Supported LLM: Azure OpenAI? about chat-llamaindex HOT 3 OPEN

Chat LlamaIndex can use any LLM that is supported by LlamaIndexTS, you just have to plug it in here:

from chat-llamaindex.

Chat LlamaIndex can use any LLM that is supported by LlamaIndexTS, you just have to plug it in here:

chat-llamaindex/app/api/llm/route.ts

Lines 149 to 154 in 86aca07

	const llm = new OpenAI({
	model: config.model,
	temperature: config.temperature,
	topP: config.topP,
	maxTokens: config.maxTokens,
	});

Hi,
Below are the config I have added as asked:
azure: {
apiKey: "xxxxxxxxx",
endpoint: "https://azureopenaillamaindex.openai.azure.com/openai/deployments/gpt-35-turbo/chat/completions?api-version=2023-07-01-preview",
apiVersion: "2023-07-01-preview",
deploymentName:"gpt-35-turbo" ,
}

And I am getting below error:

[LlamaIndex] BadRequestError: 400 Unsupported data type

   at APIError.generate (C:\LAAMA\chat-llamaindex\node_modules\openai\error.js:43:20)
   at AzureOpenAI.makeStatusError (C:\LAAMA\chat-llamaindex\node_modules\openai\core.js:252:33)
   at AzureOpenAI.makeRequest (C:\LAAMA\chat-llamaindex\node_modules\openai\core.js:293:30)
   at process.processTicksAndRejections (node:internal/process/task_queues:95:5) {
status: 400,
headers: {
   'apim-request-id': 'df10be42-1577-481f-b65e-d1abb4f43bc9',
   'content-length': '22',
   'content-type': 'text/plain; charset=utf-8',
   date: 'Tue, 19 Dec 2023 07:14:23 GMT',
   'ms-azureml-model-error-reason': 'model_error',
   'ms-azureml-model-error-statuscode': '400',
   'strict-transport-security': 'max-age=31536000; includeSubDomains; preload',
   'x-content-type-options': 'nosniff',
   'x-ms-client-request-id': 'df10be42-1577-481f-b65e-d1abb4f43bc9',
   'x-ms-region': 'East US',
   'x-ratelimit-remaining-requests': '119',
   'x-ratelimit-remaining-tokens': '119984',
   'x-request-id': '23112d7f-5f0f-4d28-8673-a45c99c69cd3'
},
error: undefined,
code: undefined,
param: undefined,
type: undefined

And on UI it shows:

Can you please help me suspecting what could be the issue.

from chat-llamaindex.

Sorry, currently we're not having an azure example. I would start using this example https://github.com/run-llama/LlamaIndexTS/blob/main/examples/openai.ts and modify the parameters

from chat-llamaindex.