zilliztech/GPTCache

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

66
/ 100
Established

Implements semantic similarity matching using embeddings (ONNX, etc.) and pluggable vector stores (Faiss) to cache conceptually similar queries, reducing redundant API calls beyond exact-match caching. Provides both a Python library with adapter support for OpenAI and a Docker server exposing cache functionality via HTTP for language-agnostic integration, with configurable temperature-based cache bypass logic.

7,963 stars and 467,367 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 2 / 25
Adoption 20 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

7,963

Forks

570

Language

Python

License

MIT

Last pushed

Jul 11, 2025

Monthly downloads

467,367

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/zilliztech/GPTCache"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.