Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • Curious how semantic cache works,are cache hit based on embeddings, exact prompt normalization, how do you avoid serving stale incorrect cache..
    by master67
  • for semantic cache, there is configurable similarity threshold. using it you can control the incorrect cache serving.
    by gurveer51