Consider using gptcache for caching
prs1022 opened this issue · comments
Self Checks
- I have searched for existing issues search for existing issues, including closed ones.
- I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
- 请务必使用英文提交 Issue,否则会被关闭。谢谢!:)
- Please do not modify this template :) and fill in all the required fields.
1. Is this request related to a challenge you're experiencing? Tell me about your story.
Recalling LLM APIs can be expensive, and the response speed may slow down during LLMs’ peak times, I think dify needs a cache system to deal with this.Now open source gptcache can be considered for use within the supported model range.What do you think?
2. Additional context or comments
No response
3. Can you help us with this feature?
- I am interested in contributing to this feature.
Duplicated #848