zilliztech / GPTCache

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
https://gptcache.readthedocs.io
MIT License
7.15k stars 503 forks source link

[Feature]: Support correcting error cache #548

Open SimFG opened 12 months ago

SimFG commented 12 months ago

Is your feature request related to a problem? Please describe.

When a cache miss occurs, that is, the question does not match the cached answer, cache correction is supported.

After the cache is corrected, it is guaranteed that the same subsequent request will not hit the previous wrong cache answer.

Describe the solution you'd like.

No response

Describe an alternate solution.

No response

Anything else? (Additional Context)

No response

Vasanthavel124 commented 12 months ago

Can you assign this to me?