AW: AW: Question on RDF standardisation and large language models

Here you go
https://github.com/w3c/sparql-dev/issues/193


this is still too general, rather a place to gather material and to distinguish sub topics like


  *   Extending full text search
  *   Providing genuine LLM functionalities like generating summarizes or generating new graph nodes based out of text

Best,

Felix

Von: Vladimir Alexiev <vladimir.alexiev@ontotext.com>
Datum: Donnerstag, 14. Dezember 2023 um 06:20
An: Adrian Gschwend <adrian.gschwend@zazuko.com>
Cc: Sasaki, Felix <felix.sasaki@sap.com>, RDF-star WG <public-rdf-star-wg@w3.org>
Betreff: Re: AW: Question on RDF standardisation and large language models
Sie erhalten nicht oft eine E-Mail von vladimir.alexiev@ontotext.com. Erfahren Sie, warum dies wichtig ist<https://aka.ms/LearnAboutSenderIdentification>
Felix, post an issue and I'll describe GraphDB's LLM integration. We have several things, and one is KG Entity indexing.


On Wed, 13 Dec 2023, 16:21 Adrian Gschwend, <adrian.gschwend@zazuko.com<mailto:adrian.gschwend@zazuko.com>> wrote:
On 13.12.23 19:07, Sasaki, Felix wrote:

> I like the reference to XQuery full text search. Re-using such
> definitions indeed can safe a lot of time.
>
> In the vector search space I am not aware of other languages to look at,
> something to look up.
>
> As you said, it boils down to the community being serious about the
> topic. Statements of interest are very welcome 😊

I would definitely be interested and I think it's a good moment to
revisit standard text search as it will become more interesting with
vector based search now. Not sure about LLM integration, I currently
don't see what we could standardize there, at least not yet.

But if we would want to work on that we should probably plan it
accordingly because the SEPs don't write themselves :)

regards

Adrian

--
Adrian Gschwend
CEO Zazuko GmbH, Biel, Switzerland

Phone +41 32 510 60 31
Email adrian.gschwend@zazuko.com<mailto:adrian.gschwend@zazuko.com>