tensor_cache 0.4.0

Multi-layer LLM response cache with exact, semantic, and embedding lookup
Documentation 
1
2
3
4
5
6

{
  "git": {
    "sha1": "0f0a692b1761d608125b1f0b5782b3d6784127cf"
  },
  "path_in_vcs": "tensor_cache"
}