Discover and Allow Models

Exploring the AI Catalog

The AI Catalog enables you to fully manage all AI assets in your organization.

Explore the various models available for use in your organization in the Discovery page.

You can see which models have already been allowed for use in your projects inn the Registry page.

Detect all AI assets that are used in your system, but are unmanaged by AI catalog, and possibly even unvetted by your organization, in the Detection page. For more information about detecting unmanaged AI assets, see Detect Shadow AI.

Managing Allowed Models

After you have allowed your first model, you will see that the allowed models all appear in the Registry page.

For instructions how to start allowing models, see Allowing Your First Model.
To allow additional models, the same instructions can be followed.

📘
Note
When allowing models, if the model provider is already associated with the project (meaning that another model from the same provider is associated with the project), the connection is already set up and does not need to be re-selected.

Managing External APIs

For external APIs, the AI Catalog provides a secure gateway that centralizes access:

Instead of scattering API keys, you manage secure connections governed by JFrog's permission model.
After model access has been allowed for a specific project, all traffic is tracked and audited.
This gives you full visibility and control over usage and performance in real time.

Handling Model Packages

For model packages, the AI Catalog streamlines the path to production:

You can enforce granular, policy-based controls to create allow-lists.
This ensures developers only use models that are vetted and compliant.

Searching and Filtering AI Models

In order to help you find the best model for your project in the AI Catalog, in the Discovery page you can search for and filter models by:

Free text: Enter the search term in the search bar. Click enter and either select the required asset or click "Show all results for "xxx". The filter panel on the left opens for further filtering.
Status: In the filter pane, Select to display allowed and or live models.
Model type: Select a specific model type to display. Options: All/Custom/External/Package.

The filters selected are shown across the top of the models, and the search text remains in the free text box in the Filters panel:

Click Clear all to remove all filters.

Allow Your First Model

❗️
Important
Only Admin users have permission to allow models.

The AI Catalog provides access to thousands of models. This guide outlines the straightforward process for exploring and evaluating a diverse range of AI models, helping you identify and allow the most suitable options for your projects.

Select a model:
1. From the JFrog platform menu, select AI/ML > Discovery. The Models Discovery page opens. (If you are selecting your first model, the Registry page is empty.)
2. Browse through the catalog to find the model you want. You can search and filter to locate a specific model or model type.
3. Click the model you wish to allow. The model details are displayed. To enable your developers to use this model, assign it to a project, connect it (for external models), and allow it.
4. Browse through the catalog to find the model you want. You can search and filter to locate a specific model or model type.
5. Click the model you wish to allow. The model details are displayed. To enable your developers to use this model, assign it to a project, connect it (for external models), and allow it.
Select the project and configure model allowance:
1. In the model's detail page, click as follows:
  - For External models: Click Connect & allow
  - For Model packages: Click Allow

In the Allow Model Usage pane, select the project from the drop-down list.

Select Project for an External Model

Select Project for a Model Package

Based on your model type, perform the required configuration and complete the approval (allowance):
- For Model Packages only: Click Allow. The Allowed models tab is displayed.
- For External API Models only: First create a new connection¹² for the project, and then click Allow.
To Use the Model: See instructions how to Use Models in Your Code.

📘
Note
You can create a connection without currently allowing the project if you want.

¹ Connections are per provider per project. For more info, see Connect AI Providers.

² When allowing a model for which a connection is already set up between the project and the model provider, you do not need to define a new connection.