`OpenAIClient` and `AssistantsClient` are constructed similarly as follows:

Original code:

import { OpenAIClient } from "@azure/openai";

const endpoint = "Your Azure OpenAI resource endpoint";

On the other hand, the `AzureOpenAI` client is constructed as follows:

Migrated code:

import { AzureOpenAI } from "openai";

const deployment = "Your Azure OpenAI deployment";

The following example shows how to migrate the `getChatCompletions` method call.

Original code:

const result = await client.getChatCompletions(deploymentName, messages, { maxTokens: 100 });

Migrated code:

const result = await client.chat.completions.create({ messages, model: '', max_tokens: 100 });

Notice the following:

- The `getChatCompletions` method has been replaced with the `chat.completions.create` method

- The `messages` parameter is now passed in the options object with the `messages` property

- The `maxTokens` property has been renamed to `max_tokens` and the `deploymentName` parameter has been removed. Generally, the names of the properties in the `options` object are the same as in the Azure OpenAI service API, following the snake case convention instead of the camel case convention used in the `AssistantsClient`. This is true for all the properties across all requests and responses in the `AzureOpenAI` client

The following example shows how to migrate the `streamChatCompletions` method call.

Original code:

const stream = await client.streamChatCompletions(deploymentName, messages, { maxTokens: 100 });

Migrated code:

const stream = await client.chat.completions.create({ model: '', messages, max_tokens: 100, stream: true });

The following example shows how to migrate a `getChatCompletions` method call that enables Azure On Your Data with Azure Search.

Original code:

const azureSearchEndpoint = "Your Azure Search resource endpoint";

const azureSearchIndexName = "Your Azure Search index name";

Migrated code:

import "@azure/openai/types";

Notice that:

- The `azureExtensionOptions` property has been replaced with the inner `data_sources` property

- The `parameters` property has been added to wrap the parameters of the extension, which mirrors the schema of the Azure OpenAI service API

- camel case properties have been replaced with snake case properties

The following example shows how to migrate the `getAudioTranscription` method call.

Original code:

import { readFile } from "fs/promises";

Migrated code:

import { createReadStream } from "fs";

Notice that:

- The `getAudioTranscription` method has been replaced with the `audio.transcriptions.create` method

- The `AzureOpenAI` has to be constructed with the `deployment` option set to the deployment name in order to use audio operations such as `audio.transcriptions.create`

- The `model` property is required to be set in the options object but its value is not used in the operation so feel free to set it to any value

The following example shows how to migrate the `getAudioTranslation` method call.

Original code:

import { readFile } from "fs/promises";

Migrated code:

import { createReadStream } from "fs";

Notice that:

- The `getAudioTranslation` method has been replaced with the `audio.translations.create` method

- All other changes are the same as in the audio transcription example

Original code:

const options = {

model: azureOpenAIDeployment,

Migrated code:

const options = ...;

const assistantResponse = await assistantsClient.beta.assistants.create(

Notice that:

- The `createAssistant` method has been replaced with the `beta.assistants.create` method

The following example shows how to migrate the `createThread` method call.

Original code:

const assistantThread = await assistantsClient.createThread();

Migration code:

const assistantThread = await assistantsClient.beta.threads.create();

Notice that:

- The `createThread` method has been replaced with the `beta.threads.create` method

The following example shows how to migrate the `createMessage` method call.

Original code:

const threadResponse = await assistantsClient.createMessage(

assistantThread.id,

Migration code:

const threadResponse = await assistantsClient.beta.threads.messages.create(

assistantThread.id,

Notice that:

- The `createMessage` method has been replaced with the `beta.threads.messages.create` method

- The message specification has been moved from a parameter list to an options object

To run an assistant on a thread, the `createRun` method is used to create a run and then a loop is used to poll the run status until it is in a terminal state. The following example shows how to migrate the run creation and polling.

Original code:

let runResponse = await assistantsClient.createRun(assistantThread.id, {

assistantId: assistantResponse.id,

const runResponse = await assistantsClient.beta.threads.runs.createAndPoll(

assistantThread.id,

- The `createRun` method has been replaced with the `beta.threads.runs.create` and `createAndPoll` methods

for (const runMessageDatum of runMessages.data) {

for (const item of runMessageDatum.content) {

Pages can be looped through by using the `for await` loop.

for await (const runMessageDatum of runMessages) {

for (const item of runMessageDatum.content) {

const embeddings = await client.getEmbeddings(deploymentName, input);

const embeddings = await client.embeddings.create({ input, model: '' });

- The `getEmbeddings` method has been replaced with the `embeddings.create` method

const results = await client.getImages(deploymentName, prompt, { n, size });

const results = await client.images.generate({ prompt, model: '', n, size });

- The `getImages` method has been replaced with the `images.generate` method

const results = await client.getChatCompletions(deploymentName, messages);

for (const choice of results.choices) {

...

}

However `AzureOpenAI` does not have a direct equivalent to the `contentFilterResults` property in the `ChatCompletion.Choice` interface. The content filter results can be accessed by importing `"@azure/openai/types"` and accessing the `content_filter_results` property.

import "@azure/openai/types";

| `ChatChoice` | `ChatCompletion.Choice` | Interface | |

"dist/",

"CHANGELOG.md",

"LICENSE",

"README.md"

],

"tshy": {