# Creating vector index from SharePoint Online data

**URL:** <https://discuss.elastic.co/t/creating-vector-index-from-sharepoint-online-data/378000>\
**Category:** Elasticsearch\
**Tags:** vector-search\
**Created:** [May 9, 2025, 9:35pm UTC](https://discuss.elastic.co/t/creating-vector-index-from-sharepoint-online-data/378000 "2025-05-09T21:35:46Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![UNNIE\_Ayilliath](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/unnie_ayilliath/32/142843_2.png) [@UNNIE\_Ayilliath](https://discuss.elastic.co/u/UNNIE_Ayilliath)\
**Post date:** [May 9, 2025, 9:35pm UTC](https://discuss.elastic.co/t/creating-vector-index-from-sharepoint-online-data/378000/1 "2025-05-09T21:35:46Z")

</div>

I am trying to implement a vector index using ELSER2. The data source is SharePoint Online and I have used the Elasticsearch SharePoint Online connector to ingest data into the index with DLS enabled.

I followed this blog from Elastic =\> [Federated SharePoint searches with Azure OpenAI Service On your data - Elasticsearch Labs](https://www.elastic.co/search-labs/blog/sharepoint-federated-searches-azure) to create the vector index.

Now, how can I add token size based chunking using the Elastic pipelines? I want to chunk the incoming SharePoint document body with token size of 512.