Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

When using Azure Custom variable, the index didn't get created via script. #2361

Open
Keatnuxsuo opened this issue Feb 14, 2025 · 1 comment

Comments

@Keatnuxsuo
Copy link

When using Azure Custom variable and custom endpoint (frontdoor URL), the index didn't get created via script; hence, failed and gave error: "Error in Vectorizer" when running prepdocs.py

We later found out that the cause is from index not being created via the script so when we create an index manually inside of Azure Search Service, azd up works.

For the future deployment, how do we make sure that the script works automatically without doing anything manual?

Image
@pamelafox
Copy link
Collaborator

To clarify, your Azure OpenAI endpoint has a custom endpoint? I don't think we've tested that combination of integrated vectorization and custom OpenAI endpoints.

The relevant code is in searchmanager.py:

AzureOpenAIVectorizer(
    vectorizer_name=f"{self.search_info.index_name}-vectorizer",
    parameters=AzureOpenAIVectorizerParameters(
        resource_url=self.embeddings.open_ai_endpoint,
        deployment_name=self.embeddings.open_ai_deployment,
        model_name=self.embeddings.open_ai_model_name,
    ),
)```

Can you print `self.embeddings.open_ai_endpoint` and see what its value is? I'm curious if its an actual value, and AI search doesn't like it, or if its an empty string.


Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants