ContextQMD
Back to Baml

azure-openai

fern/03-reference/baml/clients/providers/azure.mdx

0.222.03.8 KB
Original Source
<Note> If you are using the new Microsoft Foundry (new) portal, please use: [`microsoft-foundry`](microsoft-foundry) instead. </Note>

For azure-openai, we provide a client that can be used to interact with the OpenAI API hosted on Azure using the /chat/completions endpoint.

Example:

baml
client<llm> MyClient {
  provider azure-openai
  options {
    resource_name "my-resource-name"
    deployment_id "my-deployment-id"
    // Alternatively, you can use the base_url field
    // base_url "https://my-resource-name.openai.azure.com/openai/deployments/my-deployment-id"
    api_version "2024-02-01"
    api_key env.AZURE_OPENAI_API_KEY
  }
}
<Warning> `api_version` is required. Azure will return not found if the version is not specified. </Warning>

The options are passed through directly to the API, barring a few. Here's a shorthand of the options:

BAML-specific request options

These unique parameters (aka options) modify the API request sent to the provider.

You can use this to modify the azure api key, base url, and api version for example.

<ParamField path="api_key" type="string"

Will be injected via the header API-KEY. Default: env.AZURE_OPENAI_API_KEY

API-KEY: $api_key </ParamField>

<ParamField path="base_url" type="string"

The base URL for the API. Default: https://${resource_name}.openai.azure.com/openai/deployments/${deployment_id}

May be used instead of resource_name and deployment_id. </ParamField>

<ParamField path="deployment_id" type="string" required

See the base_url field. </ParamField>

<ParamField path="resource_name" type="string" required

See the base_url field. </ParamField>

<ParamField path="api_version" type="string" required> Will be passed via a query parameter `api-version`. </ParamField> <ParamField path="headers" type="object"> Additional headers to send with the request.

Example:

baml
client<llm> MyClient {
  provider azure-openai
  options {
    resource_name "my-resource-name"
    deployment_id "my-deployment-id"
    api_version "2024-02-01"
    api_key env.AZURE_OPENAI_API_KEY
    headers {
      "X-My-Header" "my-value"
    }
  }
}
</ParamField> <Markdown src="/snippets/role-selection.mdx" /> <Markdown src="/snippets/allowed-role-metadata-basic.mdx" /> <Markdown src="/snippets/supports-streaming.mdx" /> <Markdown src="/snippets/finish-reason.mdx" /> <Markdown src="/snippets/client-response-type.mdx" /> <Markdown src="/snippets/media-url-handler.mdx" />

Provider request parameters

These are other options that are passed through to the provider, without modification by BAML. For example if the request has a temperature field, you can define it in the client here so every call has that set.

Consult the specific provider's documentation for more information.

<Warning> For reasoning models (like `o1` or `o1-mini`), you must use `max_completion_tokens` instead of `max_tokens`. Please set `max_tokens` to `null` in order to get this to work.

See the OpenAI API documentation and OpenAI Reasoning Docs for more details about token handling.

Example:

baml
client<llm> AzureO1 {
  provider azure-openai
  options {
    deployment_id "o1-mini"
    max_tokens null
  }
}
</Warning>

<ParamField path="messages" type="DO NOT USE"

BAML will auto construct this field for you from the prompt </ParamField> <ParamField path="stream" type="DO NOT USE"

BAML will auto construct this field for you based on how you call the client in your code </ParamField>

For all other options, see the official Azure API documentation.