returns additional information about any forms that are detected in the input document.document_read_mode : document_read_mode option;Determines the text extraction actions for PDF files. Enter one of the following values:
SERVICE_DEFAULT - use the Amazon Comprehend service defaults for PDF files.FORCE_DOCUMENT_READ_ACTION - Amazon Comprehend uses the Textract API specified by DocumentReadAction for all PDF files, including digital PDF files.document_read_action : document_read_action;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:
TEXTRACT_DETECT_DOCUMENT_TEXT - The Amazon Comprehend service uses the DetectDocumentText API operation.TEXTRACT_ANALYZE_DOCUMENT - The Amazon Comprehend service uses the AnalyzeDocument API operation.}Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.
By default, Amazon Comprehend performs the following actions to extract text from files, based on the input file type:
DetectDocumentText API to extract the text.DocumentReaderConfig does not apply to plain text files or Word files.
For image files and PDF documents, you can override these default actions using the fields listed below. For more information, see Setting text extraction options in the Comprehend Developer Guide.
type nonrec input_data_config = {document_reader_config : document_reader_config option;Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.
*)input_format : input_format option;Specifies how the text in an input file should be processed:
ONE_DOC_PER_FILE - Each file is considered a separate document. Use this option when you are processing large documents, such as newspaper articles or scientific papers.ONE_DOC_PER_LINE - Each line in a file is considered a separate document. Use this option when you are processing many short documents, such as text messages.s3_uri : s3_uri;The Amazon S3 URI for the input data. The URI must be in same Region as the API endpoint that you are calling. The URI can point to a single input file or it can provide the prefix for a collection of data files.
For example, if you use the URI S3://bucketName/prefix, if the prefix is a single file, Amazon Comprehend uses that file as input. If more than one file begins with the prefix, Amazon Comprehend uses all of them as input.
}The input properties for an inference job. The document reader config field applies only to non-text inputs for custom analysis.
type nonrec output_data_config = {kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the output results from an analysis job. Specify the Key Id of a symmetric key, because you cannot use an asymmetric key for uploading data to S3.
The KmsKeyId can be one of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab""alias/ExampleAlias""arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias"s3_uri : s3_uri;When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. The URI must be in the same Region as the API endpoint that you are calling. The location is used as the prefix for the actual location of the output file.
When the topic detection job is finished, the service creates an output file in a directory specific to the job. The S3Uri field contains the location of the output file, called output.tar.gz. It is a compressed archive that contains the ouput of the operation.
For a PII entity detection job, the output file is plain text, not a compressed archive. The output file name is the same as the input file, with .out appended at the end.
}Provides configuration parameters for the output of inference jobs.
type nonrec topics_detection_job_properties = {vpc_config : vpc_config option;Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your topic detection job. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your job data.
*)number_of_topics : integer option;The number of topics to detect supplied when you created the topic detection job. The default is 10.
*)output_data_config : output_data_config option;The output data configuration supplied when you created the topic detection job.
*)input_data_config : input_data_config option;The input data configuration supplied when you created the topic detection job.
*)end_time : timestamp option;The time that the topic detection job was completed.
*)submit_time : timestamp option;The time that the topic detection job was submitted for processing.
*)message : any_length_string option;A description for the status of a job.
*)job_status : job_status option;The current status of the topic detection job. If the status is Failed, the reason for the failure is shown in the Message field.
job_name : job_name option;The name of the topic detection job.
*)job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the topics detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::topics-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:topics-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier assigned to the topic detection job.
*)}Provides information about a topic detection job.
type nonrec topics_detection_job_properties_list =
topics_detection_job_properties listtype nonrec topics_detection_job_filter = {submit_time_after : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Only returns jobs submitted after the specified time. Jobs are returned in ascending order, oldest to newest.
*)submit_time_before : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Only returns jobs submitted before the specified time. Jobs are returned in descending order, newest to oldest.
*)job_status : job_status option;Filters the list of topic detection jobs based on job status. Returns only jobs with the specified status.
*)job_name : job_name option;}Provides information for filtering topic detection jobs. For more information, see .
The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.
The size of the input text exceeds the limit. Use a smaller document.
One of the of text strings. Each string has a size limit of 1KB.
type nonrec sentiment_score = {mixed : float_ option;The level of confidence that Amazon Comprehend has in the accuracy of its detection of the MIXED sentiment.
neutral : float_ option;The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEUTRAL sentiment.
negative : float_ option;The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEGATIVE sentiment.
positive : float_ option;The level of confidence that Amazon Comprehend has in the accuracy of its detection of the POSITIVE sentiment.
}Describes the level of confidence that Amazon Comprehend has in the accuracy of its detection of sentiments.
type nonrec mention_sentiment = {sentiment_score : sentiment_score option;sentiment : sentiment_type option;The sentiment of the mention.
*)}Contains the sentiment and sentiment score for one mention of an entity.
For more information about targeted sentiment, see Targeted sentiment in the Amazon Comprehend Developer Guide.
type nonrec targeted_sentiment_mention = {end_offset : integer option;The offset into the document text where the mention ends.
*)begin_offset : integer option;The offset into the document text where the mention begins.
*)mention_sentiment : mention_sentiment option;Contains the sentiment and sentiment score for the mention.
*)type_ : targeted_sentiment_entity_type option;text : string_ option;The text in the document that identifies the entity.
*)group_score : float_ option;The confidence that all the entities mentioned in the group relate to the same entity.
*)score : float_ option;Model confidence that the entity is relevant. Value range is zero to one, where one is highest confidence.
*)}Information about one mention of an entity. The mention information includes the location of the mention in the text and the sentiment of the mention.
For more information about targeted sentiment, see Targeted sentiment in the Amazon Comprehend Developer Guide.
type nonrec list_of_descriptive_mention_indices = integer listtype nonrec list_of_mentions = targeted_sentiment_mention listtype nonrec targeted_sentiment_entity = {mentions : list_of_mentions option;An array of mentions of the entity in the document. The array represents a co-reference group. See Co-reference group for an example.
*)descriptive_mention_index : list_of_descriptive_mention_indices option;One or more index into the Mentions array that provides the best name for the entity group.
*)}Information about one of the entities found by targeted sentiment analysis.
For more information about targeted sentiment, see Targeted sentiment in the Amazon Comprehend Developer Guide.
type nonrec targeted_sentiment_detection_job_properties = {vpc_config : vpc_config option;volume_kms_key_id : kms_key_id option;ID for the KMS key that Amazon Comprehend uses to encrypt the data on the storage volume attached to the ML compute instance(s) that process the targeted sentiment detection job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)language_code : language_code option;The language code of the input documents.
*)output_data_config : output_data_config option;input_data_config : input_data_config option;end_time : timestamp option;The time that the targeted sentiment detection job ended.
*)submit_time : timestamp option;The time that the targeted sentiment detection job was submitted for processing.
*)message : any_length_string option;A description of the status of a job.
*)job_status : job_status option;The current status of the targeted sentiment detection job. If the status is FAILED, the Messages field shows the reason for the failure.
job_name : job_name option;The name that you assigned to the targeted sentiment detection job.
*)job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the targeted sentiment detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::targeted-sentiment-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:targeted-sentiment-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier assigned to the targeted sentiment detection job.
*)}Provides information about a targeted sentiment detection job.
type nonrec targeted_sentiment_detection_job_properties_list =
targeted_sentiment_detection_job_properties listtype nonrec targeted_sentiment_detection_job_filter = {submit_time_after : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
*)submit_time_before : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
*)job_status : job_status option;Filters the list of jobs based on job status. Returns only jobs with the specified status.
*)job_name : job_name option;Filters on the name of the job.
*)}Provides information for filtering a list of dominant language detection jobs. For more information, see the ListTargetedSentimentDetectionJobs operation.
type nonrec target_event_types = event_type_string listtype nonrec tag = {value : tag_value option;The second part of a key-value pair that forms a tag associated with a given resource. For instance, if you want to show which resources are used by which departments, you might use “Department” as the initial (key) portion of the pair, with a value of “sales” to indicate the sales department.
*)key : tag_key;The initial part of a key-value pair that forms a tag associated with a given resource. For instance, if you want to show which resources are used by which departments, you might use “Department” as the key portion of the pair, with multiple possible values such as “sales,” “legal,” and “administration.”
*)}A key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with the key-value pair ‘Department’:’Sales’ might be added to a resource to indicate its use by a particular department.
type nonrec tag_list = tag listtype nonrec tag_resource_request = {resource_arn : comprehend_arn;The Amazon Resource Name (ARN) of the given Amazon Comprehend resource to which you want to associate the tags.
*)}type nonrec part_of_speech_tag = {score : float_ option;The confidence that Amazon Comprehend has that the part of speech was correctly identified.
*)tag : part_of_speech_tag_type option;Identifies the part of speech that the token represents.
*)}Identifies the part of speech represented by the token and gives the confidence that Amazon Comprehend has that the part of speech was correctly identified. For more information about the parts of speech that Amazon Comprehend can identify, see Syntax in the Comprehend Developer Guide.
type nonrec syntax_token = {part_of_speech : part_of_speech_tag option;Provides the part of speech label and the confidence level that Amazon Comprehend has that the part of speech was correctly identified. For more information, see Syntax in the Comprehend Developer Guide.
*)end_offset : integer option;The zero-based offset from the beginning of the source text to the last character in the word.
*)begin_offset : integer option;The zero-based offset from the beginning of the source text to the first character in the word.
*)text : string_ option;The word that was recognized in the source text.
*)token_id : integer option;A unique identifier for a token.
*)}Represents a work in the input text that was recognized and assigned a part of speech. There is one syntax token record for each word in the source text.
type nonrec string_list = string_ listtype nonrec stop_training_entity_recognizer_request = {entity_recognizer_arn : entity_recognizer_arn;The Amazon Resource Name (ARN) that identifies the entity recognizer currently being trained.
*)}type nonrec stop_training_document_classifier_request = {document_classifier_arn : document_classifier_arn;The Amazon Resource Name (ARN) that identifies the document classifier currently being trained.
*)}type nonrec stop_targeted_sentiment_detection_job_response = {job_status : job_status option;Either STOP_REQUESTED if the job is currently running, or STOPPED if the job was previously stopped with the StopSentimentDetectionJob operation.
job_id : job_id option;The identifier of the targeted sentiment detection job to stop.
*)}type nonrec stop_targeted_sentiment_detection_job_request = {job_id : job_id;The identifier of the targeted sentiment detection job to stop.
*)}The specified job was not found. Check the job ID and try again.
type nonrec stop_sentiment_detection_job_response = {job_status : job_status option;Either STOP_REQUESTED if the job is currently running, or STOPPED if the job was previously stopped with the StopSentimentDetectionJob operation.
job_id : job_id option;The identifier of the sentiment detection job to stop.
*)}type nonrec stop_sentiment_detection_job_request = {job_id : job_id;The identifier of the sentiment detection job to stop.
*)}type nonrec stop_pii_entities_detection_job_response = {job_status : job_status option;The status of the PII entities detection job.
*)job_id : job_id option;The identifier of the PII entities detection job to stop.
*)}type nonrec stop_pii_entities_detection_job_request = {job_id : job_id;The identifier of the PII entities detection job to stop.
*)}type nonrec stop_key_phrases_detection_job_response = {job_status : job_status option;Either STOP_REQUESTED if the job is currently running, or STOPPED if the job was previously stopped with the StopKeyPhrasesDetectionJob operation.
job_id : job_id option;The identifier of the key phrases detection job to stop.
*)}type nonrec stop_key_phrases_detection_job_request = {job_id : job_id;The identifier of the key phrases detection job to stop.
*)}type nonrec stop_events_detection_job_response = {job_status : job_status option;The status of the events detection job.
*)job_id : job_id option;The identifier of the events detection job to stop.
*)}type nonrec stop_events_detection_job_request = {job_id : job_id;The identifier of the events detection job to stop.
*)}type nonrec stop_entities_detection_job_response = {job_status : job_status option;Either STOP_REQUESTED if the job is currently running, or STOPPED if the job was previously stopped with the StopEntitiesDetectionJob operation.
job_id : job_id option;The identifier of the entities detection job to stop.
*)}type nonrec stop_entities_detection_job_request = {job_id : job_id;The identifier of the entities detection job to stop.
*)}type nonrec stop_dominant_language_detection_job_response = {job_status : job_status option;Either STOP_REQUESTED if the job is currently running, or STOPPED if the job was previously stopped with the StopDominantLanguageDetectionJob operation.
job_id : job_id option;The identifier of the dominant language detection job to stop.
*)}type nonrec stop_dominant_language_detection_job_request = {job_id : job_id;The identifier of the dominant language detection job to stop.
*)}type nonrec start_topics_detection_job_response = {job_status : job_status option;The status of the job:
DescribeTopicDetectionJob operation.job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the topics detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::topics-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:document-classification-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier generated for the job. To get the status of the job, use this identifier with the DescribeTopicDetectionJob operation.
}type nonrec start_topics_detection_job_request = {vpc_config : vpc_config option;Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your topic detection job. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"client_request_token : client_request_token_string option;A unique identifier for the request. If you do not set the client request token, Amazon Comprehend generates one.
*)number_of_topics : number_of_topics_integer option;The number of topics to detect.
*)job_name : job_name option;The identifier of the job.
*)data_access_role_arn : iam_role_arn;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data. For more information, see Role-based permissions.
*)output_data_config : output_data_config;Specifies where to send the output files. The output is a compressed archive with two files, topic-terms.csv that lists the terms associated with each topic, and doc-topics.csv that lists the documents associated with each topic
input_data_config : input_data_config;Specifies the format and location of the input data for the job.
*)}type nonrec start_targeted_sentiment_detection_job_response = {job_status : job_status option;The status of the job.
DescribeTargetedSentimentDetectionJob operation.job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the targeted sentiment detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::targeted-sentiment-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:targeted-sentiment-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier generated for the job. To get the status of a job, use this identifier with the DescribeTargetedSentimentDetectionJob operation.
}type nonrec start_targeted_sentiment_detection_job_request = {vpc_config : vpc_config option;volume_kms_key_id : kms_key_id option;ID for the KMS key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"client_request_token : client_request_token_string option;A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
*)language_code : language_code;The language of the input documents. Currently, English is the only supported language.
*)job_name : job_name option;The identifier of the job.
*)data_access_role_arn : iam_role_arn;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data. For more information, see Role-based permissions.
*)output_data_config : output_data_config;Specifies where to send the output files.
*)input_data_config : input_data_config;}type nonrec start_sentiment_detection_job_response = {job_status : job_status option;The status of the job.
job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the sentiment detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::sentiment-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:sentiment-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier generated for the job. To get the status of a job, use this identifier with the operation.
*)}type nonrec start_sentiment_detection_job_request = {vpc_config : vpc_config option;Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your sentiment detection job. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"client_request_token : client_request_token_string option;A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
*)language_code : language_code;The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
*)job_name : job_name option;The identifier of the job.
*)data_access_role_arn : iam_role_arn;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data. For more information, see Role-based permissions.
*)output_data_config : output_data_config;Specifies where to send the output files.
*)input_data_config : input_data_config;Specifies the format and location of the input data for the job.
*)}type nonrec start_pii_entities_detection_job_response = {job_status : job_status option;The status of the job.
*)job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the PII entity detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::pii-entities-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:pii-entities-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier generated for the job.
*)}type nonrec pii_entity_type = | IN_VOTER_NUMBER| IN_AADHAAR| CA_HEALTH_NUMBER| UK_NATIONAL_HEALTH_SERVICE_NUMBER| SWIFT_CODE| INTERNATIONAL_BANK_ACCOUNT_NUMBER| IN_NREGA| IN_PERMANENT_ACCOUNT_NUMBER| UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER| US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER| CA_SOCIAL_INSURANCE_NUMBER| UK_NATIONAL_INSURANCE_NUMBER| VEHICLE_IDENTIFICATION_NUMBER| LICENSE_PLATE| ALL| MAC_ADDRESS| IP_ADDRESS| AWS_SECRET_KEY| AWS_ACCESS_KEY| PASSWORD| USERNAME| AGE| URL| DRIVER_ID| PASSPORT_NUMBER| DATE_TIME| SSN| PHONE| NAME| ADDRESS| EMAIL| PIN| CREDIT_DEBIT_EXPIRY| CREDIT_DEBIT_CVV| CREDIT_DEBIT_NUMBER| BANK_ROUTING| BANK_ACCOUNT_NUMBERtype nonrec list_of_pii_entity_types = pii_entity_type listtype nonrec redaction_config = {mask_character : mask_character option;A character that replaces each character in the redacted PII entity.
*)mask_mode : pii_entities_detection_mask_mode option;Specifies whether the PII entity is redacted with the mask character or the entity type.
*)pii_entity_types : list_of_pii_entity_types option;An array of the types of PII entities that Amazon Comprehend detects in the input text for your request.
*)}Provides configuration parameters for PII entity redaction.
type nonrec start_pii_entities_detection_job_request = {client_request_token : client_request_token_string option;A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
*)language_code : language_code;The language of the input documents. Enter the language code for English (en) or Spanish (es).
*)job_name : job_name option;The identifier of the job.
*)data_access_role_arn : iam_role_arn;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)redaction_config : redaction_config option;Provides configuration parameters for PII entity redaction.
This parameter is required if you set the Mode parameter to ONLY_REDACTION. In that case, you must provide a RedactionConfig definition that includes the PiiEntityTypes parameter.
mode : pii_entities_detection_mode;Specifies whether the output provides the locations (offsets) of PII entities or a file in which PII entities are redacted.
*)output_data_config : output_data_config;Provides configuration parameters for the output of PII entity detection jobs.
*)input_data_config : input_data_config;The input properties for a PII entities detection job.
*)}type nonrec start_key_phrases_detection_job_response = {job_status : job_status option;The status of the job.
job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the key phrase detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::key-phrases-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:key-phrases-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier generated for the job. To get the status of a job, use this identifier with the operation.
*)}type nonrec start_key_phrases_detection_job_request = {vpc_config : vpc_config option;Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your key phrases detection job. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"client_request_token : client_request_token_string option;A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
*)language_code : language_code;The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
*)job_name : job_name option;The identifier of the job.
*)data_access_role_arn : iam_role_arn;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data. For more information, see Role-based permissions.
*)output_data_config : output_data_config;Specifies where to send the output files.
*)input_data_config : input_data_config;Specifies the format and location of the input data for the job.
*)}type nonrec start_flywheel_iteration_response = {flywheel_iteration_id : flywheel_iteration_id option;flywheel_arn : comprehend_flywheel_arn option;}type nonrec start_flywheel_iteration_request = {client_request_token : client_request_token_string option;A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
*)flywheel_arn : comprehend_flywheel_arn;The ARN of the flywheel.
*)}type nonrec start_events_detection_job_response = {job_status : job_status option;The status of the events detection job.
*)job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the events detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::events-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:events-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;An unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
*)}type nonrec start_events_detection_job_request = {target_event_types : target_event_types;The types of events to detect in the input documents.
*)client_request_token : client_request_token_string option;An unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
*)language_code : language_code;The language code of the input documents.
*)job_name : job_name option;The identifier of the events detection job.
*)data_access_role_arn : iam_role_arn;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)output_data_config : output_data_config;Specifies where to send the output files.
*)input_data_config : input_data_config;Specifies the format and location of the input data for the job.
*)}type nonrec start_entities_detection_job_response = {entity_recognizer_arn : entity_recognizer_arn option;The ARN of the custom entity recognition model.
*)job_status : job_status option;The status of the job.
job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the entities detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::entities-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:entities-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier generated for the job. To get the status of job, use this identifier with the operation.
*)}type nonrec start_entities_detection_job_request = {flywheel_arn : comprehend_flywheel_arn option;The Amazon Resource Number (ARN) of the flywheel associated with the model to use.
*)vpc_config : vpc_config option;Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your entity detection job. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"client_request_token : client_request_token_string option;A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
*)language_code : language_code;The language of the input documents. All documents must be in the same language. You can specify any of the languages supported by Amazon Comprehend. If custom entities recognition is used, this parameter is ignored and the language used for training the model is used instead.
*)entity_recognizer_arn : entity_recognizer_arn option;The Amazon Resource Name (ARN) that identifies the specific entity recognizer to be used by the StartEntitiesDetectionJob. This ARN is optional and is only used for a custom entity recognition job.
job_name : job_name option;The identifier of the job.
*)data_access_role_arn : iam_role_arn;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data. For more information, see Role-based permissions.
*)output_data_config : output_data_config;Specifies where to send the output files.
*)input_data_config : input_data_config;Specifies the format and location of the input data for the job.
*)}type nonrec start_dominant_language_detection_job_response = {job_status : job_status option;The status of the job.
job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the dominant language detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::dominant-language-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:dominant-language-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier generated for the job. To get the status of a job, use this identifier with the operation.
*)}type nonrec start_dominant_language_detection_job_request = {vpc_config : vpc_config option;Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your dominant language detection job. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"client_request_token : client_request_token_string option;A unique identifier for the request. If you do not set the client request token, Amazon Comprehend generates one.
*)job_name : job_name option;An identifier for the job.
*)data_access_role_arn : iam_role_arn;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data. For more information, see Role-based permissions.
*)output_data_config : output_data_config;Specifies where to send the output files.
*)input_data_config : input_data_config;Specifies the format and location of the input data for the job.
*)}type nonrec start_document_classification_job_response = {document_classifier_arn : document_classifier_arn option;The ARN of the custom classification model.
*)job_status : job_status option;The status of the job:
DescribeDocumentClassificationJob operation.job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the document classification job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::document-classification-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:document-classification-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier generated for the job. To get the status of the job, use this identifier with the DescribeDocumentClassificationJob operation.
}type nonrec start_document_classification_job_request = {flywheel_arn : comprehend_flywheel_arn option;The Amazon Resource Number (ARN) of the flywheel associated with the model to use.
*)vpc_config : vpc_config option;Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your document classification job. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"client_request_token : client_request_token_string option;A unique identifier for the request. If you do not set the client request token, Amazon Comprehend generates one.
*)data_access_role_arn : iam_role_arn;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)output_data_config : output_data_config;Specifies where to send the output files.
*)input_data_config : input_data_config;Specifies the format and location of the input data for the job.
*)document_classifier_arn : document_classifier_arn option;The Amazon Resource Name (ARN) of the document classifier to use to process the job.
*)job_name : job_name option;The identifier of the job.
*)}type nonrec sentiment_detection_job_properties = {vpc_config : vpc_config option;Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your sentiment detection job. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)language_code : language_code option;The language code of the input documents.
*)output_data_config : output_data_config option;The output data configuration that you supplied when you created the sentiment detection job.
*)input_data_config : input_data_config option;The input data configuration that you supplied when you created the sentiment detection job.
*)end_time : timestamp option;The time that the sentiment detection job ended.
*)submit_time : timestamp option;The time that the sentiment detection job was submitted for processing.
*)message : any_length_string option;A description of the status of a job.
*)job_status : job_status option;The current status of the sentiment detection job. If the status is FAILED, the Messages field shows the reason for the failure.
job_name : job_name option;The name that you assigned to the sentiment detection job
*)job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the sentiment detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::sentiment-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:sentiment-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier assigned to the sentiment detection job.
*)}Provides information about a sentiment detection job.
type nonrec sentiment_detection_job_properties_list =
sentiment_detection_job_properties listtype nonrec sentiment_detection_job_filter = {submit_time_after : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
*)submit_time_before : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
*)job_status : job_status option;Filters the list of jobs based on job status. Returns only jobs with the specified status.
*)job_name : job_name option;Filters on the name of the job.
*)}Provides information for filtering a list of dominant language detection jobs. For more information, see the operation.
type nonrec relationships_list_item = {type_ : relationship_type option;Only supported relationship is a child relationship.
*)ids : string_list option;Identifers of the child blocks.
*)}List of child blocks for the current block.
type nonrec put_resource_policy_response = {policy_revision_id : policy_revision_id option;The revision ID of the policy. Each time you modify a policy, Amazon Comprehend assigns a new revision ID, and it deletes the prior version of the policy.
*)}type nonrec put_resource_policy_request = {policy_revision_id : policy_revision_id option;The revision ID that Amazon Comprehend assigned to the policy that you are updating. If you are creating a new policy that has no prior version, don't use this parameter. Amazon Comprehend creates the revision ID for you.
*)resource_policy : policy;The JSON resource-based policy to attach to your custom model. Provide your JSON as a UTF-8 encoded string without line breaks. To provide valid JSON for your policy, enclose the attribute names and values in double quotes. If the JSON body is also enclosed in double quotes, then you must escape the double quotes that are inside the policy:
"{\"attribute\": \"value\", \"attribute\": [\"value\"]}"
To avoid escaping quotes, you can use single quotes to enclose the policy and double quotes to enclose the JSON names and values:
'{"attribute": "value", "attribute": ["value"]}'
resource_arn : comprehend_model_arn;The Amazon Resource Name (ARN) of the custom model to attach the policy to.
*)}type nonrec point = {y : float_ option;The value of the Y coordinate for a point on a polygon
*)x : float_ option;The value of the X coordinate for a point on a polygon
*)}The X and Y coordinates of a point on a document page.
For additional information, see Point in the Amazon Textract API reference.
type nonrec polygon = point listtype nonrec pii_output_data_config = {kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the output results from an analysis job.
*)s3_uri : s3_uri;When you use the PiiOutputDataConfig object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data.
For a PII entity detection job, the output file is plain text, not a compressed archive. The output file name is the same as the input file, with .out appended at the end.
}Provides configuration parameters for the output of PII entity detection jobs.
type nonrec pii_entity = {end_offset : integer option;The zero-based offset from the beginning of the source text to the last character in the entity.
*)begin_offset : integer option;The zero-based offset from the beginning of the source text to the first character in the entity.
*)type_ : pii_entity_type option;The entity's type.
*)score : float_ option;The level of confidence that Amazon Comprehend has in the accuracy of the detection.
*)}Provides information about a PII entity.
type nonrec pii_entities_detection_job_properties = {mode : pii_entities_detection_mode option;Specifies whether the output provides the locations (offsets) of PII entities or a file in which PII entities are redacted.
*)data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)language_code : language_code option;The language code of the input documents.
*)redaction_config : redaction_config option;Provides configuration parameters for PII entity redaction.
This parameter is required if you set the Mode parameter to ONLY_REDACTION. In that case, you must provide a RedactionConfig definition that includes the PiiEntityTypes parameter.
output_data_config : pii_output_data_config option;The output data configuration that you supplied when you created the PII entities detection job.
*)input_data_config : input_data_config option;The input properties for a PII entities detection job.
*)end_time : timestamp option;The time that the PII entities detection job completed.
*)submit_time : timestamp option;The time that the PII entities detection job was submitted for processing.
*)message : any_length_string option;A description of the status of a job.
*)job_status : job_status option;The current status of the PII entities detection job. If the status is FAILED, the Message field shows the reason for the failure.
job_name : job_name option;The name that you assigned the PII entities detection job.
*)job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the PII entities detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::pii-entities-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:pii-entities-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier assigned to the PII entities detection job.
*)}Provides information about a PII entities detection job.
type nonrec pii_entities_detection_job_properties_list =
pii_entities_detection_job_properties listtype nonrec pii_entities_detection_job_filter = {submit_time_after : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
*)submit_time_before : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
*)job_status : job_status option;Filters the list of jobs based on job status. Returns only jobs with the specified status.
*)job_name : job_name option;Filters on the name of the job.
*)}Provides information for filtering a list of PII entity detection jobs.
type nonrec number_of_documents = Smaws_Lib.CoreTypes.Int64.ttype nonrec list_topics_detection_jobs_response = {next_token : string_ option;Identifies the next page of results to return.
*)topics_detection_job_properties_list : topics_detection_job_properties_list
option;A list containing the properties of each job that is returned.
*)}type nonrec list_topics_detection_jobs_request = {max_results : max_results_integer option;The maximum number of results to return in each page. The default is 100.
*)next_token : string_ option;Identifies the next page of results to return.
*)filter : topics_detection_job_filter option;Filters the jobs that are returned. Jobs can be filtered on their name, status, or the date and time that they were submitted. You can set only one filter at a time.
*)}The filter specified for the operation is invalid. Specify a different filter.
type nonrec list_targeted_sentiment_detection_jobs_response = {next_token : string_ option;Identifies the next page of results to return.
*)targeted_sentiment_detection_job_properties_list : targeted_sentiment_detection_job_properties_list
option;A list containing the properties of each job that is returned.
*)}type nonrec list_targeted_sentiment_detection_jobs_request = {max_results : max_results_integer option;The maximum number of results to return in each page. The default is 100.
*)next_token : string_ option;Identifies the next page of results to return.
*)filter : targeted_sentiment_detection_job_filter option;Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
*)}type nonrec list_sentiment_detection_jobs_response = {next_token : string_ option;Identifies the next page of results to return.
*)sentiment_detection_job_properties_list : sentiment_detection_job_properties_list
option;A list containing the properties of each job that is returned.
*)}type nonrec list_sentiment_detection_jobs_request = {max_results : max_results_integer option;The maximum number of results to return in each page. The default is 100.
*)next_token : string_ option;Identifies the next page of results to return.
*)filter : sentiment_detection_job_filter option;Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
*)}type nonrec list_pii_entities_detection_jobs_response = {next_token : string_ option;Identifies the next page of results to return.
*)pii_entities_detection_job_properties_list : pii_entities_detection_job_properties_list
option;A list containing the properties of each job that is returned.
*)}type nonrec list_pii_entities_detection_jobs_request = {max_results : max_results_integer option;The maximum number of results to return in each page.
*)next_token : string_ option;Identifies the next page of results to return.
*)filter : pii_entities_detection_job_filter option;Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
*)}type nonrec list_of_warnings = warnings_list_item listtype nonrec list_of_toxic_labels = toxic_labels listtype nonrec list_of_text_segments = text_segment listtype nonrec list_of_targeted_sentiment_entities =
targeted_sentiment_entity listtype nonrec list_of_syntax_tokens = syntax_token listtype nonrec list_of_relationships = relationships_list_item listtype nonrec list_of_pii_entities = pii_entity listtype nonrec document_label = {page : integer option;Page number where the label occurs. This field is present in the response only if your request includes the Byte parameter.
score : float_ option;The confidence score that Amazon Comprehend has this label correctly attributed.
*)name : string_ option;The name of the label.
*)}Specifies one of the label or labels that categorize the document being analyzed.
type nonrec list_of_labels = document_label listtype nonrec key_phrase = {end_offset : integer option;The zero-based offset from the beginning of the source text to the last character in the key phrase.
*)begin_offset : integer option;The zero-based offset from the beginning of the source text to the first character in the key phrase.
*)text : string_ option;The text of a key noun phrase.
*)score : float_ option;The level of confidence that Amazon Comprehend has in the accuracy of the detection.
*)}Describes a key noun phrase.
type nonrec list_of_key_phrases = key_phrase listtype nonrec extracted_characters_list_item = {count : integer option;Number of characters extracted from each page.
*)page : integer option;Page number.
*)}Array of the number of characters extracted from each page.
type nonrec list_of_extracted_characters = extracted_characters_list_item listtype nonrec errors_list_item = {error_message : string_ option;Text message explaining the reason for the error.
*)error_code : page_based_error_code option;Error code for the cause of the error.
*)page : integer option;Page number where the error occurred.
*)}Text extraction encountered one or more page-level errors in the input document.
The ErrorCode contains one of the following values:
type nonrec list_of_errors = errors_list_item listtype nonrec entity_label = {score : float_ option;The level of confidence that Amazon Comprehend has in the accuracy of the detection.
*)name : pii_entity_type option;The name of the label.
*)}Specifies one of the label or labels that categorize the personally identifiable information (PII) entity being analyzed.
type nonrec list_of_entity_labels = entity_label listtype nonrec child_block = {end_offset : integer option;Offset of the end of the child block within its parent block.
*)begin_offset : integer option;Offset of the start of the child block within its parent block.
*)child_block_id : string_ option;Unique identifier for the child block.
*)}Nested block contained within a block.
type nonrec list_of_child_blocks = child_block listtype nonrec block_reference = {child_blocks : list_of_child_blocks option;List of child blocks within this block.
*)end_offset : integer option;Offset of the end of the block within its parent block.
*)begin_offset : integer option;Offset of the start of the block within its parent block.
*)block_id : string_ option;Unique identifier for the block.
*)}A reference to a block.
type nonrec list_of_block_references = block_reference listtype nonrec entity = {block_references : list_of_block_references option;A reference to each block for this entity. This field is empty for plain-text input.
*)end_offset : integer option;The zero-based offset from the beginning of the source text to the last character in the entity.
This field is empty for non-text input.
*)begin_offset : integer option;The zero-based offset from the beginning of the source text to the first character in the entity.
This field is empty for non-text input.
*)text : string_ option;The text of the entity.
*)type_ : entity_type option;The entity type. For entity detection using the built-in model, this field contains one of the standard entity types listed below.
For custom entity detection, this field contains one of the entity types that you specified when you trained your custom model.
*)score : float_ option;The level of confidence that Amazon Comprehend has in the accuracy of the detection.
*)}Provides information about an entity.
type nonrec list_of_entities = entity listtype nonrec dominant_language = {score : float_ option;The level of confidence that Amazon Comprehend has in the accuracy of the detection.
*)language_code : string_ option;The RFC 5646 language code for the dominant language. For more information about RFC 5646, see Tags for Identifying Languages on the IETF Tools web site.
*)}Returns the code for the dominant language in the input text and the level of confidence that Amazon Comprehend has in the accuracy of the detection.
type nonrec list_of_dominant_languages = dominant_language listtype nonrec document_type_list_item = {type_ : document_type option;Document type.
*)page : integer option;Page number.
*)}Document type for each page in the document.
type nonrec list_of_document_type = document_type_list_item listtype nonrec batch_detect_targeted_sentiment_item_result = {entities : list_of_targeted_sentiment_entities option;An array of targeted sentiment entities.
*)index : integer option;The zero-based index of this result in the input list.
*)}Analysis results for one of the documents in the batch.
type nonrec list_of_detect_targeted_sentiment_result =
batch_detect_targeted_sentiment_item_result listtype nonrec batch_detect_syntax_item_result = {syntax_tokens : list_of_syntax_tokens option;The syntax tokens for the words in the document, one token for each word.
*)index : integer option;The zero-based index of the document in the input list.
*)}The result of calling the operation. The operation returns one object that is successfully processed by the operation.
type nonrec list_of_detect_syntax_result = batch_detect_syntax_item_result listtype nonrec batch_detect_sentiment_item_result = {sentiment_score : sentiment_score option;The level of confidence that Amazon Comprehend has in the accuracy of its sentiment detection.
*)sentiment : sentiment_type option;The sentiment detected in the document.
*)index : integer option;The zero-based index of the document in the input list.
*)}The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.
type nonrec list_of_detect_sentiment_result =
batch_detect_sentiment_item_result listtype nonrec batch_detect_key_phrases_item_result = {key_phrases : list_of_key_phrases option;One or more KeyPhrase objects, one for each key phrase detected in the document.
index : integer option;The zero-based index of the document in the input list.
*)}The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.
type nonrec list_of_detect_key_phrases_result =
batch_detect_key_phrases_item_result listtype nonrec batch_detect_entities_item_result = {entities : list_of_entities option;One or more Entity objects, one for each entity detected in the document.
index : integer option;The zero-based index of the document in the input list.
*)}The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.
type nonrec list_of_detect_entities_result =
batch_detect_entities_item_result listtype nonrec batch_detect_dominant_language_item_result = {languages : list_of_dominant_languages option;One or more DominantLanguage objects describing the dominant languages in the document.
index : integer option;The zero-based index of the document in the input list.
*)}The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.
type nonrec list_of_detect_dominant_language_result =
batch_detect_dominant_language_item_result listtype nonrec document_class = {page : integer option;Page number in the input document. This field is present in the response only if your request includes the Byte parameter.
score : float_ option;The confidence score that Amazon Comprehend has this class correctly attributed.
*)name : string_ option;The name of the class.
*)}Specifies the class that categorizes the document being analyzed
type nonrec list_of_classes = document_class listtype nonrec bounding_box = {width : float_ option;The width of the bounding box as a ratio of the overall document page width.
*)top : float_ option;The top coordinate of the bounding box as a ratio of overall document page height.
*)left : float_ option;The left coordinate of the bounding box as a ratio of overall document page width.
*)height : float_ option;The height of the bounding box as a ratio of the overall document page height.
*)}The bounding box around the detected page or around an element on a document page. The left (x-coordinate) and top (y-coordinate) are coordinates that represent the top and left sides of the bounding box. Note that the upper-left corner of the image is the origin (0,0).
For additional information, see BoundingBox in the Amazon Textract API reference.
type nonrec geometry = {polygon : polygon option;Within the bounding box, a fine-grained polygon around the recognized item.
*)bounding_box : bounding_box option;An axis-aligned coarse representation of the location of the recognized item on the document page.
*)}Information about the location of items on a document page.
For additional information, see Geometry in the Amazon Textract API reference.
type nonrec block = {relationships : list_of_relationships option;A list of child blocks of the current block. For example, a LINE object has child blocks for each WORD block that's part of the line of text.
*)geometry : geometry option;Co-ordinates of the rectangle or polygon that contains the text.
*)page : integer option;Page number where the block appears.
*)text : string_ option;The word or line of text extracted from the block.
*)block_type : block_type option;The block represents a line of text or one word of text.
id : string_ option;Unique identifier for the block.
*)}Information about each word or line of text in the input document.
For additional information, see Block in the Amazon Textract API reference.
type nonrec list_of_blocks = block listtype nonrec key_phrases_detection_job_properties = {vpc_config : vpc_config option;Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your key phrases detection job. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the KMS key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)language_code : language_code option;The language code of the input documents.
*)output_data_config : output_data_config option;The output data configuration that you supplied when you created the key phrases detection job.
*)input_data_config : input_data_config option;The input data configuration that you supplied when you created the key phrases detection job.
*)end_time : timestamp option;The time that the key phrases detection job completed.
*)submit_time : timestamp option;The time that the key phrases detection job was submitted for processing.
*)message : any_length_string option;A description of the status of a job.
*)job_status : job_status option;The current status of the key phrases detection job. If the status is FAILED, the Message field shows the reason for the failure.
job_name : job_name option;The name that you assigned the key phrases detection job.
*)job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the key phrases detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::key-phrases-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:key-phrases-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier assigned to the key phrases detection job.
*)}Provides information about a key phrases detection job.
type nonrec key_phrases_detection_job_properties_list =
key_phrases_detection_job_properties listtype nonrec list_key_phrases_detection_jobs_response = {next_token : string_ option;Identifies the next page of results to return.
*)key_phrases_detection_job_properties_list : key_phrases_detection_job_properties_list
option;A list containing the properties of each job that is returned.
*)}type nonrec key_phrases_detection_job_filter = {submit_time_after : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
*)submit_time_before : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
*)job_status : job_status option;Filters the list of jobs based on job status. Returns only jobs with the specified status.
*)job_name : job_name option;Filters on the name of the job.
*)}Provides information for filtering a list of dominant language detection jobs. For more information, see the operation.
type nonrec list_key_phrases_detection_jobs_request = {max_results : max_results_integer option;The maximum number of results to return in each page. The default is 100.
*)next_token : string_ option;Identifies the next page of results to return.
*)filter : key_phrases_detection_job_filter option;Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
*)}type nonrec flywheel_summary = {latest_flywheel_iteration : flywheel_iteration_id option;The most recent flywheel iteration.
*)last_modified_time : timestamp option;Last modified time for the flywheel.
*)creation_time : timestamp option;Creation time of the flywheel.
*)message : any_length_string option;A description of the status of the flywheel.
*)model_type : model_type option;Model type of the flywheel's model.
*)status : flywheel_status option;The status of the flywheel.
*)data_lake_s3_uri : s3_uri option;Amazon S3 URI of the data lake location.
*)active_model_arn : comprehend_model_arn option;ARN of the active model version for the flywheel.
*)flywheel_arn : comprehend_flywheel_arn option;The Amazon Resource Number (ARN) of the flywheel
*)}Flywheel summary information.
type nonrec flywheel_summary_list = flywheel_summary listtype nonrec list_flywheels_response = {next_token : string_ option;Identifies the next page of results to return.
*)flywheel_summary_list : flywheel_summary_list option;A list of flywheel properties retrieved by the service in response to the request.
*)}type nonrec flywheel_filter = {creation_time_before : timestamp option;Filter the flywheels to include flywheels created before the specified time.
*)creation_time_after : timestamp option;Filter the flywheels to include flywheels created after the specified time.
*)status : flywheel_status option;Filter the flywheels based on the flywheel status.
*)}Filter the flywheels based on creation time or flywheel status.
type nonrec list_flywheels_request = {max_results : max_results_integer option;Maximum number of results to return in a response. The default is 100.
*)next_token : string_ option;Identifies the next page of results to return.
*)filter : flywheel_filter option;Filters the flywheels that are returned. You can filter flywheels on their status, or the date and time that they were submitted. You can only set one filter at a time.
*)}type nonrec flywheel_model_evaluation_metrics = {average_accuracy : double option;Average accuracy metric for the model.
*)average_recall : double option;Average recall metric for the model.
*)average_precision : double option;Average precision metric for the model.
*)average_f1_score : double option;The average F1 score from the evaluation metrics.
*)}The evaluation metrics associated with the evaluated model.
type nonrec flywheel_iteration_properties = {evaluation_manifest_s3_prefix : s3_uri option;trained_model_metrics : flywheel_model_evaluation_metrics option;The metrics associated with the trained model.
*)trained_model_arn : comprehend_model_arn option;The ARN of the trained model associated with this flywheel iteration.
*)evaluated_model_metrics : flywheel_model_evaluation_metrics option;evaluated_model_arn : comprehend_model_arn option;The ARN of the evaluated model associated with this flywheel iteration.
*)message : any_length_string option;A description of the status of the flywheel iteration.
*)status : flywheel_iteration_status option;The status of the flywheel iteration.
*)end_time : timestamp option;The completion time of this flywheel iteration.
*)creation_time : timestamp option;The creation start time of the flywheel iteration.
*)flywheel_iteration_id : flywheel_iteration_id option;flywheel_arn : comprehend_flywheel_arn option;}The configuration properties of a flywheel iteration.
type nonrec flywheel_iteration_properties_list =
flywheel_iteration_properties listtype nonrec list_flywheel_iteration_history_response = {next_token : string_ option;Next token
*)flywheel_iteration_properties_list : flywheel_iteration_properties_list option;List of flywheel iteration properties
*)}type nonrec flywheel_iteration_filter = {creation_time_before : timestamp option;Filter the flywheel iterations to include iterations created before the specified time.
*)creation_time_after : timestamp option;Filter the flywheel iterations to include iterations created after the specified time.
*)}Filter the flywheel iterations based on creation time.
type nonrec list_flywheel_iteration_history_request = {max_results : max_results_integer option;Maximum number of iteration history results to return
*)next_token : string_ option;Next token
*)filter : flywheel_iteration_filter option;Filter the flywheel iteration history based on creation time.
*)flywheel_arn : comprehend_flywheel_arn;The ARN of the flywheel.
*)}type nonrec events_detection_job_properties = {target_event_types : target_event_types option;The types of events that are detected by the job.
*)data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)language_code : language_code option;The language code of the input documents.
*)output_data_config : output_data_config option;The output data configuration that you supplied when you created the events detection job.
*)input_data_config : input_data_config option;The input data configuration that you supplied when you created the events detection job.
*)end_time : timestamp option;The time that the events detection job completed.
*)submit_time : timestamp option;The time that the events detection job was submitted for processing.
*)message : any_length_string option;A description of the status of the events detection job.
*)job_status : job_status option;The current status of the events detection job.
*)job_name : job_name option;The name you assigned the events detection job.
*)job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the events detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::events-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:events-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier assigned to the events detection job.
*)}Provides information about an events detection job.
type nonrec events_detection_job_properties_list =
events_detection_job_properties listtype nonrec list_events_detection_jobs_response = {next_token : string_ option;Identifies the next page of results to return.
*)events_detection_job_properties_list : events_detection_job_properties_list
option;A list containing the properties of each job that is returned.
*)}type nonrec events_detection_job_filter = {submit_time_after : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
*)submit_time_before : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
*)job_status : job_status option;Filters the list of jobs based on job status. Returns only jobs with the specified status.
*)job_name : job_name option;Filters on the name of the events detection job.
*)}Provides information for filtering a list of event detection jobs.
type nonrec list_events_detection_jobs_request = {max_results : max_results_integer option;The maximum number of results to return in each page.
*)next_token : string_ option;Identifies the next page of results to return.
*)filter : events_detection_job_filter option;Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
*)}type nonrec entity_recognizer_documents = {input_format : input_format option;Specifies how the text in an input file should be processed. This is optional, and the default is ONE_DOC_PER_LINE. ONE_DOC_PER_FILE - Each file is considered a separate document. Use this option when you are processing large documents, such as newspaper articles or scientific papers. ONE_DOC_PER_LINE - Each line in a file is considered a separate document. Use this option when you are processing many short documents, such as text messages.
*)test_s3_uri : s3_uri option;Specifies the Amazon S3 location where the test documents for an entity recognizer are located. The URI must be in the same Amazon Web Services Region as the API endpoint that you are calling.
*)s3_uri : s3_uri;Specifies the Amazon S3 location where the training documents for an entity recognizer are located. The URI must be in the same Region as the API endpoint that you are calling.
*)}Describes the training documents submitted with an entity recognizer.
type nonrec entity_recognizer_annotations = {test_s3_uri : s3_uri option;Specifies the Amazon S3 location where the test annotations for an entity recognizer are located. The URI must be in the same Region as the API endpoint that you are calling.
*)s3_uri : s3_uri;Specifies the Amazon S3 location where the annotations for an entity recognizer are located. The URI must be in the same Region as the API endpoint that you are calling.
*)}Describes the annotations associated with a entity recognizer.
type nonrec entity_recognizer_entity_list = {s3_uri : s3_uri;Specifies the Amazon S3 location where the entity list is located. The URI must be in the same Region as the API endpoint that you are calling.
*)}Describes the entity list submitted with an entity recognizer.
type nonrec attribute_names_list = attribute_names_list_item listtype nonrec augmented_manifests_list_item = {document_type : augmented_manifests_document_type_format option;The type of augmented manifest. PlainTextDocument or SemiStructuredDocument. If you don't specify, the default is PlainTextDocument.
PLAIN_TEXT_DOCUMENT A document type that represents any unicode text that is encoded in UTF-8.SEMI_STRUCTURED_DOCUMENT A document type with positional and structural context, like a PDF. For training with Amazon Comprehend, only PDFs are supported. For inference, Amazon Comprehend support PDFs, DOCX and TXT.source_documents_s3_uri : s3_uri option;The S3 prefix to the source files (PDFs) that are referred to in the augmented manifest file.
*)annotation_data_s3_uri : s3_uri option;The S3 prefix to the annotation files that are referred in the augmented manifest file.
*)attribute_names : attribute_names_list;The JSON attribute that contains the annotations for your training documents. The number of attribute names that you specify depends on whether your augmented manifest file is the output of a single labeling job or a chained labeling job.
If your file is the output of a single labeling job, specify the LabelAttributeName key that was used when the job was created in Ground Truth.
If your file is the output of a chained labeling job, specify the LabelAttributeName key for one or more jobs in the chain. Each LabelAttributeName key provides the annotations from an individual job.
*)split : split option;The purpose of the data you've provided in the augmented manifest. You can either train or test this data. If you don't specify, the default is train.
TRAIN - all of the documents in the manifest will be used for training. If no test documents are provided, Amazon Comprehend will automatically reserve a portion of the training documents for testing.
TEST - all of the documents in the manifest will be used for testing.
*)s3_uri : s3_uri;The Amazon S3 location of the augmented manifest file.
*)}An augmented manifest file that provides training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
type nonrec entity_recognizer_augmented_manifests_list =
augmented_manifests_list_item listtype nonrec entity_recognizer_input_data_config = {augmented_manifests : entity_recognizer_augmented_manifests_list option;A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
This parameter is required if you set DataFormat to AUGMENTED_MANIFEST.
entity_list : entity_recognizer_entity_list option;The S3 location of the CSV file that has the entity list for your custom entity recognizer.
*)annotations : entity_recognizer_annotations option;The S3 location of the CSV file that annotates your training documents.
*)documents : entity_recognizer_documents option;The S3 location of the folder that contains the training documents for your custom entity recognizer.
This parameter is required if you set DataFormat to COMPREHEND_CSV.
entity_types : entity_types_list;The entity types in the labeled training data that Amazon Comprehend uses to train the custom entity recognizer. Any entity types that you don't specify are ignored.
A maximum of 25 entity types can be used at one time to train an entity recognizer. Entity types must not contain the following invalid characters: \n (line break), \\n (escaped line break), \r (carriage return), \\r (escaped carriage return), \t (tab), \\t (escaped tab), space, and , (comma).
*)data_format : entity_recognizer_data_format option;The format of your training data:
COMPREHEND_CSV: A CSV file that supplements your training documents. The CSV file contains information about the custom entities that your trained model will detect. The required format of the file depends on whether you are providing annotations or an entity list.
If you use this value, you must provide your CSV file by using either the Annotations or EntityList parameters. You must provide your training documents by using the Documents parameter.
AUGMENTED_MANIFEST: A labeled dataset that is produced by Amazon SageMaker Ground Truth. This file is in JSON lines format. Each line is a complete JSON object that contains a training document and its labels. Each label annotates a named entity in the training document.
If you use this value, you must provide the AugmentedManifests parameter in your request.
If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.
}Specifies the format and location of the input data.
type nonrec entity_recognizer_evaluation_metrics = {f1_score : double option;A measure of how accurate the recognizer results are for the test data. It is derived from the Precision and Recall values. The F1Score is the harmonic average of the two scores. For plain text entity recognizer models, the range is 0 to 100, where 100 is the best score. For PDF/Word entity recognizer models, the range is 0 to 1, where 1 is the best score.
recall : double option;A measure of how complete the recognizer results are for the test data. High recall means that the recognizer returned most of the relevant results.
*)precision : double option;A measure of the usefulness of the recognizer results in the test data. High precision means that the recognizer returned substantially more relevant results than irrelevant ones.
*)}Detailed information about the accuracy of an entity recognizer.
type nonrec entity_types_evaluation_metrics = {f1_score : double option;A measure of how accurate the recognizer results are for a specific entity type in the test data. It is derived from the Precision and Recall values. The F1Score is the harmonic average of the two scores. The highest score is 1, and the worst score is 0.
recall : double option;A measure of how complete the recognizer results are for a specific entity type in the test data. High recall means that the recognizer returned most of the relevant results.
*)precision : double option;A measure of the usefulness of the recognizer results for a specific entity type in the test data. High precision means that the recognizer returned substantially more relevant results than irrelevant ones.
*)}Detailed information about the accuracy of an entity recognizer for a specific entity type.
type nonrec entity_recognizer_metadata_entity_types_list_item = {number_of_train_mentions : integer option;Indicates the number of times the given entity type was seen in the training data.
*)evaluation_metrics : entity_types_evaluation_metrics option;Detailed information about the accuracy of the entity recognizer for a specific item on the list of entity types.
*)type_ : any_length_string option;Type of entity from the list of entity types in the metadata of an entity recognizer.
*)}Individual item from the list of entity types in the metadata of an entity recognizer.
type nonrec entity_recognizer_metadata_entity_types_list =
entity_recognizer_metadata_entity_types_list_item listtype nonrec entity_recognizer_metadata = {entity_types : entity_recognizer_metadata_entity_types_list option;Entity types from the metadata of an entity recognizer.
*)evaluation_metrics : entity_recognizer_evaluation_metrics option;Detailed information about the accuracy of an entity recognizer.
*)number_of_test_documents : integer option;The number of documents in the input data that were used to test the entity recognizer. Typically this is 10 to 20 percent of the input documents.
*)number_of_trained_documents : integer option;The number of documents in the input data that were used to train the entity recognizer. Typically this is 80 to 90 percent of the input documents.
*)}Detailed information about an entity recognizer.
type nonrec entity_recognizer_output_data_config = {flywheel_stats_s3_prefix : s3_uri option;The Amazon S3 prefix for the data lake location of the flywheel statistics.
*)}Output data configuration.
type nonrec entity_recognizer_properties = {output_data_config : entity_recognizer_output_data_config option;Output data configuration.
*)flywheel_arn : comprehend_flywheel_arn option;The Amazon Resource Number (ARN) of the flywheel
*)source_model_arn : entity_recognizer_arn option;The Amazon Resource Name (ARN) of the source model. This model was imported from a different Amazon Web Services account to create the entity recognizer model in your Amazon Web Services account.
*)version_name : version_name option;The version name you assigned to the entity recognizer.
*)model_kms_key_id : kms_key_id option;ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"vpc_config : vpc_config option;Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your custom entity recognizer. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)recognizer_metadata : entity_recognizer_metadata option;Provides information about an entity recognizer.
*)input_data_config : entity_recognizer_input_data_config option;The input data properties of an entity recognizer.
*)training_end_time : timestamp option;The time that training of the entity recognizer was completed.
*)training_start_time : timestamp option;The time that training of the entity recognizer started.
*)end_time : timestamp option;The time that the recognizer creation completed.
*)submit_time : timestamp option;The time that the recognizer was submitted for processing.
*)message : any_length_string option;A description of the status of the recognizer.
*)status : model_status option;Provides the status of the entity recognizer.
*)language_code : language_code option;The language of the input documents. All documents must be in the same language. Only English ("en") is currently supported.
*)entity_recognizer_arn : entity_recognizer_arn option;The Amazon Resource Name (ARN) that identifies the entity recognizer.
*)}Describes information about an entity recognizer.
type nonrec entity_recognizer_properties_list =
entity_recognizer_properties listtype nonrec list_entity_recognizers_response = {next_token : string_ option;Identifies the next page of results to return.
*)entity_recognizer_properties_list : entity_recognizer_properties_list option;The list of properties of an entity recognizer.
*)}type nonrec entity_recognizer_filter = {submit_time_after : timestamp option;Filters the list of entities based on the time that the list was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in ascending order, oldest to newest.
*)submit_time_before : timestamp option;Filters the list of entities based on the time that the list was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in descending order, newest to oldest.
*)recognizer_name : comprehend_arn_name option;The name that you assigned the entity recognizer.
*)status : model_status option;The status of an entity recognizer.
*)}Provides information for filtering a list of entity recognizers. You can only specify one filtering parameter in a request. For more information, see the ListEntityRecognizers operation./>
type nonrec list_entity_recognizers_request = {max_results : max_results_integer option;The maximum number of results to return on each page. The default is 100.
*)next_token : string_ option;Identifies the next page of results to return.
*)filter : entity_recognizer_filter option;Filters the list of entities returned. You can filter on Status, SubmitTimeBefore, or SubmitTimeAfter. You can only set one filter at a time.
}type nonrec entity_recognizer_summary = {latest_version_status : model_status option;Provides the status of the latest entity recognizer version.
*)latest_version_name : version_name option;The version name you assigned to the latest entity recognizer version.
*)latest_version_created_at : timestamp option;The time that the latest entity recognizer version was submitted for processing.
*)number_of_versions : integer option;The number of versions you created.
*)recognizer_name : comprehend_arn_name option;The name that you assigned the entity recognizer.
*)}Describes the information about an entity recognizer and its versions.
type nonrec entity_recognizer_summaries_list = entity_recognizer_summary listtype nonrec list_entity_recognizer_summaries_response = {next_token : string_ option;Identifies the next page of results to return.
*)entity_recognizer_summaries_list : entity_recognizer_summaries_list option;The list entity recognizer summaries.
*)}type nonrec list_entity_recognizer_summaries_request = {max_results : max_results_integer option;The maximum number of results to return on each page. The default is 100.
*)next_token : string_ option;Identifies the next page of results to return.
*)}type nonrec entities_detection_job_properties = {flywheel_arn : comprehend_flywheel_arn option;The Amazon Resource Name (ARN) of the flywheel associated with this job.
*)vpc_config : vpc_config option;Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your entity detection job. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)language_code : language_code option;The language code of the input documents.
*)output_data_config : output_data_config option;The output data configuration that you supplied when you created the entities detection job.
*)input_data_config : input_data_config option;The input data configuration that you supplied when you created the entities detection job.
*)entity_recognizer_arn : entity_recognizer_arn option;The Amazon Resource Name (ARN) that identifies the entity recognizer.
*)end_time : timestamp option;The time that the entities detection job completed
*)submit_time : timestamp option;The time that the entities detection job was submitted for processing.
*)message : any_length_string option;A description of the status of a job.
*)job_status : job_status option;The current status of the entities detection job. If the status is FAILED, the Message field shows the reason for the failure.
job_name : job_name option;The name that you assigned the entities detection job.
*)job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the entities detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::entities-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:entities-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier assigned to the entities detection job.
*)}Provides information about an entities detection job.
type nonrec entities_detection_job_properties_list =
entities_detection_job_properties listtype nonrec list_entities_detection_jobs_response = {next_token : string_ option;Identifies the next page of results to return.
*)entities_detection_job_properties_list : entities_detection_job_properties_list
option;A list containing the properties of each job that is returned.
*)}type nonrec entities_detection_job_filter = {submit_time_after : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
*)submit_time_before : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
*)job_status : job_status option;Filters the list of jobs based on job status. Returns only jobs with the specified status.
*)job_name : job_name option;Filters on the name of the job.
*)}Provides information for filtering a list of dominant language detection jobs. For more information, see the operation.
type nonrec list_entities_detection_jobs_request = {max_results : max_results_integer option;The maximum number of results to return in each page. The default is 100.
*)next_token : string_ option;Identifies the next page of results to return.
*)filter : entities_detection_job_filter option;Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
*)}type nonrec endpoint_properties = {flywheel_arn : comprehend_flywheel_arn option;The Amazon Resource Number (ARN) of the flywheel
*)desired_data_access_role_arn : iam_role_arn option;Data access role ARN to use in case the new model is encrypted with a customer KMS key.
*)data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to trained custom models encrypted with a customer managed key (ModelKmsKeyId).
*)last_modified_time : timestamp option;The date and time that the endpoint was last modified.
*)creation_time : timestamp option;The creation date and time of the endpoint.
*)current_inference_units : inference_units_integer option;The number of inference units currently used by the model using this endpoint.
*)desired_inference_units : inference_units_integer option;The desired number of inference units to be used by the model using this endpoint. Each inference unit represents of a throughput of 100 characters per second.
*)desired_model_arn : comprehend_model_arn option;ARN of the new model to use for updating an existing endpoint. This ARN is going to be different from the model ARN when the update is in progress
*)model_arn : comprehend_model_arn option;The Amazon Resource Number (ARN) of the model to which the endpoint is attached.
*)message : any_length_string option;Specifies a reason for failure in cases of Failed status.
status : endpoint_status option;Specifies the status of the endpoint. Because the endpoint updates and creation are asynchronous, so customers will need to wait for the endpoint to be Ready status before making inference requests.
endpoint_arn : comprehend_endpoint_arn option;The Amazon Resource Number (ARN) of the endpoint.
*)}Specifies information about the specified endpoint. For information about endpoints, see Managing endpoints.
type nonrec endpoint_properties_list = endpoint_properties listtype nonrec list_endpoints_response = {next_token : string_ option;Identifies the next page of results to return.
*)endpoint_properties_list : endpoint_properties_list option;Displays a list of endpoint properties being retrieved by the service in response to the request.
*)}type nonrec endpoint_filter = {creation_time_after : timestamp option;Specifies a date after which the returned endpoint or endpoints were created.
*)creation_time_before : timestamp option;Specifies a date before which the returned endpoint or endpoints were created.
*)status : endpoint_status option;Specifies the status of the endpoint being returned. Possible values are: Creating, Ready, Updating, Deleting, Failed.
*)model_arn : comprehend_model_arn option;The Amazon Resource Number (ARN) of the model to which the endpoint is attached.
*)}The filter used to determine which endpoints are returned. You can filter jobs on their name, model, status, or the date and time that they were created. You can only set one filter at a time.
type nonrec list_endpoints_request = {max_results : max_results_integer option;The maximum number of results to return in each page. The default is 100.
*)next_token : string_ option;Identifies the next page of results to return.
*)filter : endpoint_filter option;Filters the endpoints that are returned. You can filter endpoints on their name, model, status, or the date and time that they were created. You can only set one filter at a time.
*)}type nonrec dominant_language_detection_job_properties = {vpc_config : vpc_config option;Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your dominant language detection job. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)output_data_config : output_data_config option;The output data configuration that you supplied when you created the dominant language detection job.
*)input_data_config : input_data_config option;The input data configuration that you supplied when you created the dominant language detection job.
*)end_time : timestamp option;The time that the dominant language detection job completed.
*)submit_time : timestamp option;The time that the dominant language detection job was submitted for processing.
*)message : any_length_string option;A description for the status of a job.
*)job_status : job_status option;The current status of the dominant language detection job. If the status is FAILED, the Message field shows the reason for the failure.
job_name : job_name option;The name that you assigned to the dominant language detection job.
*)job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the dominant language detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::dominant-language-detection-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:dominant-language-detection-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier assigned to the dominant language detection job.
*)}Provides information about a dominant language detection job.
type nonrec dominant_language_detection_job_properties_list =
dominant_language_detection_job_properties listtype nonrec list_dominant_language_detection_jobs_response = {next_token : string_ option;Identifies the next page of results to return.
*)dominant_language_detection_job_properties_list : dominant_language_detection_job_properties_list
option;A list containing the properties of each job that is returned.
*)}type nonrec dominant_language_detection_job_filter = {submit_time_after : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
*)submit_time_before : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
*)job_status : job_status option;Filters the list of jobs based on job status. Returns only jobs with the specified status.
*)job_name : job_name option;Filters on the name of the job.
*)}Provides information for filtering a list of dominant language detection jobs. For more information, see the operation.
type nonrec list_dominant_language_detection_jobs_request = {max_results : max_results_integer option;The maximum number of results to return in each page. The default is 100.
*)next_token : string_ option;Identifies the next page of results to return.
*)filter : dominant_language_detection_job_filter option;Filters that jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
*)}type nonrec document_classifier_augmented_manifests_list =
augmented_manifests_list_item listtype nonrec document_classifier_documents = {test_s3_uri : s3_uri option;The S3 URI location of the test documents included in the TestS3Uri CSV file. This field is not required if you do not specify a test CSV file.
*)s3_uri : s3_uri;The S3 URI location of the training documents specified in the S3Uri CSV file.
*)}The location of the training documents. This parameter is required in a request to create a semi-structured document classification model.
type nonrec document_classifier_input_data_config = {document_reader_config : document_reader_config option;documents : document_classifier_documents option;The S3 location of the training documents. This parameter is required in a request to create a native document model.
*)document_type : document_classifier_document_type_format option;The type of input documents for training the model. Provide plain-text documents to create a plain-text model, and provide semi-structured documents to create a native document model.
*)augmented_manifests : document_classifier_augmented_manifests_list option;A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
This parameter is required if you set DataFormat to AUGMENTED_MANIFEST.
label_delimiter : label_delimiter option;Indicates the delimiter used to separate each label for training a multi-label classifier. The default delimiter between labels is a pipe (|). You can use a different character as a delimiter (if it's an allowed character) by specifying it under Delimiter for labels. If the training documents use a delimiter other than the default or the delimiter you specify, the labels on that line will be combined to make a single unique label, such as LABELLABELLABEL.
*)test_s3_uri : s3_uri option;This specifies the Amazon S3 location that contains the test annotations for the document classifier. The URI must be in the same Amazon Web Services Region as the API endpoint that you are calling.
*)s3_uri : s3_uri option;The Amazon S3 URI for the input data. The S3 bucket must be in the same Region as the API endpoint that you are calling. The URI can point to a single input file or it can provide the prefix for a collection of input files.
For example, if you use the URI S3://bucketName/prefix, if the prefix is a single file, Amazon Comprehend uses that file as input. If more than one file begins with the prefix, Amazon Comprehend uses all of them as input.
This parameter is required if you set DataFormat to COMPREHEND_CSV.
data_format : document_classifier_data_format option;The format of your training data:
COMPREHEND_CSV: A two-column CSV file, where labels are provided in the first column, and documents are provided in the second. If you use this value, you must provide the S3Uri parameter in your request.AUGMENTED_MANIFEST: A labeled dataset that is produced by Amazon SageMaker Ground Truth. This file is in JSON lines format. Each line is a complete JSON object that contains a training document and its associated labels.
If you use this value, you must provide the AugmentedManifests parameter in your request.
If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default.
}The input properties for training a document classifier.
For more information on how the input file is formatted, see Preparing training data in the Comprehend Developer Guide.
type nonrec document_classifier_output_data_config = {flywheel_stats_s3_prefix : s3_uri option;The Amazon S3 prefix for the data lake location of the flywheel statistics.
*)kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the output results from an analysis job. The KmsKeyId can be one of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab""alias/ExampleAlias""arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias"s3_uri : s3_uri option;When you use the OutputDataConfig object while creating a custom classifier, you specify the Amazon S3 location where you want to write the confusion matrix and other output files. The URI must be in the same Region as the API endpoint that you are calling. The location is used as the prefix for the actual location of this output file.
When the custom classifier job is finished, the service creates the output file in a directory specific to the job. The S3Uri field contains the location of the output file, called output.tar.gz. It is a compressed archive that contains the confusion matrix.
}Provide the location for output data from a custom classifier job. This field is mandatory if you are training a native document model.
type nonrec classifier_evaluation_metrics = {hamming_loss : double option;Indicates the fraction of labels that are incorrectly predicted. Also seen as the fraction of wrong labels compared to the total number of labels. Scores closer to zero are better.
*)micro_f1_score : double option;A measure of how accurate the classifier results are for the test data. It is a combination of the Micro Precision and Micro Recall values. The Micro F1Score is the harmonic mean of the two scores. The highest score is 1, and the worst score is 0.
micro_recall : double option;A measure of how complete the classifier results are for the test data. High recall means that the classifier returned most of the relevant results. Specifically, this indicates how many of the correct categories in the text that the model can predict. It is a percentage of correct categories in the text that can found. Instead of averaging the recall scores of all labels (as with Recall), micro Recall is based on the overall score of all recall scores added together.
*)micro_precision : double option;A measure of the usefulness of the recognizer results in the test data. High precision means that the recognizer returned substantially more relevant results than irrelevant ones. Unlike the Precision metric which comes from averaging the precision of all available labels, this is based on the overall score of all precision scores added together.
*)f1_score : double option;A measure of how accurate the classifier results are for the test data. It is derived from the Precision and Recall values. The F1Score is the harmonic average of the two scores. The highest score is 1, and the worst score is 0.
recall : double option;A measure of how complete the classifier results are for the test data. High recall means that the classifier returned most of the relevant results.
*)precision : double option;A measure of the usefulness of the classifier results in the test data. High precision means that the classifier returned substantially more relevant results than irrelevant ones.
*)accuracy : double option;The fraction of the labels that were correct recognized. It is computed by dividing the number of labels in the test documents that were correctly recognized by the total number of labels in the test documents.
*)}Describes the result metrics for the test data associated with an documentation classifier.
type nonrec classifier_metadata = {evaluation_metrics : classifier_evaluation_metrics option;Describes the result metrics for the test data associated with an documentation classifier.
*)number_of_test_documents : integer option;The number of documents in the input data that were used to test the classifier. Typically this is 10 to 20 percent of the input documents, up to 10,000 documents.
*)number_of_trained_documents : integer option;The number of documents in the input data that were used to train the classifier. Typically this is 80 to 90 percent of the input documents.
*)number_of_labels : integer option;The number of labels in the input data.
*)}Provides information about a document classifier.
type nonrec document_classifier_properties = {flywheel_arn : comprehend_flywheel_arn option;The Amazon Resource Number (ARN) of the flywheel
*)source_model_arn : document_classifier_arn option;The Amazon Resource Name (ARN) of the source model. This model was imported from a different Amazon Web Services account to create the document classifier model in your Amazon Web Services account.
*)version_name : version_name option;The version name that you assigned to the document classifier.
*)model_kms_key_id : kms_key_id option;ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"mode : document_classifier_mode option;Indicates the mode in which the specific classifier was trained. This also indicates the format of input documents and the format of the confusion matrix. Each classifier can only be trained in one mode and this cannot be changed once the classifier is trained.
*)vpc_config : vpc_config option;Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your custom classifier. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)classifier_metadata : classifier_metadata option;Information about the document classifier, including the number of documents used for training the classifier, the number of documents used for test the classifier, and an accuracy rating.
*)output_data_config : document_classifier_output_data_config option;Provides output results configuration parameters for custom classifier jobs.
*)input_data_config : document_classifier_input_data_config option;The input data configuration that you supplied when you created the document classifier for training.
*)training_end_time : timestamp option;The time that training of the document classifier was completed. Indicates the time when the training completes on documentation classifiers. You are billed for the time interval between this time and the value of TrainingStartTime.
*)training_start_time : timestamp option;Indicates the time when the training starts on documentation classifiers. You are billed for the time interval between this time and the value of TrainingEndTime.
*)end_time : timestamp option;The time that training the document classifier completed.
*)submit_time : timestamp option;The time that the document classifier was submitted for training.
*)message : any_length_string option;Additional information about the status of the classifier.
*)status : model_status option;The status of the document classifier. If the status is TRAINED the classifier is ready to use. If the status is TRAINED_WITH_WARNINGS the classifier training succeeded, but you should review the warnings returned in the CreateDocumentClassifier response.
If the status is FAILED you can see additional information about why the classifier wasn't trained in the Message field.
language_code : language_code option;The language code for the language of the documents that the classifier was trained on.
*)document_classifier_arn : document_classifier_arn option;The Amazon Resource Name (ARN) that identifies the document classifier.
*)}Provides information about a document classifier.
type nonrec document_classifier_properties_list =
document_classifier_properties listtype nonrec list_document_classifiers_response = {next_token : string_ option;Identifies the next page of results to return.
*)document_classifier_properties_list : document_classifier_properties_list
option;A list containing the properties of each job returned.
*)}type nonrec document_classifier_filter = {submit_time_after : timestamp option;Filters the list of classifiers based on the time that the classifier was submitted for processing. Returns only classifiers submitted after the specified time. Classifiers are returned in descending order, newest to oldest.
*)submit_time_before : timestamp option;Filters the list of classifiers based on the time that the classifier was submitted for processing. Returns only classifiers submitted before the specified time. Classifiers are returned in ascending order, oldest to newest.
*)document_classifier_name : comprehend_arn_name option;The name that you assigned to the document classifier
*)status : model_status option;Filters the list of classifiers based on status.
*)}Provides information for filtering a list of document classifiers. You can only specify one filtering parameter in a request. For more information, see the ListDocumentClassifiers operation.
type nonrec list_document_classifiers_request = {max_results : max_results_integer option;The maximum number of results to return in each page. The default is 100.
*)next_token : string_ option;Identifies the next page of results to return.
*)filter : document_classifier_filter option;Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
*)}type nonrec document_classifier_summary = {latest_version_status : model_status option;Provides the status of the latest document classifier version.
*)latest_version_name : version_name option;The version name you assigned to the latest document classifier version.
*)latest_version_created_at : timestamp option;The time that the latest document classifier version was submitted for processing.
*)number_of_versions : integer option;The number of versions you created.
*)document_classifier_name : comprehend_arn_name option;The name that you assigned the document classifier.
*)}Describes information about a document classifier and its versions.
type nonrec document_classifier_summaries_list =
document_classifier_summary listtype nonrec list_document_classifier_summaries_response = {next_token : string_ option;Identifies the next page of results to return.
*)document_classifier_summaries_list : document_classifier_summaries_list option;The list of summaries of document classifiers.
*)}type nonrec list_document_classifier_summaries_request = {max_results : max_results_integer option;The maximum number of results to return on each page. The default is 100.
*)next_token : string_ option;Identifies the next page of results to return.
*)}type nonrec document_classification_job_properties = {flywheel_arn : comprehend_flywheel_arn option;The Amazon Resource Number (ARN) of the flywheel
*)vpc_config : vpc_config option;Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your document classification job. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)output_data_config : output_data_config option;The output data configuration that you supplied when you created the document classification job.
*)input_data_config : input_data_config option;The input data configuration that you supplied when you created the document classification job.
*)document_classifier_arn : document_classifier_arn option;The Amazon Resource Name (ARN) that identifies the document classifier.
*)end_time : timestamp option;The time that the document classification job completed.
*)submit_time : timestamp option;The time that the document classification job was submitted for processing.
*)message : any_length_string option;A description of the status of the job.
*)job_status : job_status option;The current status of the document classification job. If the status is FAILED, the Message field shows the reason for the failure.
job_name : job_name option;The name that you assigned to the document classification job.
*)job_arn : comprehend_arn option;The Amazon Resource Name (ARN) of the document classification job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn::comprehend:::document-classification-job/The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:document-classification-job/1234abcd12ab34cd56ef1234567890ab
job_id : job_id option;The identifier assigned to the document classification job.
*)}Provides information about a document classification job.
type nonrec document_classification_job_properties_list =
document_classification_job_properties listtype nonrec list_document_classification_jobs_response = {next_token : string_ option;Identifies the next page of results to return.
*)document_classification_job_properties_list : document_classification_job_properties_list
option;A list containing the properties of each job returned.
*)}type nonrec document_classification_job_filter = {submit_time_after : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
*)submit_time_before : timestamp option;Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
*)job_status : job_status option;Filters the list based on job status. Returns only jobs with the specified status.
*)job_name : job_name option;Filters on the name of the job.
*)}Provides information for filtering a list of document classification jobs. For more information, see the operation. You can provide only one filter parameter in each request.
type nonrec list_document_classification_jobs_request = {max_results : max_results_integer option;The maximum number of results to return in each page. The default is 100.
*)next_token : string_ option;Identifies the next page of results to return.
*)filter : document_classification_job_filter option;Filters the jobs that are returned. You can filter jobs on their names, status, or the date and time that they were submitted. You can only set one filter at a time.
*)}type nonrec dataset_properties = {end_time : timestamp option;Time when the data from the dataset becomes available in the data lake.
*)creation_time : timestamp option;Creation time of the dataset.
*)number_of_documents : number_of_documents option;The number of documents in the dataset.
*)message : any_length_string option;A description of the status of the dataset.
*)status : dataset_status option;The dataset status. While the system creates the dataset, the status is CREATING. When the dataset is ready to use, the status changes to COMPLETED.
description : description option;Description of the dataset.
*)dataset_s3_uri : s3_uri option;The S3 URI where the dataset is stored.
*)dataset_type : dataset_type option;The dataset type (training data or test data).
*)dataset_name : comprehend_arn_name option;The name of the dataset.
*)dataset_arn : comprehend_dataset_arn option;The ARN of the dataset.
*)}Properties associated with the dataset.
type nonrec dataset_properties_list = dataset_properties listtype nonrec list_datasets_response = {next_token : string_ option;Identifies the next page of results to return.
*)dataset_properties_list : dataset_properties_list option;The dataset properties list.
*)}type nonrec dataset_filter = {creation_time_before : timestamp option;Filter the datasets to include datasets created before the specified time.
*)creation_time_after : timestamp option;Filter the datasets to include datasets created after the specified time.
*)dataset_type : dataset_type option;Filter the datasets based on the dataset type.
*)status : dataset_status option;Filter the datasets based on the dataset status.
*)}Filter the datasets based on creation time or dataset status.
type nonrec list_datasets_request = {max_results : max_results_integer option;Maximum number of results to return in a response. The default is 100.
*)next_token : string_ option;Identifies the next page of results to return.
*)filter : dataset_filter option;Filters the datasets to be returned in the response.
*)flywheel_arn : comprehend_flywheel_arn option;The Amazon Resource Number (ARN) of the flywheel.
*)}type nonrec import_model_response = {model_arn : comprehend_model_arn option;The Amazon Resource Name (ARN) of the custom model being imported.
*)}type nonrec import_model_request = {data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend permission to use Amazon Key Management Service (KMS) to encrypt or decrypt the custom model.
*)model_kms_key_id : kms_key_id option;ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"version_name : version_name option;The version name given to the custom model that is created by this import. Version names can have a maximum of 256 characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The version name must be unique among all models with the same classifier name in the account/Region.
*)model_name : comprehend_arn_name option;The name to assign to the custom model that is created in Amazon Comprehend by this import.
*)source_model_arn : comprehend_model_arn;The Amazon Resource Name (ARN) of the custom model to import.
*)}type nonrec document_metadata = {extracted_characters : list_of_extracted_characters option;List of pages in the document, with the number of characters extracted from each page.
*)pages : integer option;Number of pages in the document.
*)}Information about the document, discovered during text extraction.
type nonrec detect_toxic_content_response = {result_list : list_of_toxic_labels option;Results of the content moderation analysis. Each entry in the results list contains a list of toxic content types identified in the text, along with a confidence score for each content type. The results list also includes a toxicity score for each entry in the results list.
*)}type nonrec detect_toxic_content_request = {language_code : language_code;The language of the input text. Currently, English is the only supported language.
*)text_segments : list_of_text_segments;A list of up to 10 text strings. Each string has a maximum size of 1 KB, and the maximum size of the list is 10 KB.
*)}type nonrec detect_targeted_sentiment_response = {entities : list_of_targeted_sentiment_entities option;Targeted sentiment analysis for each of the entities identified in the input text.
*)}type nonrec detect_targeted_sentiment_request = {language_code : language_code;The language of the input documents. Currently, English is the only supported language.
*)text : customer_input_string;A UTF-8 text string. The maximum string length is 5 KB.
*)}type nonrec detect_syntax_response = {syntax_tokens : list_of_syntax_tokens option;A collection of syntax tokens describing the text. For each token, the response provides the text, the token type, where the text begins and ends, and the level of confidence that Amazon Comprehend has that the token is correct. For a list of token types, see Syntax in the Comprehend Developer Guide.
*)}type nonrec detect_syntax_request = {language_code : syntax_language_code;The language code of the input documents. You can specify any of the following languages supported by Amazon Comprehend: German ("de"), English ("en"), Spanish ("es"), French ("fr"), Italian ("it"), or Portuguese ("pt").
*)text : customer_input_string;A UTF-8 string. The maximum string size is 5 KB.
*)}type nonrec detect_sentiment_response = {sentiment_score : sentiment_score option;An object that lists the sentiments, and their corresponding confidence levels.
*)sentiment : sentiment_type option;The inferred sentiment that Amazon Comprehend has the highest level of confidence in.
*)}type nonrec detect_sentiment_request = {language_code : language_code;The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
*)text : customer_input_string;A UTF-8 text string. The maximum string size is 5 KB.
*)}type nonrec detect_pii_entities_response = {entities : list_of_pii_entities option;A collection of PII entities identified in the input text. For each entity, the response provides the entity type, where the entity text begins and ends, and the level of confidence that Amazon Comprehend has in the detection.
*)}type nonrec detect_pii_entities_request = {language_code : language_code;The language of the input text. Enter the language code for English (en) or Spanish (es).
*)text : string_;A UTF-8 text string. The maximum string size is 100 KB.
*)}type nonrec detect_key_phrases_response = {key_phrases : list_of_key_phrases option;A collection of key phrases that Amazon Comprehend identified in the input text. For each key phrase, the response provides the text of the key phrase, where the key phrase begins and ends, and the level of confidence that Amazon Comprehend has in the accuracy of the detection.
*)}type nonrec detect_key_phrases_request = {language_code : language_code;The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
*)text : customer_input_string;A UTF-8 text string. The string must contain less than 100 KB of UTF-8 encoded characters.
*)}type nonrec detect_entities_response = {errors : list_of_errors option;Page-level errors that the system detected while processing the input document. The field is empty if the system encountered no errors.
*)blocks : list_of_blocks option;Information about each block of text in the input document. Blocks are nested. A page block contains a block for each line of text, which contains a block for each word.
The Block content for a Word input document does not include a Geometry field.
The Block field is not present in the response for plain-text inputs.
document_type : list_of_document_type option;The document type for each page in the input document. This field is present in the response only if your request used the Byte parameter.
document_metadata : document_metadata option;Information about the document, discovered during text extraction. This field is present in the response only if your request used the Byte parameter.
entities : list_of_entities option;A collection of entities identified in the input text. For each entity, the response provides the entity text, entity type, where the entity text begins and ends, and the level of confidence that Amazon Comprehend has in the detection.
If your request uses a custom entity recognition model, Amazon Comprehend detects the entities that the model is trained to recognize. Otherwise, it detects the default entity types. For a list of default entity types, see Entities in the Comprehend Developer Guide.
*)}type nonrec detect_entities_request = {document_reader_config : document_reader_config option;Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.
*)bytes : semi_structured_document_blob option;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 Text field.
Use the Bytes parameter to input a text, PDF, Word or image file. Using a plain-text file in the Bytes parameter is equivelent to using the Text parameter (the Entities field in the response is identical).
You can also use the Bytes parameter to input an Amazon Textract DetectDocumentText or AnalyzeDocument output file.
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.
The maximum length of this field depends on the input document type. For details, see Inputs for real-time custom analysis in the Comprehend Developer Guide.
If you use the Bytes parameter, do not use the Text parameter.
endpoint_arn : entity_recognizer_endpoint_arn option;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.
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.
For information about endpoints, see Managing endpoints.
*)language_code : language_code option;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.
All input documents must be in the same language.
*)text : customer_input_string option;A UTF-8 text string. The maximum string size is 100 KB. If you enter text using this parameter, do not use the Bytes parameter.
}type nonrec detect_dominant_language_response = {languages : list_of_dominant_languages option;Array of languages that Amazon Comprehend detected in the input text. The array is sorted in descending order of the score (the dominant language is always the first element in the array).
For each language, the response returns the RFC 5646 language code and the level of confidence that Amazon Comprehend has in the accuracy of its inference. For more information about RFC 5646, see Tags for Identifying Languages on the IETF Tools web site.
*)}type nonrec detect_dominant_language_request = {text : customer_input_string;A UTF-8 text string. The string must contain at least 20 characters. The maximum string size is 100 KB.
*)}type nonrec describe_topics_detection_job_response = {topics_detection_job_properties : topics_detection_job_properties option;The list of properties for the requested job.
*)}type nonrec describe_topics_detection_job_request = {job_id : job_id;The identifier assigned by the user to the detection job.
*)}type nonrec describe_targeted_sentiment_detection_job_response = {targeted_sentiment_detection_job_properties : targeted_sentiment_detection_job_properties
option;An object that contains the properties associated with a targeted sentiment detection job.
*)}type nonrec describe_targeted_sentiment_detection_job_request = {job_id : job_id;The identifier that Amazon Comprehend generated for the job. The StartTargetedSentimentDetectionJob operation returns this identifier in its response.
}type nonrec describe_sentiment_detection_job_response = {sentiment_detection_job_properties : sentiment_detection_job_properties option;An object that contains the properties associated with a sentiment detection job.
*)}type nonrec describe_sentiment_detection_job_request = {job_id : job_id;The identifier that Amazon Comprehend generated for the job. The operation returns this identifier in its response.
*)}type nonrec describe_resource_policy_response = {policy_revision_id : policy_revision_id option;The revision ID of the policy. Each time you modify a policy, Amazon Comprehend assigns a new revision ID, and it deletes the prior version of the policy.
*)last_modified_time : timestamp option;The time at which the policy was last modified.
*)creation_time : timestamp option;The time at which the policy was created.
*)resource_policy : policy option;The JSON body of the resource-based policy.
*)}type nonrec describe_resource_policy_request = {resource_arn : comprehend_model_arn;The Amazon Resource Name (ARN) of the custom model version that has the resource policy.
*)}type nonrec describe_pii_entities_detection_job_response = {pii_entities_detection_job_properties : pii_entities_detection_job_properties
option;}type nonrec describe_pii_entities_detection_job_request = {job_id : job_id;The identifier that Amazon Comprehend generated for the job. The operation returns this identifier in its response.
*)}type nonrec describe_key_phrases_detection_job_response = {key_phrases_detection_job_properties : key_phrases_detection_job_properties
option;An object that contains the properties associated with a key phrases detection job.
*)}type nonrec describe_key_phrases_detection_job_request = {job_id : job_id;The identifier that Amazon Comprehend generated for the job. The StartKeyPhrasesDetectionJob operation returns this identifier in its response.
}type nonrec describe_flywheel_response = {flywheel_properties : flywheel_properties option;The flywheel properties.
*)}type nonrec describe_flywheel_request = {flywheel_arn : comprehend_flywheel_arn;The Amazon Resource Number (ARN) of the flywheel.
*)}type nonrec describe_flywheel_iteration_response = {flywheel_iteration_properties : flywheel_iteration_properties option;The configuration properties of a flywheel iteration.
*)}type nonrec describe_flywheel_iteration_request = {flywheel_iteration_id : flywheel_iteration_id;flywheel_arn : comprehend_flywheel_arn;}type nonrec describe_events_detection_job_response = {events_detection_job_properties : events_detection_job_properties option;An object that contains the properties associated with an event detection job.
*)}type nonrec describe_events_detection_job_request = {job_id : job_id;The identifier of the events detection job.
*)}type nonrec describe_entity_recognizer_response = {entity_recognizer_properties : entity_recognizer_properties option;Describes information associated with an entity recognizer.
*)}type nonrec describe_entity_recognizer_request = {entity_recognizer_arn : entity_recognizer_arn;The Amazon Resource Name (ARN) that identifies the entity recognizer.
*)}type nonrec describe_entities_detection_job_response = {entities_detection_job_properties : entities_detection_job_properties option;An object that contains the properties associated with an entities detection job.
*)}type nonrec describe_entities_detection_job_request = {job_id : job_id;The identifier that Amazon Comprehend generated for the job. The StartEntitiesDetectionJob operation returns this identifier in its response.
}type nonrec describe_endpoint_response = {endpoint_properties : endpoint_properties option;Describes information associated with the specific endpoint.
*)}type nonrec describe_endpoint_request = {endpoint_arn : comprehend_endpoint_arn;The Amazon Resource Number (ARN) of the endpoint being described.
*)}type nonrec describe_dominant_language_detection_job_response = {dominant_language_detection_job_properties : dominant_language_detection_job_properties
option;An object that contains the properties associated with a dominant language detection job.
*)}type nonrec describe_dominant_language_detection_job_request = {job_id : job_id;The identifier that Amazon Comprehend generated for the job. The StartDominantLanguageDetectionJob operation returns this identifier in its response.
}type nonrec describe_document_classifier_response = {document_classifier_properties : document_classifier_properties option;An object that contains the properties associated with a document classifier.
*)}type nonrec describe_document_classifier_request = {document_classifier_arn : document_classifier_arn;The Amazon Resource Name (ARN) that identifies the document classifier. The CreateDocumentClassifier operation returns this identifier in its response.
}type nonrec describe_document_classification_job_response = {document_classification_job_properties : document_classification_job_properties
option;An object that describes the properties associated with the document classification job.
*)}type nonrec describe_document_classification_job_request = {job_id : job_id;The identifier that Amazon Comprehend generated for the job. The StartDocumentClassificationJob operation returns this identifier in its response.
}type nonrec describe_dataset_response = {dataset_properties : dataset_properties option;The dataset properties.
*)}type nonrec describe_dataset_request = {dataset_arn : comprehend_dataset_arn;The ARN of the dataset.
*)}type nonrec delete_resource_policy_request = {policy_revision_id : policy_revision_id option;The revision ID of the policy to delete.
*)resource_arn : comprehend_model_arn;The Amazon Resource Name (ARN) of the custom model version that has the policy to delete.
*)}type nonrec delete_flywheel_request = {flywheel_arn : comprehend_flywheel_arn;The Amazon Resource Number (ARN) of the flywheel to delete.
*)}type nonrec delete_entity_recognizer_request = {entity_recognizer_arn : entity_recognizer_arn;The Amazon Resource Name (ARN) that identifies the entity recognizer.
*)}type nonrec delete_endpoint_request = {endpoint_arn : comprehend_endpoint_arn;The Amazon Resource Number (ARN) of the endpoint being deleted.
*)}type nonrec delete_document_classifier_request = {document_classifier_arn : document_classifier_arn;The Amazon Resource Name (ARN) that identifies the document classifier.
*)}type nonrec dataset_augmented_manifests_list_item = {document_type : augmented_manifests_document_type_format option;The type of augmented manifest. If you don't specify, the default is PlainTextDocument.
PLAIN_TEXT_DOCUMENT A document type that represents any unicode text that is encoded in UTF-8.
source_documents_s3_uri : s3_uri option;The S3 prefix to the source files (PDFs) that are referred to in the augmented manifest file.
*)annotation_data_s3_uri : s3_uri option;The S3 prefix to the annotation files that are referred in the augmented manifest file.
*)s3_uri : s3_uri;The Amazon S3 location of the augmented manifest file.
*)attribute_names : attribute_names_list;The JSON attribute that contains the annotations for your training documents. The number of attribute names that you specify depends on whether your augmented manifest file is the output of a single labeling job or a chained labeling job.
If your file is the output of a single labeling job, specify the LabelAttributeName key that was used when the job was created in Ground Truth.
If your file is the output of a chained labeling job, specify the LabelAttributeName key for one or more jobs in the chain. Each LabelAttributeName key provides the annotations from an individual job.
*)}An augmented manifest file that provides training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
type nonrec dataset_augmented_manifests_list =
dataset_augmented_manifests_list_item listtype nonrec dataset_document_classifier_input_data_config = {label_delimiter : label_delimiter option;Indicates the delimiter used to separate each label for training a multi-label classifier. The default delimiter between labels is a pipe (|). You can use a different character as a delimiter (if it's an allowed character) by specifying it under Delimiter for labels. If the training documents use a delimiter other than the default or the delimiter you specify, the labels on that line will be combined to make a single unique label, such as LABELLABELLABEL.
*)s3_uri : s3_uri;The Amazon S3 URI for the input data. The S3 bucket must be in the same Region as the API endpoint that you are calling. The URI can point to a single input file or it can provide the prefix for a collection of input files.
For example, if you use the URI S3://bucketName/prefix, if the prefix is a single file, Amazon Comprehend uses that file as input. If more than one file begins with the prefix, Amazon Comprehend uses all of them as input.
This parameter is required if you set DataFormat to COMPREHEND_CSV.
}Describes the dataset input data configuration for a document classifier model.
For more information on how the input file is formatted, see Preparing training data in the Comprehend Developer Guide.
type nonrec dataset_entity_recognizer_annotations = {s3_uri : s3_uri;Specifies the Amazon S3 location where the training documents for an entity recognizer are located. The URI must be in the same Region as the API endpoint that you are calling.
*)}Describes the annotations associated with a entity recognizer.
type nonrec dataset_entity_recognizer_documents = {input_format : input_format option;Specifies how the text in an input file should be processed. This is optional, and the default is ONE_DOC_PER_LINE. ONE_DOC_PER_FILE - Each file is considered a separate document. Use this option when you are processing large documents, such as newspaper articles or scientific papers. ONE_DOC_PER_LINE - Each line in a file is considered a separate document. Use this option when you are processing many short documents, such as text messages.
*)s3_uri : s3_uri;Specifies the Amazon S3 location where the documents for the dataset are located.
*)}Describes the documents submitted with a dataset for an entity recognizer model.
type nonrec dataset_entity_recognizer_entity_list = {s3_uri : s3_uri;Specifies the Amazon S3 location where the entity list is located.
*)}Describes the dataset entity list for an entity recognizer model.
For more information on how the input file is formatted, see Preparing training data in the Comprehend Developer Guide.
type nonrec dataset_entity_recognizer_input_data_config = {entity_list : dataset_entity_recognizer_entity_list option;The S3 location of the entity list for your custom entity recognizer.
*)documents : dataset_entity_recognizer_documents;The format and location of the training documents for your custom entity recognizer.
*)annotations : dataset_entity_recognizer_annotations option;The S3 location of the annotation documents for your custom entity recognizer.
*)}Specifies the format and location of the input data. You must provide either the Annotations parameter or the EntityList parameter.
type nonrec dataset_input_data_config = {entity_recognizer_input_data_config : dataset_entity_recognizer_input_data_config
option;The input properties for training an entity recognizer model.
*)document_classifier_input_data_config : dataset_document_classifier_input_data_config
option;The input properties for training a document classifier model.
For more information on how the input file is formatted, see Preparing training data in the Comprehend Developer Guide.
*)data_format : dataset_data_format option;COMPREHEND_CSV: The data format is a two-column CSV file, where the first column contains labels and the second column contains documents.
AUGMENTED_MANIFEST: The data format
augmented_manifests : dataset_augmented_manifests_list option;A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.
*)}Specifies the format and location of the input data for the dataset.
type nonrec customer_input_string_list = customer_input_string listtype nonrec create_flywheel_response = {active_model_arn : comprehend_model_arn option;The Amazon Resource Number (ARN) of the active model version.
*)flywheel_arn : comprehend_flywheel_arn option;The Amazon Resource Number (ARN) of the flywheel.
*)}type nonrec create_flywheel_request = {client_request_token : client_request_token_string option;A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
*)data_security_config : data_security_config option;Data security configurations.
*)data_lake_s3_uri : flywheel_s3_uri;Enter the S3 location for the data lake. You can specify a new S3 bucket or a new folder of an existing S3 bucket. The flywheel creates the data lake at this location.
*)model_type : model_type option;The model type. You need to set ModelType if you are creating a flywheel for a new model.
task_config : task_config option;Configuration about the model associated with the flywheel. You need to set TaskConfig if you are creating a flywheel for a new model.
data_access_role_arn : iam_role_arn;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend the permissions required to access the flywheel data in the data lake.
*)active_model_arn : comprehend_model_arn option;To associate an existing model with the flywheel, specify the Amazon Resource Number (ARN) of the model version. Do not set TaskConfig or ModelType if you specify an ActiveModelArn.
flywheel_name : comprehend_arn_name;Name for the flywheel.
*)}type nonrec create_entity_recognizer_response = {entity_recognizer_arn : entity_recognizer_arn option;The Amazon Resource Name (ARN) that identifies the entity recognizer.
*)}type nonrec create_entity_recognizer_request = {model_policy : policy option;The JSON resource-based policy to attach to your custom entity recognizer model. You can use this policy to allow another Amazon Web Services account to import your custom model.
Provide your JSON as a UTF-8 encoded string without line breaks. To provide valid JSON for your policy, enclose the attribute names and values in double quotes. If the JSON body is also enclosed in double quotes, then you must escape the double quotes that are inside the policy:
"{\"attribute\": \"value\", \"attribute\": [\"value\"]}"
To avoid escaping quotes, you can use single quotes to enclose the policy and double quotes to enclose the JSON names and values:
'{"attribute": "value", "attribute": ["value"]}'
model_kms_key_id : kms_key_id option;ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"vpc_config : vpc_config option;Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your custom entity recognizer. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"language_code : language_code;You can specify any of the following languages: English ("en"), Spanish ("es"), French ("fr"), Italian ("it"), German ("de"), or Portuguese ("pt"). If you plan to use this entity recognizer with PDF, Word, or image input files, you must specify English as the language. All training documents must be in the same language.
*)client_request_token : client_request_token_string option;A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
*)input_data_config : entity_recognizer_input_data_config;Specifies the format and location of the input data. The S3 bucket containing the input data must be located in the same Region as the entity recognizer being created.
*)data_access_role_arn : iam_role_arn;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)version_name : version_name option;The version name given to the newly created recognizer. Version names can be a maximum of 256 characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The version name must be unique among all models with the same recognizer name in the account/Region.
*)recognizer_name : comprehend_arn_name;The name given to the newly created recognizer. Recognizer names can be a maximum of 256 characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The name must be unique in the account/Region.
*)}type nonrec create_endpoint_response = {model_arn : comprehend_model_arn option;The Amazon Resource Number (ARN) of the model to which the endpoint is attached.
*)endpoint_arn : comprehend_endpoint_arn option;The Amazon Resource Number (ARN) of the endpoint being created.
*)}type nonrec create_endpoint_request = {flywheel_arn : comprehend_flywheel_arn option;The Amazon Resource Number (ARN) of the flywheel to which the endpoint will be attached.
*)data_access_role_arn : iam_role_arn option;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to trained custom models encrypted with a customer managed key (ModelKmsKeyId).
*)client_request_token : client_request_token_string option;An idempotency token provided by the customer. If this token matches a previous endpoint creation request, Amazon Comprehend will not return a ResourceInUseException.
desired_inference_units : inference_units_integer;The desired number of inference units to be used by the model using this endpoint. Each inference unit represents of a throughput of 100 characters per second.
*)model_arn : comprehend_model_arn option;The Amazon Resource Number (ARN) of the model to which the endpoint will be attached.
*)endpoint_name : comprehend_endpoint_name;This is the descriptive suffix that becomes part of the EndpointArn used for all subsequent requests to this resource.
}type nonrec create_document_classifier_response = {document_classifier_arn : document_classifier_arn option;The Amazon Resource Name (ARN) that identifies the document classifier.
*)}type nonrec create_document_classifier_request = {model_policy : policy option;The resource-based policy to attach to your custom document classifier model. You can use this policy to allow another Amazon Web Services account to import your custom model.
Provide your policy as a JSON body that you enter as a UTF-8 encoded string without line breaks. To provide valid JSON, enclose the attribute names and values in double quotes. If the JSON body is also enclosed in double quotes, then you must escape the double quotes that are inside the policy:
"{\"attribute\": \"value\", \"attribute\": [\"value\"]}"
To avoid escaping quotes, you can use single quotes to enclose the policy and double quotes to enclose the JSON names and values:
'{"attribute": "value", "attribute": ["value"]}'
model_kms_key_id : kms_key_id option;ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"mode : document_classifier_mode option;Indicates the mode in which the classifier will be trained. The classifier can be trained in multi-class (single-label) mode or multi-label mode. Multi-class mode identifies a single class label for each document and multi-label mode identifies one or more class labels for each document. Multiple labels for an individual document are separated by a delimiter. The default delimiter between labels is a pipe (|).
*)vpc_config : vpc_config option;Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your custom classifier. For more information, see Amazon VPC.
*)volume_kms_key_id : kms_key_id option;ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
"1234abcd-12ab-34cd-56ef-1234567890ab""arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"language_code : language_code;The language of the input documents. You can specify any of the languages supported by Amazon Comprehend. All documents must be in the same language.
*)client_request_token : client_request_token_string option;A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
*)output_data_config : document_classifier_output_data_config option;Specifies the location for the output files from a custom classifier job. This parameter is required for a request that creates a native document model.
*)input_data_config : document_classifier_input_data_config;Specifies the format and location of the input data for the job.
*)data_access_role_arn : iam_role_arn;The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
*)version_name : version_name option;The version name given to the newly created classifier. Version names can have a maximum of 256 characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The version name must be unique among all models with the same classifier name in the Amazon Web Services account/Amazon Web Services Region.
*)document_classifier_name : comprehend_arn_name;The name of the document classifier.
*)}type nonrec create_dataset_response = {dataset_arn : comprehend_dataset_arn option;The ARN of the dataset.
*)}type nonrec create_dataset_request = {client_request_token : client_request_token_string option;A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
*)input_data_config : dataset_input_data_config;Information about the input data configuration. The type of input data varies based on the format of the input and whether the data is for a classifier model or an entity recognition model.
*)description : description option;Description of the dataset.
*)dataset_type : dataset_type option;The dataset type. You can specify that the data in a dataset is for training the model or for testing the model.
*)dataset_name : comprehend_arn_name;Name of the dataset.
*)flywheel_arn : comprehend_flywheel_arn;The Amazon Resource Number (ARN) of the flywheel of the flywheel to receive the data.
*)}type nonrec contains_pii_entities_response = {labels : list_of_entity_labels option;The labels used in the document being analyzed. Individual labels represent personally identifiable information (PII) entity types.
*)}type nonrec contains_pii_entities_request = {language_code : language_code;The language of the input documents.
*)text : string_;A UTF-8 text string. The maximum string size is 100 KB.
*)}type nonrec classify_document_response = {warnings : list_of_warnings option;Warnings detected while processing the input document. The response includes a warning if there is a mismatch between the input document type and the model type associated with the endpoint that you specified. The response can also include warnings for individual pages that have a mismatch.
The field is empty if the system generated no warnings.
*)errors : list_of_errors option;Page-level errors that the system detected while processing the input document. The field is empty if the system encountered no errors.
*)document_type : list_of_document_type option;The document type for each page in the input document. This field is present in the response only if your request includes the Byte parameter.
document_metadata : document_metadata option;Extraction information about the document. This field is present in the response only if your request includes the Byte parameter.
labels : list_of_labels option;The labels used in the document being analyzed. These are used for multi-label trained models. Individual labels represent different categories that are related in some manner and are not mutually exclusive. For example, a movie can be just an action movie, or it can be an action movie, a science fiction movie, and a comedy, all at the same time.
*)classes : list_of_classes option;The classes used by the document being analyzed. These are used for models trained in multi-class mode. Individual classes are mutually exclusive and each document is expected to have only a single class assigned to it. For example, an animal can be a dog or a cat, but not both at the same time.
For prompt safety classification, the response includes only two classes (SAFE_PROMPT and UNSAFE_PROMPT), along with a confidence score for each class. The value range of the score is zero to one, where one is the highest confidence.
*)}type nonrec classify_document_request = {document_reader_config : document_reader_config option;Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.
*)bytes : semi_structured_document_blob option;Use the Bytes parameter to input a text, PDF, Word or image file.
When you classify a document using a custom model, you can also use the Bytes parameter to input an Amazon Textract DetectDocumentText or AnalyzeDocument output file.
To classify a document using the prompt safety classifier, use the Text parameter for input.
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.
The maximum length of this field depends on the input document type. For details, see Inputs for real-time custom analysis in the Comprehend Developer Guide.
If you use the Bytes parameter, do not use the Text parameter.
endpoint_arn : document_classifier_endpoint_arn;The Amazon Resource Number (ARN) of the endpoint.
For prompt safety classification, Amazon Comprehend provides the endpoint ARN. For more information about prompt safety classifiers, see Prompt safety classification in the Amazon Comprehend Developer Guide
For custom classification, you create an endpoint for your custom model. For more information, see Using Amazon Comprehend endpoints.
*)text : customer_input_string option;The document text to be analyzed. If you enter text using this parameter, do not use the Bytes parameter.
}The number of documents in the request exceeds the limit of 25. Try your request again with fewer documents.
type nonrec batch_item_error = {error_message : string_ option;A text description of the error.
*)error_code : string_ option;The numeric error code of the error.
*)index : integer option;The zero-based index of the document in the input list.
*)}Describes an error that occurred while processing a document in a batch. The operation returns on BatchItemError object for each document that contained an error.
type nonrec batch_item_error_list = batch_item_error listtype nonrec batch_detect_targeted_sentiment_response = {error_list : batch_item_error_list;List of errors that the operation can return.
*)result_list : list_of_detect_targeted_sentiment_result;A list of objects containing the results of the operation. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If all of the documents contain an error, the ResultList is empty.
}type nonrec batch_detect_targeted_sentiment_request = {language_code : language_code;The language of the input documents. Currently, English is the only supported language.
*)text_list : customer_input_string_list;A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25 documents. The maximum size of each document is 5 KB.
*)}type nonrec batch_detect_syntax_response = {error_list : batch_item_error_list;A list containing one object for each document that contained an error. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If there are no errors in the batch, the ErrorList is empty.
result_list : list_of_detect_syntax_result;A list of objects containing the results of the operation. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If all of the documents contain an error, the ResultList is empty.
}type nonrec batch_detect_syntax_request = {language_code : syntax_language_code;The language of the input documents. You can specify any of the following languages supported by Amazon Comprehend: German ("de"), English ("en"), Spanish ("es"), French ("fr"), Italian ("it"), or Portuguese ("pt"). All documents must be in the same language.
*)text_list : customer_input_string_list;A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25 documents. The maximum size for each document is 5 KB.
*)}type nonrec batch_detect_sentiment_response = {error_list : batch_item_error_list;A list containing one object for each document that contained an error. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If there are no errors in the batch, the ErrorList is empty.
result_list : list_of_detect_sentiment_result;A list of objects containing the results of the operation. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If all of the documents contain an error, the ResultList is empty.
}type nonrec batch_detect_sentiment_request = {language_code : language_code;The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
*)text_list : customer_input_string_list;A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25 documents. The maximum size of each document is 5 KB.
*)}type nonrec batch_detect_key_phrases_response = {error_list : batch_item_error_list;A list containing one object for each document that contained an error. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If there are no errors in the batch, the ErrorList is empty.
result_list : list_of_detect_key_phrases_result;A list of objects containing the results of the operation. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If all of the documents contain an error, the ResultList is empty.
}type nonrec batch_detect_key_phrases_request = {language_code : language_code;The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
*)text_list : customer_input_string_list;A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25 documents. The maximum size of each document is 5 KB.
*)}type nonrec batch_detect_entities_response = {error_list : batch_item_error_list;A list containing one object for each document that contained an error. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If there are no errors in the batch, the ErrorList is empty.
result_list : list_of_detect_entities_result;A list of objects containing the results of the operation. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If all of the documents contain an error, the ResultList is empty.
}type nonrec batch_detect_entities_request = {language_code : language_code;The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
*)text_list : customer_input_string_list;A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25 documents. The maximum size of each document is 5 KB.
*)}type nonrec batch_detect_dominant_language_response = {error_list : batch_item_error_list;A list containing one object for each document that contained an error. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If there are no errors in the batch, the ErrorList is empty.
result_list : list_of_detect_dominant_language_result;A list of objects containing the results of the operation. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If all of the documents contain an error, the ResultList is empty.
}type nonrec batch_detect_dominant_language_request = {text_list : customer_input_string_list;A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25 documents. Each document should contain at least 20 characters. The maximum size of each document is 5 KB.
*)}