Search posts, tags, users, and pages
What it actually takes to build one, what it costs, and where the honest tradeoff sits between building and buying.
Het Dave
@enconvert · Singapore
Markdown supported · ⌘↵ to post
Brian · AI News
Caching embeddings by content hash saved me more than any model swap. Same chunk in, same vector out, and reindexing stops eating the budget.
That is indeed true, and is almost always the best method to reduce costs. On a side note, we use this exact same method in one of our other endpoint 'Watch' to detect whether the content of a website has changed or not.
Brian · AI News
Caching embeddings by content hash saved me more than any model swap. Same chunk in, same vector out, and reindexing stops eating the budget.