Azure OpenAI Assistants - assistantsClient.createMessage returns 500

[diberry]

• Package Name: @azure/openai-assistants
• Package Version: ^1.0.0-beta.5
• Operating system: Codespaces/linux
• [ X] nodejs
  • version: Node.js v18.16.0
• [ ] browser
  • name/version:
• [ x ] typescript
  • version: ^5.4.3
• Is the bug related to documentation in
  • [ ] README.md
  • [ ] source code documentation
  • [ ] SDK API docs on https://docs.microsoft.com

Describe the bug Code correctly creates assistant and thread but returns 500 on create message

To Reproduce Steps to reproduce the behavior:

1. Create deployments

1. Create .env with following (use your own key and endpoint)

AZURE_OPENAI_MODEL_ID=gpt-35-turbo-1106
AZURE_OPENAI_KEY=b8f...
AZURE_OPENAI_RESOURCE=diberry-openai-swedencentral
AZURE_OPENAI_ENDPOINT=https://diberry-openai-swedencentral.openai.azure.com/

I assume the model id of gpt-35-turbo-1106 is a concatenation of the model name and model version from the screenshot and not the deployment name.

1. Use following code, build and run.

import { AssistantsClient, AssistantCreationOptions, MessageRole, CodeInterpreterToolDefinition, ToolDefinition } from "@azure/openai-assistants";
import { AzureKeyCredential } from "@azure/core-auth";

import 'dotenv/config'

const azureOpenAIKey = process.env.AZURE_OPENAI_KEY as string;
const azureOpenAIEndpoint = process.env.AZURE_OPENAI_ENDPOINT as string;
const azureOpenAIModelId = process.env.AZURE_OPENAI_MODEL_ID as string;

if (!azureOpenAIKey || !azureOpenAIEndpoint) {
  throw new Error(
    "Please ensure to set AZURE_OPENAI_KEY and AZURE_OPENAI_ENDPOINT in your environment variables."
  );
}

const assistantsClient = new AssistantsClient(azureOpenAIEndpoint, new AzureKeyCredential(azureOpenAIKey));

//"gpt-35-turbo-1106",
//"gpt-35-turbo-instruct-0914",
const options: AssistantCreationOptions = {
  model: azureOpenAIModelId,
  name: "Math Tutor",
  instructions: "You are a personal math tutor. Write and run JavaScript code to answer math questions.",
  tools: [{ type: "code_interpreter" } as ToolDefinition],
};

// Create an assistant
const assistantResponse = await assistantsClient.createAssistant(options);
console.log(`Assistant created: ${JSON.stringify(assistantResponse)}`);

// Create a thread
const assistantThread = await assistantsClient.createThread({});
console.log(`Thread created: ${JSON.stringify(assistantThread)}`);

// Add a user question to the thread
const threadResponse = await assistantsClient.createMessage(assistantThread.id, "user", "What is 3x + 11 = 14?");
console.log(`Message created:  ${JSON.stringify(threadResponse)}`);

// Run the thread
let runResponse = await assistantsClient.createRun(
  assistantThread.id,
  {
    assistantId: assistantResponse.id
  }
);
console.log(`Run created:  ${JSON.stringify(runResponse)}`);

// Wait for the assistant to respond
do {
  await new Promise((r) => setTimeout(r, 500));
  runResponse = await assistantsClient.getRun(assistantThread.id, runResponse.id);
} while (runResponse.status === "queued" || runResponse.status === "in_progress");

// Get the messages
const runMessages = await assistantsClient.listMessages(assistantThread.id);
for (const runMessageDatum of runMessages.data) {
  for (const item of runMessageDatum.content) {
    if (item.type === "text") {
      console.log(`Message content: ${JSON.stringify(item.text?.value)}`);
    }
  }
}

1. Get response such as

@diberry ➜ /workspaces/azure-typescript-e2e-apps/quickstarts/azure-openai-assistants (dfberry/azure-openai-assistants) $ npm run start

> azure-openai-assistants@1.0.0 start
> node dist/index.js

Assistant created: {"id":"asst_dyBhrIKCUKgWGvKY4O7U2XEZ","createdAt":"2024-04-08T17:39:49.000Z","name":"Math Tutor","description":null,"model":"gpt-35-turbo-1106","instructions":"You are a personal math tutor. Write and run JavaScript code to answer math questions.","tools":[{"type":"code_interpreter"}],"fileIds":[],"metadata":{}}
Thread created: {"id":"thread_m5DRrVS4AGTwIdYYULmDNO7h","createdAt":"2024-04-08T17:39:49.000Z","metadata":{}}
Message created:  {"id":"msg_MaiXA4hHmjP0mXT8K4LR6Gtv","createdAt":"2024-04-08T17:39:50.000Z","threadId":"thread_m5DRrVS4AGTwIdYYULmDNO7h","role":"user","content":[{"type":"text","text":{"value":"What is 3x + 11 = 14?","annotations":[]},"imageFile":{}}],"assistantId":null,"runId":null,"fileIds":[],"metadata":{}}
file:///workspaces/azure-typescript-e2e-apps/quickstarts/azure-openai-assistants/node_modules/@azure-rest/core-client/dist/esm/restError.js:10
    return new RestError(message, {
           ^

RestError: The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at oai-support@microsoft.com if you keep seeing this error. (Please include the request ID 41b61e8e-0b5e-4821-8958-4c02c08622c7 in your email.)
    at createRestError (file:///workspaces/azure-typescript-e2e-apps/quickstarts/azure-openai-assistants/node_modules/@azure-rest/core-client/dist/esm/restError.js:10:12)
    at _createRunDeserialize (file:///workspaces/azure-typescript-e2e-apps/quickstarts/azure-openai-assistants/node_modules/@azure/openai-assistants/dist-esm/src/api/operations.js:501:15)
    at createRun (file:///workspaces/azure-typescript-e2e-apps/quickstarts/azure-openai-assistants/node_modules/@azure/openai-assistants/dist-esm/src/api/operations.js:342:12)
    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
    at async file:///workspaces/azure-typescript-e2e-apps/quickstarts/azure-openai-assistants/dist/index.js:29:19 {
  code: null,
  statusCode: 500,
  request: PipelineRequestImpl {
    url: 'https://diberry-openai-swedencentral.openai.azure.com/openai/threads/thread_m5DRrVS4AGTwIdYYULmDNO7h/runs?api-version=2024-02-15-preview',
    method: 'POST',
    headers: HttpHeadersImpl {
      _headersMap: Map(7) {
        'accept' => { name: 'accept', value: 'application/json' },
        'content-type' => {
          name: 'content-type',
          value: 'application/json; charset=UTF-8'
        },
        'accept-encoding' => { name: 'Accept-Encoding', value: 'gzip,deflate' },
        'user-agent' => {
          name: 'User-Agent',
          value: 'azsdk-js-openai-assistants-rest/1.0.0-beta.5 core-rest-pipeline/1.15.1 Node/18.16.0 OS/(x64-Linux-6.2.0-1019-azure)'
        },
        'x-ms-client-request-id' => {
          name: 'x-ms-client-request-id',
          value: '6cc4a56e-283d-4152-9222-2024f42e2212'
        },
        'api-key' => { name: 'api-key', value: 'b8f...' },
        'content-length' => { name: 'Content-Length', value: '48' }
      }
    },
    timeout: 0,
    withCredentials: false,
    body: '{"assistant_id":"asst_dyBhrIKCUKgWGvKY4O7U2XEZ"}',
    multipartBody: undefined,
    formData: undefined,
    streamResponseStatusCodes: undefined,
    enableBrowserStreams: true,
    proxySettings: undefined,
    disableKeepAlive: false,
    abortSignal: undefined,
    requestId: '6cc4a56e-283d-4152-9222-2024f42e2212',
    tracingOptions: undefined,
    allowInsecureConnection: false,
    onUploadProgress: undefined,
    onDownloadProgress: undefined
  },
  response: {
    headers: HttpHeadersImpl {
      _headersMap: Map(9) {
        'content-length' => { name: 'content-length', value: '379' },
        'content-type' => { name: 'content-type', value: 'application/json' },
        'x-request-id' => {
          name: 'x-request-id',
          value: '41b61e8e-0b5e-4821-8958-4c02c08622c7'
        },
        'apim-request-id' => {
          name: 'apim-request-id',
          value: 'feffa411-5d34-478e-866f-7e4141166990'
        },
        'strict-transport-security' => {
          name: 'strict-transport-security',
          value: 'max-age=31536000; includeSubDomains; preload'
        },
        'x-ms-client-request-id' => {
          name: 'x-ms-client-request-id',
          value: '6cc4a56e-283d-4152-9222-2024f42e2212'
        },
        'x-content-type-options' => { name: 'x-content-type-options', value: 'nosniff' },
        'x-ms-region' => { name: 'x-ms-region', value: 'Sweden Central' },
        'date' => { name: 'date', value: 'Mon, 08 Apr 2024 17:39:57 GMT' }
      }
    },
    request: PipelineRequestImpl {
      url: 'https://diberry-openai-swedencentral.openai.azure.com/openai/threads/thread_m5DRrVS4AGTwIdYYULmDNO7h/runs?api-version=2024-02-15-preview',
      method: 'POST',
      headers: HttpHeadersImpl {
        _headersMap: Map(7) {
          'accept' => { name: 'accept', value: 'application/json' },
          'content-type' => {
            name: 'content-type',
            value: 'application/json; charset=UTF-8'
          },
          'accept-encoding' => { name: 'Accept-Encoding', value: 'gzip,deflate' },
          'user-agent' => {
            name: 'User-Agent',
            value: 'azsdk-js-openai-assistants-rest/1.0.0-beta.5 core-rest-pipeline/1.15.1 Node/18.16.0 OS/(x64-Linux-6.2.0-1019-azure)'
          },
          'x-ms-client-request-id' => {
            name: 'x-ms-client-request-id',
            value: '6cc4a56e-283d-4152-9222-2024f42e2212'
          },
          'api-key' => {
            name: 'api-key',
            value: 'b8f...'
          },
          'content-length' => { name: 'Content-Length', value: '48' }
        }
      },
      timeout: 0,
      withCredentials: false,
      body: '{"assistant_id":"asst_dyBhrIKCUKgWGvKY4O7U2XEZ"}',
      multipartBody: undefined,
      formData: undefined,
      streamResponseStatusCodes: undefined,
      enableBrowserStreams: true,
      proxySettings: undefined,
      disableKeepAlive: false,
      abortSignal: undefined,
      requestId: '6cc4a56e-283d-4152-9222-2024f42e2212',
      tracingOptions: undefined,
      allowInsecureConnection: false,
      onUploadProgress: undefined,
      onDownloadProgress: undefined
    },
    status: 500
  },
  details: undefined
}

Expected behavior A clear and concise description of what you expected to happen.

Screenshots If applicable, add screenshots to help explain your problem.

Additional context Add any other context about the problem here.

[diberry]

Wow, I ran it again and it all succeeded. That's surprising.