Create Grounded Connexions de modèle with Amazon Bedrock RAG capability

Create Fondé sur la base de connaissances Connexions de modèle using the native RAG (Retrieval Augmented Generation) capability from Amazon Bedrock to generate accurate and contextually relevant information referenced from Base de connaissances Amazon.

We are now offering you the option to create Connexions de modèle using the Amazon Bedrock-RAG capability. A search query on RAG retrieves relevant chunks of content from large-data-sets which are relevant and accurate to the provided context. After retrieving the relevant information, the model uses it to generate a response.

A few things to consider

  • To use the Amazon Bedrock-RAG capability, you would first create a Knowledge Base in Amazon Bedrock before creating the Fondé sur la base de connaissances Connexion de modèle.

    See: Create Base de connaissances Amazon

  • To use additional models from Amazon Bedrock that are not available for selection when creating a Connexion de modèle, you would have to procure the Model ID and the Model ARN from the supported models of Amazon Bedrock.

    See: Add Amazon Bedrock models from Services AWS

Work flow for using Amazon Bedrock RAG capability for creating Connexions de modèle

Prérequis

The Automation Admin requires these roles and permissions to create and manage Connexions de modèle for their business organization.
  • Role: AAE_Basic, Automation Admin custom role
  • Permission: Attended Bot Runner
  • Settings: AI Data Management must be enabled by the Automation Admin and the check box selected for Allow users to disable logs on AI Skills. Allow users with the Bot Creator license to disable data logging when using AI Skills to enable the Data logging toggle in the Compétences IA screen.

See Rôles et autorisations for the Automation Admin custom role permissions.

Other requirements:

  • As mentioned earlier, you would first create an Base de connaissances Amazon to create a Fondé sur la base de connaissances Connexion de modèle and use it successfully in an Compétence en IA.
  • If you want to store authentication details in a credential vault, have that information handy. See Magasin d'informations d'identification sécurisé via Credential Vault.
  • To test a Connexion de modèle, you must be connected to a Agent robot 22.60.10 and later. As part of the test, you would have to run the robot on your desktop. Hence ensure the Agent robot is configured to your user. For this task, if you have to switch connection to a different Control Room, see: Basculer l\'enregistrement de périphérique entre des instances de la Control Room.
  • You would need access to the Enregistreur package and the Compétences IA package to test the connection successfully. A test Invite would be executed to test the Connexion de modèle.

Procédure

  1. In your Control Room environment, navigate to AI > Model connections > Create model connection.
  2. In the Create model connection screen you would configure these Connection settings:
    Create Grounded Connexions de modèle with Amazon Bedrock RAG capability
    You can manually enter the model name in the Choose a model or create a custom one field. The name you enter will be used for creating the Connexion de modèle.
    1. Model connection name: Provide a name for easy identification of the Connexion de modèle.
    2. Description (optional): Add a meaningful short description defining the connection.
    3. Choose a vendor: Choose a foundational model vendor from the supported list of vendors. For creating a Fondé sur la base de connaissances Connexion de modèle with Amazon Bedrock, you would select Amazon Bedrock from the drop-down list.
    4. Choose a type: Choose Fondé sur la base de connaissances for using the RAG capability.
    5. Choose a model or create a custom one: Choose a model from the drop-down list of validated models from Amazon Bedrock.
      Additionally, we also support other models available from Amazon Bedrock, which are not available in the drop-down list. You can use either the Model ID or Model ARN to add to the list. See: Add Amazon Bedrock models from Services AWS.
      For a complete list of supported models for each foundational model vendor, see FAQ générale.
    6. Click Next to proceed to the Authentication details section.
  3. In the Authentication details section, configure these settings:
    1. Region: Choose the region where your selected model is deployed for authenticating the Connexion de modèle. You can also add a region that is not available in the drop-down list by referring to the list in Amazon Bedrock. Enter in this format to get the region added to the list. For example: us-east-1.
      For a list of supported deployment regions for Amazon Bedrock models, see Supported regions and models for Amazon Bedrock knowledge bases .
    2. Knowledge base ID: Provide the Knowledge Base ID you procured from Amazon Bedrock. .
      See Amazon Bedrock knowledge bases
    3. Access Key: This AWS access key serves as your unique identifier within the AWS ecosystem. It is a fundamental part of the authentication process, allowing Services AWS to recognize and validate your access.
    4. Secret Access Key: This key is the confidential counterpart to your Access Key ID. This key is used to sign requests made to AWS, enhancing security by ensuring that only authorized individuals or systems can access your AWS resources.
    5. Session Token (optional): This is an optional field. In addition to the above information, you can include a Session token, which is a temporary, time-bound token used when working with temporary security credentials. It provides an added layer of security, particularly in scenarios where temporary access is required, such as when using temporary security credentials.
    6. After setting up the authentication details, confirm and click Next to proceed to the Test connection section to test the Connexion de modèle.
    Remarque : For details on setting up the Access Key, Secret Access Key, and Session Token for Amazon Bedrock, see: Amazon Bedrock: action Authentifier.
  4. Click Test connection to make sure all connection details have been defined correctly and check if the connection is working.
    This is a desktop operation using a Agent robot. Use Agent robot 22.60.10 and later for successful testing.
    • If the connection works as expected, the system will process the request and you will get a system generated success message.
    • If the connection does not work as expected, you will get a system-generated message stating the reason for the connection failure. For example, if you have not downloaded the supported foundational model package to your workspace, you would get an error message. You would have to download the package and then retest the Connexion de modèle.
    • If the testing a Connexion de modèle is unsuccessful or if you leave the task incomplete, the Connexion de modèle will not get saved and you will have to restart the process of creating the Connexion de modèle.
  5. Click Next to proceed to the Invite roles section to begin assigning custom roles to users.
    The Automation Admin would create custom roles and assign the Connexions de modèle to the role, which can then be assigned to users. Only users assigned to this custom role can use this Connexion de modèle.
  6. Assign access to the Pro Developer via custom role (using RBAC), for using this Connexion de modèle to create an Compétence en IA.
  7. Click Create model connection to complete creating the Connexion de modèle.
    After successfully creating the Connexion de modèle, the Pro Developer would use it to create an Compétence en IA

    See: Créer Compétences IA avec Fondé sur la base de connaissances Connexions de modèle

    .

Étapes suivantes

After creating and testing the Connexion de modèle, you would assign it to the Pro Developers, who would use this connection to create Compétences IA.

See Créer Compétences IA avec Fondé sur la base de connaissances Connexions de modèle.

Remarque : When you create or test an Compétence en 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 Gouvernance de l\'IA.

As the next step in your sequence of tasks, go to Créer Compétences IA avec Fondé sur la base de connaissances Connexions de modèle and create an Compétence en IA and connect to a Fondé sur la base de connaissances Connexion de modèle to eventually use it in an automation.