Skip to main content

Azure OpenAI

Requisites​

To use Azure OpenAI models, you need to have the following credential information. You can get them by signing up at Azure OpenAI's website.

Required credentials:

  • AZURE_OPENAI_RESOURCE_NAME: The name of your Azure OpenAI Resource.
  • AZURE_OPENAI_DEPLOYMENT_ID: The deployment name you chose when you deployed the model.
  • AZURE_OPENAI_API_KEY: Your Azure OpenAI API Key for authentication.

Optional credentials:

  • AZURE_OPENAI_API_VERSION: The Azure API version follows the YYYY-MM-DD format.

Supported Models:​

All models provided by Anthropic has the following properties:

  • Function call: Supported
  • Streaming: Supported

All models accept the following extra configs when generating texts:

  • temperature
  • top_p
  • max_tokens
  • stop

GPT 3.5 Series​

GPT-3.5 models can understand and generate natural language or code. The most capable and cost effective model in the GPT-3.5 family is GPT-3.5 Turbo, which has been optimized for chat and works well for traditional completions tasks as well.

GPT-3.5 Turbo​

  • Model schema id: azure_openai/gpt-3.5-turbo
  • Input token limit: 16385
  • Output token limit: 4096

GPT-3.5 Turbo 16k​

  • Model schema id: azure_openai/gpt-3.5-turbo-16k
  • Input token limit: 16385
  • Output token limit: 4096

GPT-4 Series​

GPT-4 can solve difficult problems with greater accuracy than any of OpenAI's previous models. Like GPT-3.5 Turbo, GPT-4 is optimized for chat and works well for traditional completions tasks.

GPT-4​

  • Model schema id: azure_openai/gpt-4
  • Input token limit: 8192
  • Output token limit: 4096

GPT-4 32K​

  • Model schema id: azure_openai/gpt-4-32k
  • Input token limit: 32768
  • Output token limit: 4096