[ 
https://issues.apache.org/jira/browse/SOLR-18187?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18101736#comment-18101736
 ] 

ASF subversion and git services commented on SOLR-18187:
--------------------------------------------------------

Commit 8e9a7ac791741375e35f9cff512203c181759281 in solr's branch 
refs/heads/branch_10x from Nicolò Rinaldi
[ https://gitbox.apache.org/repos/asf?p=solr.git;h=8e9a7ac7917 ]

SOLR-18187: Document enrichment with LLMs (#4259)

(cherry picked from commit 0e018d0f507803a21dade153b57ed1b8b45b30da)


> Document enrichment with LLMs
> -----------------------------
>
>                 Key: SOLR-18187
>                 URL: https://issues.apache.org/jira/browse/SOLR-18187
>             Project: Solr
>          Issue Type: New Feature
>          Components: UpdateRequestProcessors
>            Reporter: Nicolò Rinaldi
>            Priority: Minor
>              Labels: pull-request-available
>          Time Spent: 6h 50m
>  Remaining Estimate: 0h
>
> The goal of this contribution is to add a way to integrate LLMs directly into 
> Solr at index time to fill fields that might be useful (e.g., categories, 
> tags, etc.). This has been done by adding an UpdateRequestProcessor called 
> DocumentEnrichmentUpdateProcessor to the 'language-models' Solr module that 
> enriches documents at index time using LLMs through Langchain4j chat models.
> The implementation has taken inspiration from the text-to-vector feature in 
> the same module, together with documentation and examples in different use 
> cases.



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to