stdweird commented on issue #1121: URL: https://github.com/apache/age/issues/1121#issuecomment-2077207580
i guess that ideally we can use eg vector search (but maybe also bm25 via pg_search) to be able to form graphs connecting similar entities (instead of exact matching ones). eg when building a knowlegde graph for RAG, the entities and relations are harvested using eg LLMs, leading to similar entities (instead of exactly teh sme ones) because eg the source data is written by diffferent people talking about the same things, yet using different words. lacking a formal verification/cleanup process, this leads to more then one entity in the graph. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: dev-unsubscr...@age.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
