GPTCache

About:

GPTCache is a semantic cache designed specifically for large language models (LLMs). It is fully integrated with LangChain and llama_index‚ providing efficient storage and retrieval of precomputed embeddings and related data. By caching semantic information‚ GPTCache accelerates inference tasks for LLMs‚ reducing latency and improving overall performance. Its seamless integration with LangChain and llama_index ensures compatibility and ease of use within existing workflows. With GPTCache‚ developers can leverage the power of semantic caching to enhance the efficiency and effectiveness of their language model applications.

Stack: ai; chatgpt

Stars: 5.9K

Sign up for 1 email a week

We send new OSS products every week in a new newsletter. No Spam.

Error. Your form has not been submittedEmoji
This is what the server says:
There must be an @ at the beginning.
I will retry
Reply
We respect your privacy. Your information is safe with us.
Built on Unicorn Platform