Hi @Florian Schlösser ,
welcome to the Microsoft Q&A Platform!
The SharePoint Indexer for Azure Cognitive Search automatically splits documents into chunks based on content type but it doesn’t provide options to customize chunking strategies. You can influence indexing through features like Document Cracking for text extraction, creating a Custom Skillset to preprocess data, and setting Field Data Extraction to limit which data is indexed. Additionally, you can control the maximum file size processed.
For reference you can refer official documentation.
Does Sharepoint Indexer for Azure Search support Alternative chunking methods or configuration parameters?
Dear Team,
i recently discovered the Sharepoint Indexer and it is quite helpful for us to set up an initial prototype. We are thinking of migrating to a custom build solution (with Microsoft Graph - as broadly described in the tutorial).
That is mostly, because I could not find any documentation about if there are ways to tweak the indexer, so that he uses a different chunking strategy or limit the chunk size.
So Is there something like this or a feature / full version of this with more configuration planned or is it advisable to build something custom in the long run?
Thank you so much!
-
Shree Hima Bindu Maganti 815 Reputation points Microsoft Vendor
2024-11-12T07:23:37.1566667+00:00