# Neural query against two indicing with different embedding models **URL:** \ **Category:** Machine Learning\ **Created:** [July 16, 2025, 1:51pm UTC](https://forum.opensearch.org/t/neural-query-against-two-indicing-with-different-embedding-models/25808 "2025-07-16T13:51:31Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![asfoorial](https://avatars.discourse-cdn.com/v4/letter/a/3da27b/32.png) [@asfoorial](https://forum.opensearch.org/u/asfoorial)\ **Post date:** [July 16, 2025, 1:51pm UTC](https://forum.opensearch.org/t/neural-query-against-two-indicing-with-different-embedding-models/25808/1 "2025-07-16T13:51:31Z")
Hi all, I am using OS 3.0.0 and I am trying to query multiple knn indices with one neural query given that each index uses different ML model. Is there a way to do it? I appreciate input on this matter. Regards ---
**Author:** ![pablo](https://sea1.discourse-cdn.com/flex019/user_avatar/forum.opensearch.org/pablo/32/10363_2.png) [@pablo](https://forum.opensearch.org/u/pablo)\ **Post date:** [July 21, 2025, 7:25pm UTC](https://forum.opensearch.org/t/neural-query-against-two-indicing-with-different-embedding-models/25808/2 "2025-07-21T19:25:55Z")
@asfoorial, I think this could be possible for a semantic search. But neural query requires a model ID. > **[Semantic search](https://docs.opensearch.org/docs/latest/vector-search/ai-search/semantic-search/#setting-a-default-model-on-an-index-or-field)** > > Semantic search ---
**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:** [September 19, 2025, 7:26pm UTC](https://forum.opensearch.org/t/neural-query-against-two-indicing-with-different-embedding-models/25808/3 "2025-09-19T19:26:39Z")
This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.