Frequently Asked Questions (FAQs)

The "Unique Identifier" and "Trigger Condition (including Example Queries)" fields are used by the LLM to identify which action it should invoke/use for a user's query.

Make sure to give a detailed trigger condition and example queries, to ensure LLM knows exactly what user queries should this action be used for.

Please follow the steps described on this page to setup authentication for Jira: (https://help.glean.com/en/articles/9006099-authenticate-actions-in-jira)

Type hints are like instructions that help the Glean AI understand and work with different actions better. They're clues that tell the AI what each part of an action does, making it easier for the AI to get the right information or do the right thing with those actions.

Benefits of Implementing Type Hints

• Simplified Action Creation: Type hints make it easier for developers to describe their actions' capabilities and requirements.
• Better at Getting Information and Doing Tasks:
• Type hints give clear instructions on gathering data or performing actions, leading to more accurate and relevant results from the AI.

How to Use Type Hints To use type-hints, consider the following steps:

• Identify Relevant Type Hints: Review the list of supported type hints to determine which ones align with your action's functionality.
• Incorporate Type Hints into Your API Specs:
• Add the selected type hints as structured details in your action's API specifications.

Supported Type Hints

Below are the type hints currently supported by Glean:

• Content

This hint is applied to fields that deal with large amounts of text or content. It's ideal for tools that generate, modify, or display content, ensuring that the information is handled appropriately. Example usage:

description:
  x-glean-typehint: 'Content'
  type: string
  description: Rich description.

• EmailAddress

This type hint is used for fields that are intended to capture the email address of the user. Example usage:

assignee:
  x-glean-typehint: 'EmailAddress'
  type: string
  description: User to which the issue is assigned.

• JiraComponentId

This hint is designated for fields that involve a JIRA component ID. It's useful for tools that need to interact with specific components within a JIRA project, facilitating precise and relevant operations. Example usage:

components:
  x-glean-typehint: 'JiraComponentId'
  type: string
  description: Component Id where the ticket should be filed.

• JiraIssueId

This hint is designated for fields that involve a JIRA issue ID. It's useful for tools that need to interact with a specific JIRA issue. Example usage:

issue:
  x-glean-typehint: 'JiraIssueId'
  type: string
  description: Issue Id on which comment should be posted.

• JiraIssuePriority

This type hint is for fields that denote the priority of a Jira issue. Example usage:

priority:
  x-glean-typehint: 'JiraIssuePriority'
  type: integer
  description: Numeric priority. 1 (Highest) to 5 (Lowest)
  minimum: 1
  maximum: 5

• JiraIssueType

This type hint is for fields that denote a Jira issue type. Example usage:

issue_type:
  x-glean-typehint: 'JiraIssueType'
  type: integer
  description: Issue type. 10000 refers to Epic, 10001 to Story, 10002 to Task, 10003 to Sub-Task, 10004 to Bug.

• JiraProjectID

This type hint is for fields that require a JIRA project ID. It's used in contexts where actions or information are specific to a particular JIRA project, helping to ensure that operations are correctly scoped. Example usage:

pid:
  x-glean-typehint: 'JiraProjectID'
  type: string
  description: Project ID where the ticket is created.

• ResultUrl

Attach this type hint to fields that contain the URL for the created object as a result of write action. Example usage:

jiraTicketUrl:
  x-glean-typehint: 'ResultUrl'
  type: string
  description: Url of the created object.

By incorporating these type hints into your action's API specifications, you can enhance the Glean AI assistant's understanding and handling of your action, leading to a more seamless integration and a better overall user experience. If you have any further questions or require assistance, our developer support team is here to help.

Yes, please contact our team for information on how to do this.

The response from the service you're connecting to retrieve content using your retrieval action will be sent to the LLM to create the final response. Hence, please ensure that the data returned is not larger than ~8000 characters. Depending on the LLM model being used, larger responses will be truncated from the end.