You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Tell us about your request. Provide a summary of the request and all versions that are affected.
We're adding support for using multimodal search in neural-search plugin. Users can ingest their data and create embeddings using model that support multiple inputs. As part of this change we will add a new ingestion processor for text and image embeddings.
Similar to that, search for such models will also be possible with neural search query. We will extend existing query clause and to allow users adding multiple inputs for a model.
Initial version of this feature is scheduled for 2.11 release of OpenSearch.
What do you want to do?
Tell us about your request. Provide a summary of the request and all versions that are affected.
We're adding support for using multimodal search in neural-search plugin. Users can ingest their data and create embeddings using model that support multiple inputs. As part of this change we will add a new ingestion processor for text and image embeddings.
Similar to that, search for such models will also be possible with
neural
search query. We will extend existing query clause and to allow users adding multiple inputs for a model.Initial version of this feature is scheduled for 2.11 release of OpenSearch.
What other resources are available? Provide links to related issues, POCs, steps for testing, etc.
[FEATURE-Experimental] Support multi-modal semantic search
The text was updated successfully, but these errors were encountered: