Create Habilidades de IA with Basado en el almacenamiento de datos Conexiones del modelo

This is the next logical step after creating a Basado en el almacenamiento de datos Conexión del modelo. You would create an Habilidad de IA and connect it to a Grounded Conexión del modelo from Google Vertex AI.

Nota:

Google Vertex AI Basado en el almacenamiento de datos Conexiones del modelo is now available in Automation 360 v34 release on Nube as well. You can use this feature in Nube and Local.

Almacén de datos de Google with document chunking is now supported to ensure optimal results in automation executions. You can enable document chunking in the Almacén de datos de Google for using Google Vertex AI Grounded models in AI Agent Studio.

A Pro Developer creates Habilidades de IA so the Bot Creators can use these in their automations to save time and effort.

Habilidades de IA are created by connecting to Conexiones del modelo the Pro Developer has access to. Next, the Habilidad de IA is fine-tuned by testing the prompts using different grounded models to find the best response that addresses the business ask. These Habilidades de IA are made available to Bot Creators for use to help accelerate the task of creating automations across solutions.

Antes de empezar

A Pro Developer requires these roles and permissions to create and test Habilidades de IA.
  • Role: AAE_Basic, Pro Developer Custom role
  • Permission: Bot Creator

See Roles y permisos para Herramientas de la IA

Other requirements:

Besides the roles and permissions the Pro Developer must be connected to a Agente de bot 22.60.10 and later. As part of testing the Conexión del modelo, you would have to run the bot on your desktop. Hence ensure the Agente de bot is configured to your user. If you have to switch connection to a different Control Room, see: Cambiar el registro del dispositivo entre las instancias de Control Room.

Procedimiento

  1. Log in to the Control Room and navigate to Automation > Create new or ‘+’ icon and choose Habilidades de IA.
  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 Conexiones del modelo you have access to. You would choose a Conexión del modelo that was created using the Anclado en la fuente de datos type option from Google Vertex AI.
    These Conexiones del modelo are created by the Automation Admin and assigned to your user with a custom role.
  4. After selecting a Conexión del modelo, the Habilidades de IA is set up with the default parameter settings that is optimal for the chosen model. You can change the settings as required.
    The Habilidad de IA 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 Constructor de agentes.
  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 Almacén de datos de Google.

    You can make sure that the Habilidad de IA grounds the response using information in a specific set of documents in the Almacén de datos de Google 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 Indicación 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 Habilidad de IA and add prompt inputs, as required. Let us use an example to walk you through the steps.
  7. In the Prompt field enter your Indicación 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 Constructor de agentes such as: tax_rules_2022.pdf, tax_rules_2023.pdf, and tax_rules_2024.pdf.

    The response for the Indicación 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 Indicación.
    Nota: Indicación data details could contain PHI, PII or other sensitive data you choose to enter in the Indicación. We recommend being mindful of this when testing and executing a Indicación.
  10. The Basado en el almacenamiento de datos Conexión del modelo 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 Basado en el almacenamiento de datos, the response is referenced from. You can see the document title of the referenced data store from the Almacén de datos de Google.

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

    Nota: 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.

Qué hacer a continuación

Your next step would be to check-in the Habilidad de IA to make it available to Citizen Developers and Pro Developers using the Habilidades de IA package.

Why would you check-in an Habilidad de IA?

After creating an Habilidad de IA, check it into the Public folder. This will let the Pro Developer, and Citizen Developer use it from the Habilidades de IA package in the production environment.

For reference, see:

A Bot de tarea, with one or multiple embedded Habilidades de IA can be added to a larger automation that would run a complete workflow scenario. You would create such a workflow in a Process Composer.

Nota: When you create or test an Habilidad de IA 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 Gobernanza de la IA.

As the next step in your sequence of tasks, go to Usar Habilidades de IA en un Bot de tarea and use the Habilidad de IA in an automation.