semantic-cache 0.2.0
Cache LLM responses using semantic similarity matching. Similar questions return cached answers instantly, cutting API costs by 70% or more. Works with OpenAI, Anthropic, and Gemini.
Gemfile:
=
instalar:
=
Runtime Dependencies (1):
ruby-openai
~> 7.0
Development Dependencies (6):
Donos:
Pushed by:
Autores:
-
stokry
SHA 256 checksum:
=