error while using AzureOpenAIEmbeddingSkill for integrated vectorization

[aradhanachaturvedi]

I am trying to use integrated vector approach to chunk and store data and vectors in Azure AI search. I am able to use Text.SplitSkill successfully. However when I am trying to use AzureOpenAIEmbeddingSkill it creates an issue.

it gives following error -

Web Api response status: 'Forbidden', Web Api response details: '{"error":{"code":"403","message": "Access denied due to Virtual Network/Firewall rules."}}'

I have already embedding models deployed using Azure OpenAI. I am using it to generate embeddings manually. so access shouldn't be an issue .

I also tried to perform integrated vectorization through portal too ,but in portal I am getting some weird error.

But in portal when I am trying to use same model for integrated vectorized approach I get this issue. Attached is the screenshot.

1>Can you kindly let me know what can we do to avoid this issue . do we need to redeploy our models? 2>Will this TextSplit skill work with json documents too?or limited to pdfs?

[tonybaloney]

CC @mattgotteiner