Skip to main content

Creating and Distributing an AI Provider

This page describes the steps for administrators who will be deploying and managing Agentiqs in their organization.


Creating an AI Provider

This section describes the steps for creating an AI provider.

Procedure
  1. Click [Settings] > [AI Providers] > [Add Provider].
    • The [Add AI Provider] dialog box will appear.
  2. Select the AI ​​provider you want to use.
    • The selected provider will be added to the list.
  3. Click [Edit] next to the provider in the list.
    • The [Edit AI Provider] dialog box will appear.
  4. Select [API Settings] and fill in the required fields.
  5. Run [Test Connection] to verify the connection.
    • If the connection is successful, you will be notified.
      (If the connection fails,Proxy Settings see below.)
  6. Click [Update] to save.
About Test Connection Results
  • Running [Test Connection] on the [Model Settings] tab will show the connection status for each added model.
    • Please confirm that the models you plan to use are successful.
    • Deleting models you do not plan to use will streamline your options and reduce operational errors.
  • If the displayed model or connection results differ from what you expected, please review whether the entered settings (API key/endpoint URL/model ID) are correct.
AI Provider Settings
  • You can add the latest AI model from [AI Provider Details] > [Model Settings] > [Add Model].
  • You can set the following usage restrictions from [AI Provider Details] > [Usage Restrictions].
    • Expiration Date
    • Monthly Cost (per user)
About Monthly Cost (per user) Restrictions
  • Monthly cost restrictions are determined based on estimated usage fees. For actual billing amounts and the latest pricing information, please check the official information of the AI ​​provider you are using.

  • For information on how to check estimated usage fees, please refer to User Guide > Checking AI Model Usage Fees.

Confirming configuration values

Configuration values such as API keys, endpoint URLs, and model IDs are obtained differently for each AI provider.
Examples for representative providers are shown below. For the latest information and details, always refer to the official documentation of each provider.

ModelWhere to obtain API key / endpoint(Reference) Model ID
Azure OpenAIOpen the Azure OpenAI resource in the Azure Portal and obtain the API key and endpoint URL from the "Keys and Endpoint" page.
OpenAISign in to the OpenAI platform and obtain an API key from the "API keys" page.
Google GeminiSign in to Google AI Studio and generate an API key for your project.
Microsoft Azure AI FoundryCreate a project in the Azure Portal or the AI Foundry portal and create an API key from the "Keys and Endpoint" section on the Overview page.

AI provider settings

This section explains how to configure an AI provider you have added.
On the AI provider settings screen (figure ① below), open the edit dialog for the target AI provider and click [Edit](②).

Steps
  • You can add the latest AI models from [Model settings] > [Add model].
  • From [AI provider details] > [Usage limits], you can set the following usage limits:
    • Expiration date
    • Monthly cost (per user)
If model pricing is not configured, it will not be reflected in "AI model usage costs".

Open the model settings dialog from the red-framed area below and set the "Input cost" and "Output cost" on the [Pricing] tab.

 → 

Distributing the AI ​​Provider

This section explains how to distribute the AI ​​provider you created.

Procedure
  1. Click [Settings] > [Sharing] > [Share settings] > [Export].
    • The [Export settings] dialog box will appear.
  2. Enable the [System] checkbox.
    • The [AI Provider] and [Proxy] checkboxes will be automatically enabled.
  3. Enter a passkey of your choice and click [Generate Export Data].
    • The passkeyandexport data will be generated and displayed on the screen.
  4. Click [Download] to save the export data as a file.
  5. Distribute the saved export datafile andpasskey to the users.
  6. Have the users import the data following the instructions in User Guide > Setting up the AI ​​Provider.
Regarding Distribution to Users
  • For security reasons, it is recommended to distribute the passkeyandexport data using different methods.
  • It is recommended to enable [Make AI Provider Read-Only] in the [Export Settings] dialog.
    Enabling this setting prevents users from changing settings such as usage restrictions at the import destination, allowing the settings distributed by the administrator to be maintained.