zilliztech / GPTCache

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
https://gptcache.readthedocs.io
MIT License
6.96k stars 490 forks source link

[Feature]: Multi-tenant GPTCache service #550

Open SimFG opened 9 months ago

SimFG commented 9 months ago

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

Currently, the GPTCache service uses a cache object to manage cached data. If GPTCache serves multiple users, user A's cached data may be queried by user B. Naturally, this is not allowed in reality.

Describe the solution you'd like.

No response

Describe an alternate solution.

No response

Anything else? (Additional Context)

No response

Vasanthavel124 commented 9 months ago

can you assign this to me?