Share via

Unable to find created/deployed model in "completions"

Shinal K 20 Reputation points
2024-09-13T06:01:19.67+00:00

Hi Team,

I'm new here and i need a small help regarding the MS Azure OpenAI, in order to use OpenAI services for one of the API poc. I have created a openAI resourse group and created a openAI service as well, in order to use the chat completion i have created a deployment model and the created/deployed model is not showing up on the completion dropdown, but it's available and showing up on the deployed models.

how to resolve this issue ? or am i missing anything? i have used GPT-4-0 mini and gpt-35-turbo16k as well both are not listing out.

thanks in advance

Azure OpenAI Service
Azure OpenAI Service
An Azure service that provides access to OpenAI’s GPT-3 models with enterprise capabilities.
3,291 questions
Microsoft Configuration Manager Deployment
Microsoft Configuration Manager Deployment
Microsoft Configuration Manager: An integrated solution for for managing large groups of personal computers and servers.Deployment: The process of delivering, assembling, and maintaining a particular version of a software system at a site.
996 questions
Accepted answer
  1. AshokPeddakotla-MSFT 35,091 Reputation points
    2024-09-13T09:36:24.5966667+00:00

    Shinal K Please see below information for more details.

    You are not seeing the deployed models in the drop down as gpt-35-turbo-16k (0613) only supports Chat Completions API. Please refer to the documentation for details around different models.

    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 is available for use with the Chat Completions API. GPT-3.5 Turbo Instruct has similar capabilities to text-davinci-003 using the Completions API instead of the Chat Completions API. We recommend using GPT-3.5 Turbo and GPT-3.5 Turbo Instruct over legacy GPT-3.5 and GPT-3 models.

    Also, future versions of gpt-35-turbo will only be made available in the /chat/completions API. Please refer to the code to use this model for ChatCompletions API.

    Unless you have a specific use case that requires the completions endpoint, we recommend instead using the chat completions endpoint which allows you to take advantage of the latest models like GPT-4o, GPT-4o mini, and GPT-4 Turbo.

    I deployed gpt-35-turbo-instruct (0914) model and able to see it under completions.

    User's image

    User's image

    User's image

    Please let me know if you have any other questions.

    If the response helped, please do click Accept Answer and Yes for was this answer helpful.

    1 person found this answer helpful.

0 additional answers

Sort by: Most helpful
Most helpful Newest Oldest

Your answer

Answers can be marked as Accepted Answers by the question author, which helps users to know the answer solved the author's problem.