# ML Tools support for nested fields

**URL:** <https://forum.opensearch.org/t/ml-tools-support-for-nested-fields/19241>\
**Category:** Machine Learning\
**Created:** [May 7, 2024, 2:28pm UTC](https://forum.opensearch.org/t/ml-tools-support-for-nested-fields/19241 "2024-05-07T14:28:36Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![malv007](https://avatars.discourse-cdn.com/v4/letter/m/5f8ce5/32.png) [@malv007](https://forum.opensearch.org/u/malv007)\
**Post date:** [May 7, 2024, 2:28pm UTC](https://forum.opensearch.org/t/ml-tools-support-for-nested-fields/19241/1 "2024-05-07T14:28:36Z")

</div>

**Versions** (relevant - OpenSearch/Dashboard/Server OS/Browser):  
2.13

**Describe the issue** :  
As of version 2.13, we can use text chunking to split a long text into smaller chunks and generate vectors/embeddings for those chunks in a nested field. And then we can use this nested field in a semantic search (neural, neural\_sparse, etc.). Is there a way to use these nested embedding fields in agent tools such as RAGTool, NeuralSparseSearchTool, VectorDBTool…?

**Configuration** :  
Docker installation with 3 nodes (2xdata+ML)

**Relevant Logs or Screenshots** :  
N/A

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/flex019/uploads/mauve_hedgehog/original/2X/3/33547ea01a5b12dcca2958411d3edd97ae2ea8c1.png) [@system](https://forum.opensearch.org/u/system)\
**Post date:** [July 6, 2024, 2:28pm UTC](https://forum.opensearch.org/t/ml-tools-support-for-nested-fields/19241/2 "2024-07-06T14:28:40Z")

</div>

Closed on July 6, 2024, 2:28pm UTC

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.