[
https://issues.apache.org/jira/browse/SOLR-17632?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17932909#comment-17932909
]
Renato Haeberli commented on SOLR-17632:
----------------------------------------
[~abenedetti]
I think it would make sense to add the label
https://issues.apache.org/jira/browse/SOLR-17679?jql=labels%20%3D%20vector-based-search
to this ticket, it took me a while to find it. Thanks.
> Text to Vector Update Request Processor
> ---------------------------------------
>
> Key: SOLR-17632
> URL: https://issues.apache.org/jira/browse/SOLR-17632
> Project: Solr
> Issue Type: New Feature
> Components: UpdateRequestProcessors
> Reporter: Alessandro Benedetti
> Assignee: Alessandro Benedetti
> Priority: Major
> Labels: pull-request-available
> Time Spent: 5h 50m
> Remaining Estimate: 0h
>
> Scope of this issue is to introduce support for automatic text vectorisation
> in Apache Solr, directly in a update request processor.
> A LLM fine-tuned for sentence similarity will be accessed to embed the text.
> Apache Solr will host the configuration parameters to access embedding
> services and the update request processor will use such services to directly
> encode the document field as a vector.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
