Skip to content

How to use keyless auth (managed identity) for AzureOpenAIVectorizerParameters in integrated vectorization notebook? #319

@Pavan-Microsoft

Description

@Pavan-Microsoft

Hi team,

I'm trying to use the notebook at:

azure-search-integrated-vectorization-sample.ipynb

In the vector search configuration section, the AzureOpenAIVectorizerParameters currently requires an api_key:

# Configure the vector search configuration vector_search = VectorSearch( algorithms=[ HnswAlgorithmConfiguration(name="myHnsw"), ], profiles=[ VectorSearchProfile( name="myHnswProfile", algorithm_configuration_name="myHnsw", vectorizer_name="myOpenAI", ) ], vectorizers=[ AzureOpenAIVectorizer( vectorizer_name="myOpenAI", kind="azureOpenAI", parameters=AzureOpenAIVectorizerParameters( resource_url=azure_openai_endpoint, deployment_name=azure_openai_embedding_deployment, model_name=azure_openai_model_name, api_key=azure_openai_key, ), ), ], )

Is there currently a way to use keyless authentication (e.g., system-assigned managed identity) instead of providing an api_key in AzureOpenAIVectorizerParameters?

If not:
Is this a planned feature?
Is there a recommended workaround for now?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions