The Language - Annotate Text task lets you perform several natural language operations such as, sentiment analysis, entity analysis, and syntactic analysis on a given text using Cloud Natural Language.
Before you begin
Ensure that you perform the following tasks in your Google Cloud project before configuring the Language - Annotate Text task:
- Enable the Cloud Natural Language API (
language.googleapis.com
). - Create an authentication profile. Apigee Integration uses an authentication profile to connect to an authentication endpoint for the Language - Annotate Text task.
For information about granting additional roles or permissions to a service account, see Granting, changing, and revoking access.
Configure the Language - Annotate Text task
- In the Apigee UI, select your Apigee Organization.
- Click Develop > Integrations.
- Select an existing integration or create a new integration by clicking Create Integration.
If you are creating a new integration:
- Enter a name and description in the Create Integration dialog.
- Select a Region for the integration from the list of supported regions.
- Click Create.
This opens the integration in the integration designer.
- In the integration designer navigation bar, click +Add a task/trigger > Tasks to view the list of available tasks.
- Click and place the Language - Annotate Text element in the integration designer.
- Click the Language - Annotate Text element on the designer to view the Language - Annotate Text task configuration pane.
- Go to Authentication, and select an existing authentication profile that you want to use.
Optional. If you have not created an authentication profile prior to configuring the task, Click + New authentication profile and follow the steps as mentioned in Create a new authentication profile.
- Go to Task Input, and configure the displayed inputs fields using the following Task input parameters table.
Changes to the inputs fields are saved automatically.
Task input parameters
The following table describes the input parameters of the Language - Annotate Text task:
Property | Data type | Description |
---|---|---|
Region | String | Region where you want to run the annotate operation. For example, us-central1 . |
ProjectsId | String | Your Google Cloud project ID. |
Request | JSON | See request JSON structure. For information on the supported Natural Language operations, see Supported Natural Language operations. |
Task output
The Language - Annotate Text task returns the response output depending on the operations performed. Following is a sample output when syntactic analysis are performed:
{ "sentences": [ ... Array of sentences with sentence information ], "tokens": [ ... Array of tokens with token information ] }
Supported Natural Language operations
The Language - Annotate Text task lets you perform the following Natural Language operations:
- Sentiment Analysis
- Use sentiment analysis to identify and determine the emotional attitue (positive, negative, or neutral) of a given text. To perform this operation, set the
extractDocumentSentiment
field of the request JSON totrue
. - Entity Analysis
- Use entity analysis to inspect and retrieve entities such as proper nouns and common nouns and from a given text. To perform this operation, set the
extractEntities
field of the request JSON totrue
. - Syntactic Analysis
- Use syntactic analysis to extract linguistic information from a given text. To perform this operation, set the
extractSyntax
field of the request JSON totrue
.
Error handling strategy
An error handling strategy for a task specifies the action to take if the task fails due to a temporary error. For information about how to use an error handling strategy, and to know about the different types of error handling strategies, see Error handling strategies.
What's next
- Add edges and edge conditions.
- Test and publish your integration.
- Configure a trigger.
- Add a Data Mapping task.
- See all tasks for Google Cloud services.