[ 
https://issues.apache.org/jira/browse/SOLR-17525?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17896035#comment-17896035
 ] 

Alessandro Benedetti commented on SOLR-17525:
---------------------------------------------

Thanks guys for your input!
[~epugh] I am in favour of having multiple people contributing, I would love to 
first close a first version that works and then create other tasks to improve 
it/solidify it.
I think this ticket should handle the first iteration + documentation.
Other tasks I see coming:
- UpdateRequestProcessor to add the indexing time support
- performance testing
- support for additional embedding models (including potentially an In-Process 
one)

My plan is to create the Jiras and work at least on the UpdateRequestProcessor.
Happy for anyone who joins the train!

[~ichattopadhyaya] I don't know what a SIP is 
(https://www.acronymfinder.com/SIP.html didn't help).
If it's anything that can help in finalising the contribution quickly, great, I 
am open to it, but I have limited time allocated to the task and I hope we can 
get feedback and improve the pull request in a decent time frame to avoid 
losing the momentum

> Text to Vector Query Parser
> ---------------------------
>
>                 Key: SOLR-17525
>                 URL: https://issues.apache.org/jira/browse/SOLR-17525
>             Project: Solr
>          Issue Type: New Feature
>      Security Level: Public(Default Security Level. Issues are Public) 
>          Components: query parsers
>            Reporter: Alessandro Benedetti
>            Priority: Major
>              Labels: pull-request-available
>          Time Spent: 4h 20m
>  Remaining Estimate: 0h
>
> Scope of this issue is to introduce support for automatic text vectorisation 
> in Apache Solr, directly in a query parser.
> 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 query parser will use such services to directly encode the 
> query to a vector and then run vector search on a DenseVectorField.



--
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