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

[pamelafox]

I am closing this issue since we are deprecating the previous integrated vectorization feature.
We have made a custom skillset that runs our own code instead, mirroring the local ingestion in Azure Functions. We recommend the new skillset approach for maximal compatibility with the repo features.
Please try it out and raise any issues you run into. Thanks!
https://github.com/Azure-Samples/azure-search-openai-demo/releases/tag/2025-11-12