See Model Configuration for a full list of available model properties.

Overview

Use the procedure outlined below to configure and use Azure OpenAI services in Profound AI.

Steps

Go to https://portal.azure.com and sign in.
Search and select the Azure OpenAI service.
Click Create a Resource and follow the steps to create the resource.
Go to the resource you created and select Keys and Endpoint.
1. Copy those items into the config.js file as endpoint and apiKey properties of your model.
2. Alternatively, instead of the endpoint property, you can also set the resource property based on the resource name you chose.
  1. With this property set, the endpoint will be constructed automatically.
3. Set the provider property to openai.
4. Set the cloud property to azure.
Go to Manage Deployments.
Select Create Deployment.
Select desired model and model version and give it a name. Supply this name as the model property in the config.js file.
1. Ensure the model and version you select supports function calling.
2. It may take a few minutes before the model is fully deployed and you are ready to try it.

Example

The example below shows a sample configuration for the azure-gpt-35-0613 model:

models: {
  "Azure OpenAI GPT-3.5": {
    provider: "openai",
    cloud: "azure",
    model: "azure-gpt-35-0613",
    resource: "profound-openai",
    apiKey: "......",
    apiVersion: "2023-12-01-preview"
  }
}

Azure (Azure OpenAI) Models

Overview

Steps

Example