{ "version": "2.0", "service": "
Amazon Comprehend is an AWS service for gaining insight into the content of documents. Use these actions to determine the topics contained in your documents, the topics they discuss, the predominant sentiment expressed in them, the predominant language used, and more.
", "operations": { "BatchDetectDominantLanguage": "Determines the dominant language of the input text for a batch of documents. For a list of languages that Amazon Comprehend can detect, see Amazon Comprehend Supported Languages.
", "BatchDetectEntities": "Inspects the text of a batch of documents and returns information about them. For more information about entities, see how-entities
", "BatchDetectKeyPhrases": "Detects the key noun phrases found in a batch of documents.
", "BatchDetectSentiment": "Inspects a batch of documents and returns an inference of the prevailing sentiment, POSITIVE
, NEUTRAL
, MIXED
, or NEGATIVE
, in each one.
Gets the properties associated with a topic detection job. Use this operation to get the status of a detection job.
", "DetectDominantLanguage": "Determines the dominant language of the input text. For a list of languages that Amazon Comprehend can detect, see Amazon Comprehend Supported Languages.
", "DetectEntities": "Inspects text for entities, and returns information about them. For more information, about entities, see how-entities.
", "DetectKeyPhrases": "Detects the key noun phrases found in the text.
", "DetectSentiment": "Inspects text and returns an inference of the prevailing sentiment (POSITIVE
, NEUTRAL
, MIXED
, or NEGATIVE
).
Gets a list of the topic detection jobs that you have submitted.
", "StartTopicsDetectionJob": "Starts an asynchronous topic detection job. Use the DescribeTopicDetectionJob
operation to track the status of a job.
A description for the status of a job.
" } }, "BatchDetectDominantLanguageItemResult": { "base": "The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.
", "refs": { "ListOfDetectDominantLanguageResult$member": null } }, "BatchDetectDominantLanguageRequest": { "base": null, "refs": { } }, "BatchDetectDominantLanguageResponse": { "base": null, "refs": { } }, "BatchDetectEntitiesItemResult": { "base": "The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.
", "refs": { "ListOfDetectEntitiesResult$member": null } }, "BatchDetectEntitiesRequest": { "base": null, "refs": { } }, "BatchDetectEntitiesResponse": { "base": null, "refs": { } }, "BatchDetectKeyPhrasesItemResult": { "base": "The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.
", "refs": { "ListOfDetectKeyPhrasesResult$member": null } }, "BatchDetectKeyPhrasesRequest": { "base": null, "refs": { } }, "BatchDetectKeyPhrasesResponse": { "base": null, "refs": { } }, "BatchDetectSentimentItemResult": { "base": "The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.
", "refs": { "ListOfDetectSentimentResult$member": null } }, "BatchDetectSentimentRequest": { "base": null, "refs": { } }, "BatchDetectSentimentResponse": { "base": null, "refs": { } }, "BatchItemError": { "base": "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.
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.
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.
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.
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.
The number of documents in the request exceeds the limit of 25. Try your request again with fewer documents.
", "refs": { } }, "ClientRequestTokenString": { "base": null, "refs": { "StartTopicsDetectionJobRequest$ClientRequestToken": "A unique identifier for the request. If you do not set the client request token, Amazon Comprehend generates one.
" } }, "DescribeTopicsDetectionJobRequest": { "base": null, "refs": { } }, "DescribeTopicsDetectionJobResponse": { "base": null, "refs": { } }, "DetectDominantLanguageRequest": { "base": null, "refs": { } }, "DetectDominantLanguageResponse": { "base": null, "refs": { } }, "DetectEntitiesRequest": { "base": null, "refs": { } }, "DetectEntitiesResponse": { "base": null, "refs": { } }, "DetectKeyPhrasesRequest": { "base": null, "refs": { } }, "DetectKeyPhrasesResponse": { "base": null, "refs": { } }, "DetectSentimentRequest": { "base": null, "refs": { } }, "DetectSentimentResponse": { "base": null, "refs": { } }, "DominantLanguage": { "base": "Returns the code for the dominant language in the input text and the level of confidence that Amazon Comprehend has in the accuracy of the detection.
", "refs": { "ListOfDominantLanguages$member": null } }, "Entity": { "base": "Provides information about an entity.
", "refs": { "ListOfEntities$member": null } }, "EntityType": { "base": null, "refs": { "Entity$Type": "
The entity's type.
" } }, "Float": { "base": null, "refs": { "DominantLanguage$Score": "The level of confidence that Amazon Comprehend has in the accuracy of the detection.
", "Entity$Score": "The level of confidence that Amazon Comprehend has in the accuracy of the detection.
", "KeyPhrase$Score": "The level of confidence that Amazon Comprehend has in the accuracy of the detection.
", "SentimentScore$Positive": "The level of confidence that Amazon Comprehend has in the accuracy of its detection of the POSITIVE
sentiment.
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEGATIVE
sentiment.
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEUTRAL
sentiment.
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the MIXED
sentiment.
The Amazon Resource Name (ARN) of the AWS Identity and Access Management (IAM) role that grants Amazon Comprehend read access to your input data.
" } }, "InputDataConfig": { "base": "The input properties for a topic detection job.
", "refs": { "StartTopicsDetectionJobRequest$InputDataConfig": "Specifies the format and location of the input data for the job.
", "TopicsDetectionJobProperties$InputDataConfig": "The input data configuration supplied when you created the topic detection job.
" } }, "InputFormat": { "base": null, "refs": { "InputDataConfig$InputFormat": "Specifies how the text in an input file should be processed:
ONE_DOC_PER_FILE
- Each file is considered a separate document. Use this option when you are processing large documents, such as newspaper articles or scientific papers.
ONE_DOC_PER_LINE
- Each line in a file is considered a separate document. Use this option when you are processing many short documents, such as text messages.
The zero-based index of the document in the input list.
", "BatchDetectEntitiesItemResult$Index": "The zero-based index of the document in the input list.
", "BatchDetectKeyPhrasesItemResult$Index": "The zero-based index of the document in the input list.
", "BatchDetectSentimentItemResult$Index": "The zero-based index of the document in the input list.
", "BatchItemError$Index": "The zero-based index of the document in the input list.
", "Entity$BeginOffset": "A character offset in the input text that shows where the entity begins (the first character is at position 0). The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.
", "Entity$EndOffset": "A character offset in the input text that shows where the entity ends. The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.
", "KeyPhrase$BeginOffset": "A character offset in the input text that shows where the key phrase begins (the first character is at position 0). The offset returns the position of each UTF-8 code point in the string. A code point is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.
", "KeyPhrase$EndOffset": "A character offset in the input text where the key phrase ends. The offset returns the position of each UTF-8 code point in the string. A code point
is the abstract character from a particular graphical representation. For example, a multi-byte UTF-8 character maps to a single code point.
The number of topics to detect supplied when you created the topic detection job. The default is 10.
" } }, "InternalServerException": { "base": "An internal server error occurred. Retry your request.
", "refs": { } }, "InvalidFilterException": { "base": "The filter specified for the ListTopicDetectionJobs
operation is invalid. Specify a different filter.
The request is invalid.
", "refs": { } }, "JobId": { "base": null, "refs": { "DescribeTopicsDetectionJobRequest$JobId": "The identifier assigned by the user to the detection job.
", "StartTopicsDetectionJobResponse$JobId": "The identifier generated for the job. To get the status of the job, use this identifier with the DescribeTopicDetectionJob
operation.
The identifier assigned to the topic detection job.
" } }, "JobName": { "base": null, "refs": { "StartTopicsDetectionJobRequest$JobName": "The identifier of the job.
", "TopicsDetectionJobFilter$JobName": "", "TopicsDetectionJobProperties$JobName": "The name of the topic detection job.
" } }, "JobNotFoundException": { "base": "The specified job was not found. Check the job ID and try again.
", "refs": { } }, "JobStatus": { "base": null, "refs": { "StartTopicsDetectionJobResponse$JobStatus": "The status of the job:
SUBMITTED - The job has been received and is queued for processing.
IN_PROGRESS - Amazon Comprehend is processing the job.
COMPLETED - The job was successfully completed and the output is available.
FAILED - The job did not complete. To get details, use the DescribeTopicDetectionJob
operation.
Filters the list of topic detection jobs based on job status. Returns only jobs with the specified status.
", "TopicsDetectionJobProperties$JobStatus": "The current status of the topic detection job. If the status is Failed
, the reason for the failure is shown in the Message
field.
Describes a key noun phrase.
", "refs": { "ListOfKeyPhrases$member": null } }, "LanguageCode": { "base": null, "refs": { "DetectEntitiesRequest$LanguageCode": "The RFC 5646 language code of the input text. If the request does not specify the language code, the service detects the dominant language. If you specify a language code that the service does not support, it returns UnsupportedLanguageException
exception. For more information about RFC 5646, see Tags for Identifying Languages on the IETF Tools web site.
The RFC 5646 language code for the input text. If you don't specify a language code, Amazon Comprehend detects the dominant language. If you specify the code for a language that Amazon Comprehend does not support, it returns and UnsupportedLanguageException
. For more information about RFC 5646, see Tags for Identifying Languages on the IETF Tools web site.
The RFC 5646 language code for the input text. If you don't specify a language code, Amazon Comprehend detects the dominant language. If you specify the code for a language that Amazon Comprehend does not support, it returns and UnsupportedLanguageException
. For more information about RFC 5646, see Tags for Identifying Languages on the IETF Tools web site.
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.
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.
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.
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.
One or more DominantLanguage objects describing the dominant languages in the document.
", "DetectDominantLanguageResponse$Languages": "The languages that Amazon Comprehend detected in the input text. For each language, the response returns the RFC 5646 language code and the level of confidence that Amazon Comprehend has in the accuracy of its inference. For more information about RFC 5646, see Tags for Identifying Languages on the IETF Tools web site.
" } }, "ListOfEntities": { "base": null, "refs": { "BatchDetectEntitiesItemResult$Entities": "One or more Entity objects, one for each entity detected in the document.
", "DetectEntitiesResponse$Entities": "A collection of entities identified in the input text. For each entity, the response provides the entity text, entity type, where the entity text begins and ends, and the level of confidence that Amazon Comprehend has in the detection. For a list of entity types, see how-entities.
" } }, "ListOfKeyPhrases": { "base": null, "refs": { "BatchDetectKeyPhrasesItemResult$KeyPhrases": "One or more KeyPhrase objects, one for each key phrase detected in the document.
", "DetectKeyPhrasesResponse$KeyPhrases": "A collection of key phrases that Amazon Comprehend identified in the input text. For each key phrase, the response provides the text of the key phrase, where the key phrase begins and ends, and the level of confidence that Amazon Comprehend has in the accuracy of the detection.
" } }, "ListTopicsDetectionJobsRequest": { "base": null, "refs": { } }, "ListTopicsDetectionJobsResponse": { "base": null, "refs": { } }, "MaxResultsInteger": { "base": null, "refs": { "ListTopicsDetectionJobsRequest$MaxResults": "The maximum number of results to return in each page.
" } }, "NumberOfTopicsInteger": { "base": null, "refs": { "StartTopicsDetectionJobRequest$NumberOfTopics": "The number of topics to detect.
" } }, "OutputDataConfig": { "base": "Provides configuration parameters for the output of topic detection jobs.
", "refs": { "StartTopicsDetectionJobRequest$OutputDataConfig": "Specifies where to send the output files.
", "TopicsDetectionJobProperties$OutputDataConfig": "The output data configuration supplied when you created the topic detection job.
" } }, "S3Uri": { "base": null, "refs": { "InputDataConfig$S3Uri": "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 Amazon S3 URI 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 service creates an output file called output.tar.gz
. It is a compressed archive that contains 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. For more information, see topic-modeling.
Describes the level of confidence that Amazon Comprehend has in the accuracy of its detection of sentiments.
", "refs": { "BatchDetectSentimentItemResult$SentimentScore": "The level of confidence that Amazon Comprehend has in the accuracy of its sentiment detection.
", "DetectSentimentResponse$SentimentScore": "An object that lists the sentiments, and their corresponding confidence levels.
" } }, "SentimentType": { "base": null, "refs": { "BatchDetectSentimentItemResult$Sentiment": "The sentiment detected in the document.
", "DetectSentimentResponse$Sentiment": "The inferred sentiment that Amazon Comprehend has the highest level of confidence in.
" } }, "StartTopicsDetectionJobRequest": { "base": null, "refs": { } }, "StartTopicsDetectionJobResponse": { "base": null, "refs": { } }, "String": { "base": null, "refs": { "BatchDetectEntitiesRequest$LanguageCode": "The language of the input documents. All documents must be in the same language.
", "BatchDetectKeyPhrasesRequest$LanguageCode": "The language of the input documents. All documents must be in the same language.
", "BatchDetectSentimentRequest$LanguageCode": "The language of the input documents. All documents must be in the same language.
", "BatchItemError$ErrorCode": "The numeric error code of the error.
", "BatchItemError$ErrorMessage": "A text description of the error.
", "BatchSizeLimitExceededException$Message": null, "DetectDominantLanguageRequest$Text": "A UTF-8 text string. Each string should contain at least 20 characters and must contain fewer that 5,000 bytes of UTF-8 encoded characters.
", "DetectEntitiesRequest$Text": "A UTF-8 text string. Each string must contain fewer that 5,000 bytes of UTF-8 encoded characters.
", "DetectKeyPhrasesRequest$Text": "A UTF-8 text string. Each string must contain fewer that 5,000 bytes of UTF-8 encoded characters.
", "DetectSentimentRequest$Text": "A UTF-8 text string. Each string must contain fewer that 5,000 bytes of UTF-8 encoded characters.
", "DominantLanguage$LanguageCode": "The RFC 5646 language code for the dominant language.
", "Entity$Text": "The text of the entity.
", "InternalServerException$Message": null, "InvalidFilterException$Message": null, "InvalidRequestException$Message": null, "JobNotFoundException$Message": null, "KeyPhrase$Text": "The text of a key noun phrase.
", "ListTopicsDetectionJobsRequest$NextToken": "Identifies the next page of results to return.
", "ListTopicsDetectionJobsResponse$NextToken": "Identifies the next page of results to return.
", "StringList$member": null, "TextSizeLimitExceededException$Message": null, "TooManyRequestsException$Message": null, "UnsupportedLanguageException$Message": null } }, "StringList": { "base": null, "refs": { "BatchDetectDominantLanguageRequest$TextList": "A list containing the text of the input documents. The list can contain a maximum of 25 documents. Each document should contain at least 20 characters and must contain fewer than 5,000 bytes of UTF-8 encoded characters.
", "BatchDetectEntitiesRequest$TextList": "A list containing the text of the input documents. The list can contain a maximum of 25 documents. Each document must contain fewer than 5,000 bytes of UTF-8 encoded characters.
", "BatchDetectKeyPhrasesRequest$TextList": "A list containing the text of the input documents. The list can contain a maximum of 25 documents. Each document must contain fewer that 5,000 bytes of UTF-8 encoded characters.
", "BatchDetectSentimentRequest$TextList": "A list containing the text of the input documents. The list can contain a maximum of 25 documents. Each document must contain fewer that 5,000 bytes of UTF-8 encoded characters.
" } }, "TextSizeLimitExceededException": { "base": "The size of the input text exceeds the limit. Use a smaller document.
", "refs": { } }, "Timestamp": { "base": null, "refs": { "TopicsDetectionJobFilter$SubmitTimeBefore": "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.
", "TopicsDetectionJobFilter$SubmitTimeAfter": "Filters the list of jobs based on the time that the job was submitted for processing. Only returns jobs submitted after the specified time. Jobs are returned in ascending order, oldest to newest.
", "TopicsDetectionJobProperties$SubmitTime": "The time that the topic detection job was submitted for processing.
", "TopicsDetectionJobProperties$EndTime": "The time that the topic detection job was completed.
" } }, "TooManyRequestsException": { "base": "The number of requests exceeds the limit. Resubmit your request later.
", "refs": { } }, "TopicsDetectionJobFilter": { "base": "Provides information for filtering topic detection jobs. For more information, see .
", "refs": { "ListTopicsDetectionJobsRequest$Filter": "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.
" } }, "TopicsDetectionJobProperties": { "base": "Provides information about a topic detection job.
", "refs": { "DescribeTopicsDetectionJobResponse$TopicsDetectionJobProperties": "The list of properties for the requested job.
", "TopicsDetectionJobPropertiesList$member": null } }, "TopicsDetectionJobPropertiesList": { "base": null, "refs": { "ListTopicsDetectionJobsResponse$TopicsDetectionJobPropertiesList": "A list containing the properties of each job that is returned.
" } }, "UnsupportedLanguageException": { "base": "Amazon Comprehend can't process the language of the input text. For all APIs except DetectDominantLanguage
, Amazon Comprehend accepts only English or Spanish text. For the DetectDominantLanguage
API, Amazon Comprehend detects 100 languages. For a list of languages, see how-languages