Azure OpenAI
Chat model
We recommend configuring GPT-4o as your chat model.
"models": [{
"title": "GPT-4o",
"provider": "azure",
"model": "gpt-4o",
"apiBase": "<YOUR_DEPLOYMENT_BASE>",
"engine": "<YOUR_ENGINE>",
"apiVersion": "<YOUR_API_VERSION>",
"apiType": "azure",
"apiKey": "<MY_API_KEY>"
}]
Autocomplete model
We recommend configuring Codestral as your autocomplete model.
"tabAutocompleteModel": [{
"title": "Codestral",
"provider": "azure",
"model": "codestral-latest",
"apiBase": "<YOUR_DEPLOYMENT_BASE>",
"engine": "<YOUR_ENGINE>",
"apiVersion": "<YOUR_API_VERSION>",
"apiType": "azure",
"apiKey": "<MY_API_KEY>"
}]
Embeddings model
We recommend configuring text-embedding-3-large as your embeddings model.
"embeddingsProvider": [{
"provider": "azure",
"model": "text-embedding-3-large",
"apiBase": "<YOUR_DEPLOYMENT_BASE>",
"engine": "<YOUR_ENGINE>",
"apiVersion": "<YOUR_API_VERSION>",
"apiType": "azure",
"apiKey": "<MY_API_KEY>"
}]
Reranking model
Azure OpenAI currently does not offer any reranking models.
Click here to see a list of reranking models.
Privacy
If you'd like to use OpenAI models but are concerned about privacy, you can use the Azure OpenAI service, which is GDPR and HIPAA compliant.
You need to apply for access to the Azure OpenAI service. Response times are typically within a few days.
General model configuration
Azure OpenAI requires a handful of additional parameters to be configured, such as a model engine and API version.
To find this information in Azure AI Studio, first select the model that you would like to connect. Then visit Endpoint > Target URI.
For example, a Target URI of <https://just-an-example.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2023-03-15-preview>
would map to the following:
{
"title": "GPT-4o Azure",
"model": "gpt-4o",
"provider": "azure",
"apiBase": "https://just-an-example.openai.azure.com",
"apiType": "azure",
"engine": "gpt-4o",
"apiVersion": "2023-03-15-preview",
"apiKey": "<MY_API_KEY>"
}