semantic-cache 0.1.0
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:
=
dependencias de Runtime (1):
ruby-openai
~> 7.0
dependencias de Development (6):
Propietarios:
Subida por:
Autores:
-
stokry
SHA 256 checksum:
=