Is there any kind of prompt caching in

You can create a retriver and extract all the nodes and then do the llm call as per your format adding all node content

yeah but implicit

not explicitly creating a vector store

isnt there anything in the LLM abstraction?

Let me see if I got your query right:

• You want to use llm without creating a vector store ? with prompt changing capability?

So I want to have a cache layer so that eveyr prompt gets intercepted and ran through the caching layers.
I want to avoid doing it manually for every request. Lets say we have an agent that makes multiple requests that I wont have access manually, I would have to rewrite all of the classes to be able to have cache.
Lets say i use a query engine for agent tools, I would have to rewrite query engine so that it intercepts the prompts and checks the cache

Yea currently there is no feature such as this present, You'll have to write this on your own

thank you!