You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is your feature request related to a problem? Please describe.
We are creating multiple GPT Assistants to support our customer service operations. Currently, there is only support for caching results via ChatCompletion. We would like to see a GPT Assistant implementation of GPTCache.
GPT Assistants will mainly answer multiple queries that are very common like
Greeting a user/customer
Generic FAQs - questions that have been answered previously (stored in cache)
Out-of-Scope Answers that are stored in the cache ( using RAG, we limit the answers to the ones stored in the cache)
Over the course of time, we build a decent cache storage of all answers for user queries. These answers can be pulled from the cache directly instead of requesting Open AI every time. This would save us a lot of tokens and latency time.
Describe the solution you'd like.
I would like to see a solution where we have
GPT Assistant adapter class in Open AI adapter
Functionality to select assistant via assistant_id
Functionality to create and update cache for a specific assistant
Describe an alternate solution.
No response
Anything else? (Additional Context)
No response
The text was updated successfully, but these errors were encountered:
Is your feature request related to a problem? Please describe.
We are creating multiple GPT Assistants to support our customer service operations. Currently, there is only support for caching results via ChatCompletion. We would like to see a GPT Assistant implementation of GPTCache.
GPT Assistants will mainly answer multiple queries that are very common like
Over the course of time, we build a decent cache storage of all answers for user queries. These answers can be pulled from the cache directly instead of requesting Open AI every time. This would save us a lot of tokens and latency time.
Describe the solution you'd like.
I would like to see a solution where we have
Describe an alternate solution.
No response
Anything else? (Additional Context)
No response
The text was updated successfully, but these errors were encountered: