Re: using dense vector search with Solr

[Alessandro Benedetti <a....@sease.io>]

Hi Till,
it's great to see how this new feature is impacting the community!
I and we(as a community of committers) are actively working on various new
contributions related to the neural search domain.
Some minor ones will come soon, keep an eye on 9.2 or 9.3 .

In terms of bigger contributions such as an end-to-end integration with
large language models and inference, it's a work in progress, but from my
side, I'm waiting for some funding to prioritize the work.

Keep an eye on our Twitter (https://twitter.com/SeaseLtd), blog(
https://sease.io/blog-2/our-blog), and official Solr Jira and GitHub for
news!

Cheers

--------------------------
*Alessandro Benedetti*
Director @ Sease Ltd.
*Apache Lucene/Solr Committer*
*Apache Solr PMC Member*

e-mail: a.benedetti@sease.io


*Sease* - Information Retrieval Applied
Consulting | Training | Open Source

Website: Sease.io <http://sease.io/>
LinkedIn <https://linkedin.com/company/sease-ltd> | Twitter
<https://twitter.com/seaseltd> | Youtube
<https://www.youtube.com/channel/UCDx86ZKLYNpI3gzMercM7BQ> | Github
<https://github.com/seaseltd>


On Thu, 23 Feb 2023 at 22:44, Till Kinstler <ki...@gbv.de> wrote:

> Hi,
>
> I've been playing with "neural" / dense vector search in Solr 9 a bit
> and find it very promising.
> Currently I am calculating the vectors outside of Solr at indexing and
> search time with a bunch of scripts using NLP models (text in, vectors
> out...). Especially at search time, that's not exactly a handy solution,
> because every client application would have to do this (or some sort of
> proxy application between client applications and Solr, that would
> manipulate requests (search terms out, vector in) on their way to Solr).
> That's ok for my very basic prototype, but nothing else.
> How are others solving this? Are there any best practices? Or even plans
> to make Solr talk directly to ML models?
> In Solr's traditional logic, I would imagine something like an analyzer,
> that does the "dense vector creation" at indexing and search time. It
> would have to use a ML model, pass data/searches in, get vectors out and
> put them into a DenseVectorField. Just as traditional analyzers work.
> The model could be a configurable ONNX model?
> Is someone working on something like this? (I only found some related
> comments in https://github.com/apache/solr/pull/1213)
>
> Till
>
> --
> Till Kinstler
> Verbundzentrale des Gemeinsamen Bibliotheksverbundes (VZG)
> Platz der Göttinger Sieben 1, D 37073 Göttingen
> kinstler@gbv.de, http://www.gbv.de/
>