Still facing the AZURE embedding issue

[shagu2021]

git log
commit 2911989

i still see the auth error when i use AZURE and embeddings
AuthenticationError: No API key provided. You can set your API key in code using 'openai.api_key = ', or you can set the environment variable OPENAI_API_KEY=). If your API
key is stored in a file, you can point the openai module at it with 'openai.api_key_path = '. You can generate API keys in the OpenAI web interface. See

following is my command

MemGPT > memgpt --archival-storage-files-compute-embeddings="*.pdf" --persona=memgpt_doc --human=basic --use-azure-openai

[s-spillias]

similar issue: I have defined the new 'AZURE_OPENAI_EMBEDDING_DEPLOYMENT' variable using our deployment name for embedgginds. But it looks like it is trying to reach this through the gpt4 endpoint, whereas, we have a different endpoint for embeddings.

The specific error is:
InvalidRequestError: The API deployment for this resource does not exist. If you created the deployment within the last
5 minutes, please wait a moment and try again.

[cpacker]

@vivi I think this is because of a typo here: https://github.com/cpacker/MemGPT/blob/main/memgpt/openai_tools.py#L150

Patching now, will link the PR.

[vivi]

Define AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT. (EMBEDDINGS -- see README).

The patch we pushed makes everything consistent (to use AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT) now.