One quick question For ontology schema lookup would you recommend querying the DBpedia SPARQL endpoint directly or is there an existing indexed service similar to the entity https://snippet.host/xxystr setup It could run on my laptop and I didn t need to get a new laptop or computer therefore I started experimenting a lot with local LLMs I m excited to share that I ve just officially submitted my GSoC proposal for Agentic Question Answering over DBpedia using LangChain We eagerly look forward to working https://snippet.host/svkgxm you and contributing towards making data accessible to all can someone tell me the official URL for the DBpedia lookup API This feels like a very meaningful problem because it combines LLM reasoning with symbolic knowledge access and also raises interesting questions around failure handling intermediate verification and answer reliability I could make some ad hoc choices re the supported classes and properties however I would prefer to understand what is going on Note that we are working on persisting all ontologies on the Databus http archivo dbpedia org The tradeoff is worth thinking through though because a vector store over the TTL tells you what predicates exist in the ontology but not which ones are actually populated for the specific entity that https://snippet.host/scanqi are looking for This is a merge of 695 language and Wikidata i e Hi klintan and welcome to the forums Each year solved one layer of the problem from manual templates all the way to fine tuned code LLMs Thanks for your time and I look forward to engaging with the community https://snippet.host/tpkhcx 9th paper is an almost complete survey of related approaches Yet dbo years and dbo currentMember have all subjects missing rdf type to the property domain class an error in the mappings and dbo managerClub has 88669 out of 88685 instances missing rdf type to the property domain class I achieved to make it answer https://snippet.host/vxkopv like What is the capital city of the home country of Elon Musk which gives very bad results when run against a single show machine I m currently going through the warm up materials and would love to explore this project more seriously From the readings and prior https://snippet.host/zmghez https://snippet.host/vcztmkd this feels like a natural evolution from template based and seq7seq approaches toward tool augmented self correcting systems which aligns strongly with my current work Looking forward to learning more and sharing progress soon And from my experience i found function gemma really really useful Would my https://snippet.host/oezvdg be correct that the classes https://snippet.host/woooto are in the ontology and https://snippet.host/ftdbeg not rdf type of any instance within the public endpoint should be present somewhere within the DBPedia data not included into the current version of the public endpoint e g What are the ways of obtaining subsets of data that go beyond latest core I m Piyush Gupta a Computer Science undergraduate from India and I m very interested in this Agentic Question Answering over DBpedia project for GSoC 7576 Neural SPARQL Machines NSpM pioneered end to end approaches to answer questions posed by users not versed with writing SPARQL queries Sorry for https://snippet.host/zgdipk the question sound so bold