Microsoft Azure Engine for Azure Openai

Question

I'm currently doing a tutorial which works with OpenAi and Microsoft Azure and I'm now asked to enter my

// PARAMETERS FOR AZURE OPENAI SERVICES CHAT COMPLETION API
const ENGINE = "YOUR_ENGINE_OF_AZURE_OPENAI_SERVICES"; // DEPLOYMENT ID FOR GPT-3.5-TURBO.

I don't know where I get that and where and what I have to deploy. Could someone please help me, thank you.

Tage Tutorial added this note but I don't understand it:

 CHAT COMPLETION (see https://learn.microsoft.com/en-us/azure/cognitive-services/openai/reference#chat-completions)
     *
     * !!! Note: The following action currently supports only non-chat use cases.
     * !!! For chat based use cases the payload of the messages needs to be adjusted (see https://platform.openai.com/docs/guides/chat)
     * !!! Also have a look at the markup lang ChatML of OpenAI https://github.com/openai/openai-python/blob/main/chatml.md
     * ========================
     */

Answer 1

Where do I get that and where and what do I have to deploy?

You can deploy the model from the portal by

Portal -> Azure open-ai -> Model deployments -> Create deployment like below.

Once, it created you can use the below code to create a sample chat completion by following this MS-document.

Code:

const { OpenAIClient, AzureKeyCredential } = require("@azure/openai");
const endpoint ="your-open-ai-endpoint" ;
const azureApiKey = "your open-ai key";

const messages = [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "Does Azure OpenAI support customer managed keys?" },
  { role: "assistant", content: "Yes, customer managed keys are supported by Azure OpenAI" },
  { role: "user", content: "Do other Azure Cognitive Services support this too" },
];

async function main() {
  console.log("== Chat Completions Sample ==");

  const client = new OpenAIClient(endpoint, new AzureKeyCredential(azureApiKey));
  const deploymentId = "deployment1";
  const result = await client.getChatCompletions(deploymentId, messages);

  for (const choice of result.choices) {
    console.log(choice.message);
  }
}

main().catch((err) => {
  console.error("The sample encountered an error:", err);
});

module.exports = { main };

Output:

== Chat Completions Sample ==
{
  role: 'assistant',
  content: 'Yes, many of Azure Cognitive Services support customer managed keys for encryption and decryption of data. This includes services like Azure Text Analytics, Azure Speech Services, Azure Translator Text, and Azure Content Moderator. By using customer managed keys, customers can control access to their encrypted data and protect it from unauthorized access.'
}