Semantic Caching

Cache LLM responses by semantic similarity.

Cache Hierarchy

Request → L1 (Exact) → L2 (Semantic) → L3 (Prompt) → L4 (LLM)
           ~1ms         ~10ms           ~2s          ~3s
         100% save    100% save       90% save    Full cost

Redis Semantic Cache

from redisvl.index import SearchIndex
from redisvl.query import VectorQuery