openAI doesnt response after deployment in azure server

Forum feedback
,
1

I am using openAPI with node.js. In local, it works and get the answer from completion, but when to deploy on azure server then its giving ‘undefined’ answer. Here is sample code
const prompt = Given the following: ${result1[0].answer}, and the user query: "${query}", give me short concise answer.;

        const completion = await openai.completions.create({
          model: "text-davinci-003",
          prompt: prompt,
          max_tokens: 200,
        });
2

You will need to upgrade your application to use gpt-3.5-turbo. text-davinci-003 is already unavailable for new Azure accounts.

Azure OpenAI Service offers a variety of models for different use cases. The following models are not available for new deployments beginning July 6, 2023. Deployments created prior to July 6, 2023 remain available to customers until July 5, 2024. We recommend customers migrate to the replacement models prior to the July 5, 2024 retirement.

Model summary table and region availability

Region availability is for customers with deployments of the models prior to July 6, 2023.

GPT-3.5 models

Model ID Base model Regions Fine-Tuning Regions Max Request (tokens) Training Data (up to)
text-davinci-002 East US, South Central US, West Europe N/A 4,097 Jun 2021
text-davinci-003 East US, West Europe N/A 4,097 Jun 2021
code-davinci-002 East US, West Europe N/A 8,001 Jun 2021
3

Thank you for your answer, and i have changed the model and redeployed it. But getting nothing, do have to create ‘gpt-3.5-turbo’ model in azure as well?
const prompt = Given the following: ${result1[0].answer}, and the user query: "${query}", give me one line and a short answer;

        const completion = await openai.chat.completions.create({
          model: "gpt-3.5-turbo",
          messages: [
            { role: "user", content: prompt }
          ],
          max_tokens: 50
        });
        
        console.log("OpenAI Answer", completion.choices[0].message.content);
4

Here’s your quickstart guide.

and deployment

You’ll also want to verify the region and model availability when you pull the trigger, as they can change.

Then specify your endpoint.