Closed michaelthwan closed 1 year ago
For reference
If the bottleneck is the embedding service for Semantic search, should we try to setup config to use external provider, e.g. says cost effective GPT text-embedding-ada-002
for trial?
We can still have the sentence-transformers/all-mpnet-base-v2 as the default choice, but externalize the loading to other embedding service endpoint seems making more sense to me.
@karabC possibly~
quite fast now. Let me close this.
e.g. I think the 5x scrap website is quite slow