milvus + azure openai

At a glance

The community member is trying to follow the Milvus tutorial but is using Azure OpenAI instead of OpenAI. The code is trying to connect to OpenAI during the embedding step, which is causing an authentication error. The community members suggest that the issue is likely due to the default service context being set to OpenAI, and that the community member should configure the service context for Azure OpenAI. After trying this, the community members confirm that this resolved the issue. However, they note that the Azure OpenAI embedding model seems to be problematic, and they recommend using a local embedding model instead.

Useful resources

tthoraxe

i'm trying to follow the Milvus tutorial but I am using Azure OpenAI and not OpenAI, but it keeps trying to talk to OpenAI during the embedding step:

Plain Text

Retrying llama_index.embeddings.openai.base.get_embeddings in 0.275948059787665 seconds as it raised AuthenticationError: Error code: 401 - {'error': {'message': 'Incorrect API key provided: xxx. You can find your API key at https://platform.openai.com/account/api-keys.', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_api_key'}}.

7 comments

tthoraxe

ohh i probably have to configure the service context

tthoraxe

bc the default is likely openai when not configured

tthoraxe

trying that now

tthoraxe

that seems like it was the issue

tthoraxe

ok, interesting. it specifically is related to the embed_model setting (or lack thereof). looks like azure openai embed is a hot mess. will use local for now

tthoraxe

sorry for the noise!

LLogan M

Yea with azure, I really recommend setting a global service context

Its a little more straight forward in v0.10.x, you can explicitly pass in the embedding model for certain steps, and more easily set a global default

Add a reply

Find answers from the community

milvus + azure openai