Is this package works with AzureOpenAI?

[mraguth]

Please share llm and text_embedder configurations along with import settings please?

In our corporation, we use Azure OpenAI and love to explore.

[mraguth]

I am able to configure and working for me now :-)

[jgbradley1]

Azure OpenAI is supported. With Azure OpenAI specifically, there are two authentication options. You can provide an API key or if you leave the API key out of your configuration file, graphrag will fallback and attempt to use managed identity if you have it setup on your system.

[ghost]

Hi @jgbradley1 ,

Can you help me to configure by giving sample file..
what is organization parameter. is it api key for the organization?

encoding_model: cl100k_base
skip_workflows: []
llm:
----# api_key: ${GRAPHRAG_API_KEY}
type: azure_openai_chat
model: gpt-35-turbo-16k
model_supports_json: false # recommended if this is available for your model.
----# max_tokens: 4000
---- # request_timeout: 180.0
api_base: https://xxxxx.openai.azure.com/
api_version: 2024-02-15-preview
organization: 893xxxxxc675e2
deployment_name: gpt-35-turbo-16k

-------------Received ERROR ---------------
File "C:\Users\vijay.r\anaconda\envs\ragagent\lib\site-packages\openai\_base_client.py", line 1514, in request\n return await self._request(\n File "C:\Users\vijay.r\anaconda\envs\ragagent\lib\site-packages\openai\_base_client.py", line 1610, in _request\n raise self._make_status_error_from_response(err.response) from None\nopenai.AuthenticationError: Error code: 401 - {'statusCode': 401, 'message': 'Unauthorized. Access token is missing, invalid, audience is incorrect (https://cognitiveservices.azure.com), or have expired.