Create Affiné Connexions des modèles
- Dernière mise à jour2024/10/31
Create Affiné Connexions des modèles
Create Affiné Connexions des modèles by customizing the supported foundational models via testing and fine-tuning to make them available to Pro Developers for connecting to the Compétences en IA they create.
Connect to your instances of the foundational models from hyperscaler vendors such as Amazon Bedrock, Google Vertex AI, Azure OpenAI, or OpenAI and customize their models by fine-tuning them and saving them with a specific name.
The Automation Admin creates and tests the Affiné Connexions des modèles and makes these available to the Pro Developers, who can connect to them when creating Compétences en IA. The Connexions des modèles are used in Compétences en IA to send prompts and receive responses from the models.
The Automation Admin creates custom roles and assigns these Affiné Connexions des modèles to the custom roles that are assigned to users to enable their access to the Connexions des modèles.
This feature gives you the option to create your own custom models based on your specific use case. As these Affiné Connexions des modèles are customized and trained using your data, within your organization's environment, you can govern and monitor their use as per your compliance and governance policies.
Additionally, you can use the Affiné models created with Amazon Bedrock in AWS Services, and Google Vertex AI in Boutique de données Google when creating Affiné Connexions des modèles in Automation Anywhere.
A few things to consider
To use the Affiné Connexions des modèles you would first create them by via tooling provided by the hyperscaler models. These Affiné models are supported out-of-the-box by AI Agent Studio in Automation Anywhere.
Refer to the following information to create your custom, Affiné models for each foundational model:
- Create your Affiné model in Amazon Bedrock Services. See Fine-tuned models for Amazon Bedrock.
- Next, click Custom Models.
- Find your Affiné model and select it.
- Make a note of the Region where the model is deployed.
- Use the Model ARN and Region values procured from Amazon Bedrock to connect to your Affiné model when creating a Connexion du modèle in Automation Anywhere.
- Create a custom model in Google Vertex AI. See How to create Fine-tuned models for Google Vertex AI.
- Next, navigate to .
- Click View My Endpoints & Models.
- You should see the ModelID, and the relevant Region values for your Affiné model.
- Procure the ProjectId for this model from the first page after you log into Google Vertex AI. You can also get it from the top left corner after you log in, where it is additionally displayed.
- Use the procured ModelID and Region values to connect to your Affiné model when creating a Connexion du modèle in Automation Anywhere.
- To create a custom model in Azure OpenAI, see Customize a model with fine-tuning.
- Then create a deployment using this custom model. Make a note of the Model name and Deployment name.
- Use the Model name and Deployment name values to connect to your Affiné model when creating a Connexion du modèle in Automation Anywhere.
- Create your Affiné model in OpenAI. See Create a Fine-tuned model with OpenAI.
- Procure the Model ID that was generated for the Affiné model.
- Use this Model ID value when creating a Connexion du modèle in Automation Anywhere.
Prérequis
- 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.
See Rôles et autorisations pour les Outils AI for the Automation Admin custom role permissions.
- You would first create a Affiné Connexion du modèle and save it with a specific name so that you can use it when creating a Connexion du modèle. Refer to the section above to see how to create Affiné Connexions des modèles for each foundational model vendor.
- 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 du modèle, you must be connected to a Agent de 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 de 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 need access to the Enregistreur package and the Compétences en IA package to test the connection successfully. A test Invite would be executed to test the Connexion du modèle.
Follow these steps to create a Affiné Connexion du modèle.
Procédure
Étapes suivantes
See Gouvernance de l\'IA.
As the next step in your sequence of tasks, go to Créer Compétences en IA and create an Compétence en IA and connect to a Affiné Connexion du modèle to eventually use it in an automation.