You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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?
The text was updated successfully, but these errors were encountered:
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.
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?
The text was updated successfully, but these errors were encountered: