Need some clarification on IntegratedVectorizerStrategy and Indexer

[sudheer05071996]

Hi @pamelafox , @srbalakr

Previously I am using Azure Document intelligence and Sentence Text splitter(prepdocs.py file- setup_list_file_strategy method) for reading the data and converting it into chunks and embeddings. It is taking huge amount of time for indexing data.

I can see IntegratedVectorizerStrategy( https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/app/backend/prepdocslib/integratedvectorizerstrategy.py) file in the updated Repo which will serves the same purpose with the help of Skillsets and Indexer.

I would like to know what is the exact difference between them and does the latest IntegratedVectorizerStrategy approach will consume less time for indexing purpose or does it have any other advantages compared to previous approach . Which approach has more benefits and does the usage of both approaches depends on any particular things.

Thankyou so much

[sudheer05071996]

Hi @pamelafox , @srbalakr

Can you please clarify this.

[christ25442544]

The integrated vectorization can help you run the indexer without needing to keep the prepdocs script open all day. You can simply hit the run button and carry on with your other tasks. This strategy is particularly beneficial when dealing with a large volume of data.

[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