Create AI スキル with データ ストアに基づく モデル接続

This is the next logical step after creating a データ ストアに基づく モデル接続. You would create an AI スキル and connect it to a Grounded モデル接続 from Google Vertex AI.

注:

Google Vertex AI データ ストアに基づく モデル接続 is now available in Automation 360 v34 release on クラウド as well. You can use this feature in クラウド and オンプレミス.

Google データ ソース with document chunking is now supported to ensure optimal results in automation executions. You can enable document chunking in the Google データ ソース for using Google Vertex AI Grounded models in AI エージェント Studio.

A Pro Developer creates AI スキル so the Bot 作成者 can use these in their automations to save time and effort.

AI スキル are created by connecting to モデル接続 the Pro Developer has access to. Next, the AI スキル is fine-tuned by testing the prompts using different grounded models to find the best response that addresses the business ask. These AI スキル are made available to Bot 作成者 for use to help accelerate the task of creating automations across solutions.

前提条件

A Pro Developer requires these roles and permissions to create and test AI スキル.
  • Role: AAE_Basic, Pro Developer Custom role
  • Permission: Bot Creator

See AI ツール のロールと権限

Other requirements:

Besides the roles and permissions the Pro Developer must be connected to a Bot エージェント 22.60.10 and later. As part of testing the モデル接続, you would have to run the Bot on your desktop. Hence ensure the Bot エージェント is configured to your user. If you have to switch connection to a different Control Room, see: Control Room インスタンス間でのデバイス登録の切り替え.

手順

  1. Log in to the Control Room and navigate to Automation > Create new or ‘+’ icon and choose AI スキル.
  2. Provide a name and description and click Create & edit to display a template outline.
  3. In the AI Skills screen, click Choose model connection to choose from the available list of モデル接続 you have access to. You would choose a モデル接続 that was created using the データ ソースに基づく type option from Google Vertex AI.
    These モデル接続 are created by the Automation Admin and assigned to your user with a custom role.
  4. After selecting a モデル接続, the AI スキル is set up with the default parameter settings that is optimal for the chosen model. You can change the settings as required.
    The AI スキル editor displays with default parameter values set by the model vendor which you can configure as required. These values can be configured when creating a data store in エージェント ビルダー.
  5. Next, add a filter condition, which is optional. This field supports a string format for entering the filter value. Adding a filter helps narrow down the model's search to the specific files within the Google データ ソース.

    You can make sure that the AI スキル grounds the response using information in a specific set of documents in the Google データ ソース by adding relevant metadata to the data store. This narrows down the scope of response and makes it more accurate. This also helps reduce the size of the data retrieved from the vector data store before passing it to the foundational model. If the data store content is vast, this filtering mechanism using metadata helps get a better response performance from the プロンプト query. For example: for the example What is the gift tax limit for the year 2024? (see below), you could use a filter for tax_year: ANY("2024").

    See Filter generic search for structured or unstructured data .

  6. Now you can start creating an AI スキル and add prompt inputs, as required. Let us use an example to walk you through the steps.
  7. In the Prompt field enter your プロンプト text with the input variables.

    For example:

    What is the gift tax limit for the year 2024?

    Prior to this step, you would have uploaded tax rule PDF documents for the last 3 years in the エージェント ビルダー such as: tax_rules_2022.pdf, tax_rules_2023.pdf, and tax_rules_2024.pdf.

    The response for the プロンプト text will be referenced from the tax_rules_2024.pdf document.

  8. Click out of the Prompt entry field.
  9. Click Get response to get a response from the model based on your プロンプト.
    注: プロンプト data details could contain PHI, PII or other sensitive data you choose to enter in the プロンプト. We recommend being mindful of this when testing and executing a プロンプト.
  10. The データ ストアに基づく モデル接続 returns a response in the Response field, and additionally displays a Citations field displaying all citation references.

    Citations are chunks of information stating, which section of a document stored in the データ ストアに基づく, the response is referenced from. You can see the document title of the referenced data store from the Google データ ソース.

    See Parse and chunk documents , and Chunk documents for RAG .

    注: The Document retrieval count parameter determines the maximum number of chunks that can be retrieved from the data store and provided as context to the hyperscaler model to generate the response.

次のステップ

Your next step would be to check-in the AI スキル to make it available to Citizen Developers and Pro Developers using the AI スキル package.

Why would you check-in an AI スキル?

After creating an AI スキル, check it into the Public folder. This will let the Pro Developer, and Citizen Developer use it from the AI スキル package in the production environment.

For reference, see:

A タスク Bot, with one or multiple embedded AI スキル can be added to a larger automation that would run a complete workflow scenario. You would create such a workflow in a Process Composer.

注: When you create or test an AI スキル in the AI Skill screen, the success or failure details along with the model responses can be viewed in these navigation screens:
  • Administration > AI governance > AI Prompt log
  • Administration > AI governance > Event log
  • Administration > Audit log

See AI ガバナンス.

As the next step in your sequence of tasks, go to AI スキル でのタスク Botの使用 and use the AI スキル in an automation.