This seems interesting, how do you actually decide what to fetch from the memory that is relevant? "This setup enables efficient memory retrieval based on relevance, recency, and context" -- but how does it actually "decide" what to retrieve?
I was just thinking about this recently! Eventually I settled on making a .txt which I manually update whenever I want it to remember some stuff and uploading it to every conversation.
This seems interesting, how do you actually decide what to fetch from the memory that is relevant? "This setup enables efficient memory retrieval based on relevance, recency, and context" -- but how does it actually "decide" what to retrieve?
I was just thinking about this recently! Eventually I settled on making a .txt which I manually update whenever I want it to remember some stuff and uploading it to every conversation.
Doesn’t larger conversations also consume more therefore hitting the usage limit faster?
That’s great ! Does the extension work with APIs UIs like open-webui or LibreChat?