News for hackers. Stuff that matters.

A comment on Pg_vectorize: The simplest way to do vector search and RAG on Postgres. Parent comment

Re:Pg_vectorize: The simplest way to do vector search and RA... by WhitneyLand on Wednesday March 06, 2024 @01:26PM (#39619171)
Wild speculation - do you think there could be any benefit from creating two sets of chunks with one set at a different offset from the first? So like, the boundary between chunks in the first set would be near the middle of a chunk in the second set?
[ Parent | on HN ]
Re:Pg_vectorize: The simplest way to do vector search and RA... by CuriouslyC on Wednesday March 06, 2024 @02:06PM (#39619860)
No, it's better to just create summaries of all the chunks, and return summaries of chunks that are adjacent to chunks that are being retrieved. That gives you edge context without the duplication. Having 50% duplicated chunks is just going to burn context, or force you to do more pre-processing of your context.
[ Parent | on HN ]