Determines the dominant language of the input text for a batch of documents.

Inspects the text of a batch of documents for named entities and returns information about them.

Inspects the text of a batch of documents for the syntax and part of speech of the words in the document and returns information about them.

Inspects a batch of documents and returns a sentiment analysis for each entity identified in the documents.

Creates a classification request to analyze a single document in real-time.

ClassifyDocument supports the following model types:

• Custom classifier - a custom model that you have created and trained. For input, you can provide plain text, a single-page document (PDF, Word, or image), or Amazon Textract API output. For more information, see Custom classification: https://docs.aws.amazon.com/comprehend/latest/dg/how-document-classification.html in the Amazon Comprehend Developer Guide.

• Prompt safety classifier - Amazon Comprehend provides a pre-trained model for classifying input prompts for generative AI applications. For input, you provide English plain text input. For prompt safety classification, the response includes only the Classes field. For more information about prompt safety classifiers, see Prompt safety classification: https://docs.aws.amazon.com/comprehend/latest/dg/trust-safety.html#prompt-classification in the Amazon Comprehend Developer Guide.

If the system detects errors while processing a page in the input document, the API response includes an Errors field that describes the errors.

Creates a dataset to upload training or test data for a model associated with a flywheel.

Creates a new document classifier that you can use to categorize documents.

Creates an entity recognizer using submitted files.

A flywheel is an Amazon Web Services resource that orchestrates the ongoing training of a model for custom classification or custom entity recognition.

You can create a flywheel to start with an existing trained model, or Comprehend can create and train a new model.

When you create the flywheel, Comprehend creates a data lake in your account. The data lake holds the training data and test data for all versions of the model.

To use a flywheel with an existing trained model, you specify the active model version. Comprehend copies the model's training data and test data into the flywheel's data lake.

To use the flywheel with a new model, you need to provide a dataset for training data (and optional test data) when you create the flywheel.

Deletes a previously created document classifier

Only those classifiers that are in terminated states (IN_ERROR, TRAINED) will be deleted.

If an active inference job is using the model, a ResourceInUseException will be returned.

Deletes a model-specific endpoint for a previously-trained custom model.

Deletes an entity recognizer.

Only those recognizers that are in terminated states (IN_ERROR, TRAINED) will be deleted. If an active inference job is using the model, a ResourceInUseException will be returned.

Deletes a flywheel.

When you delete the flywheel, Amazon Comprehend does not delete the data lake or the model associated with the flywheel.

Returns information about the dataset that you specify.

Gets the properties associated with a document classification job.

Gets the properties associated with a dominant language detection job.

Gets the properties associated with a specific endpoint.

Gets the properties associated with an entities detection job.

Provides configuration information about the flywheel.

Retrieve the configuration properties of a flywheel iteration.

Gets the properties associated with a key phrases detection job.

Gets the properties associated with a PII entities detection job.

Gets the properties associated with a sentiment detection job.

Gets the properties associated with a targeted sentiment detection job.

Gets the properties associated with a topic detection job.

Determines the dominant language of the input text.

Detects named entities in input text when you use the pre-trained model.

Detects custom entities if you have a custom entity recognition model.

When detecting named entities using the pre-trained model, use plain text as the input. For more information about named entities, see Entities: https://docs.aws.amazon.com/comprehend/latest/dg/how-entities.html in the Comprehend Developer Guide.

When you use a custom entity recognition model, you can input plain text or you can upload a single-page input document (text, PDF, Word, or image).

If the system detects errors while processing a page in the input document, the API response includes an entry in Errors for each error.

Inspects text for syntax and the part of speech of words in the document.

Inspects the input text and returns a sentiment analysis for each entity identified in the text.

Performs toxicity analysis on the list of text strings that you provide as input.

Creates a new custom model that replicates a source custom model that you import.

The source model can be in your Amazon Web Services account or another one.

If the source model is in another Amazon Web Services account, then it must have a resource-based policy that authorizes you to import it.

List the datasets that you have configured in this Region.

Gets a list of all existing endpoints that you've created.

Gets a list of the properties of all entity recognizers that you created, including recognizers currently in training.

Allows you to filter the list of recognizers based on criteria such as status and submission time. This call returns up to 500 entity recognizers in the list, with a default number of 100 recognizers in the list.

Information about the history of a flywheel iteration.

Attaches a resource-based policy to a custom model.

Starts an asynchronous document classification job using a custom classification model.

Starts an asynchronous dominant language detection job for a collection of documents.

Starts an asynchronous entity detection job for a collection of documents.

Use the operation to track the status of a job.

Start the flywheel iteration.This operation uses any new datasets to train a new model version.

Starts an asynchronous key phrase detection job for a collection of documents.

Starts an asynchronous sentiment detection job for a collection of documents.

Starts an asynchronous targeted sentiment detection job for a collection of documents.

Starts an asynchronous topic detection job.

Stops a dominant language detection job in progress.

If the job state is IN_PROGRESS the job is marked for termination and put into the STOP_REQUESTED state. If the job completes before it can be stopped, it is put into the COMPLETED state; otherwise the job is stopped and put into the STOPPED state.

If the job is in the COMPLETED or FAILED state when you call the StopDominantLanguageDetectionJob operation, the operation returns a 400 Internal Request Exception.

Stops an entities detection job in progress.

If the job state is IN_PROGRESS the job is marked for termination and put into the STOP_REQUESTED state. If the job completes before it can be stopped, it is put into the COMPLETED state; otherwise the job is stopped and put into the STOPPED state.

If the job is in the COMPLETED or FAILED state when you call the StopDominantLanguageDetectionJob operation, the operation returns a 400 Internal Request Exception.

Stops a key phrases detection job in progress.

If the job state is IN_PROGRESS the job is marked for termination and put into the STOP_REQUESTED state. If the job completes before it can be stopped, it is put into the COMPLETED state; otherwise the job is stopped and put into the STOPPED state.

If the job is in the COMPLETED or FAILED state when you call the StopDominantLanguageDetectionJob operation, the operation returns a 400 Internal Request Exception.

Stops a sentiment detection job in progress.

If the job state is IN_PROGRESS, the job is marked for termination and put into the STOP_REQUESTED state. If the job completes before it can be stopped, it is put into the COMPLETED state; otherwise the job is be stopped and put into the STOPPED state.

If the job is in the COMPLETED or FAILED state when you call the StopDominantLanguageDetectionJob operation, the operation returns a 400 Internal Request Exception.

Stops a targeted sentiment detection job in progress.

If the job state is IN_PROGRESS, the job is marked for termination and put into the STOP_REQUESTED state. If the job completes before it can be stopped, it is put into the COMPLETED state; otherwise the job is be stopped and put into the STOPPED state.

If the job is in the COMPLETED or FAILED state when you call the StopDominantLanguageDetectionJob operation, the operation returns a 400 Internal Request Exception.

Stops a document classifier training job while in progress.

Stops an entity recognizer training job while in progress.

Associates a specific tag with an Amazon Comprehend resource.

Updates information about the specified endpoint.