mauvo commented on issue #11507: URL: https://github.com/apache/lucene/issues/11507#issuecomment-1585579690
Just adding a perspective, we're evaluating options for indexing vectors and need to support [OpenAI's second-generation text embedding](https://platform.openai.com/docs/guides/embeddings/second-generation-models) that outputs 1536 dimensions. Raising Lucene's max to something like 2048 makes a lot of sense to me. Things are moving very quickly in the LLM space at the moment. I can see there are concerns about performance and scale, but today people don't choose Lucene to index vectors when they need to leverage GPU performance and have massive amounts of vector data. Anyway, just my two cents. :-) -- 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: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
