Long term memory support (virtually no context memory limit)

[michaelveilleux]

Hi,

Have you seen this project on Github?

https://github.com/LagPixelLOL/ChatGPTCLIBot

The introduction of this project : « Long term memory support! Keep hitting the 4096 tokens context limit? Worry no more with this CLI Bot. It has nearly INFINITE context memory(If you have infinite disk space lol), all thanks to Embeddings! If you want to see how this program handles embeddings internally, set debug_reference to true in config.json! »

It would be really very interesting/powerful to implement a function similar to this project (proof of concept) to your project ChatGPT… or/and why not in NoFWL.

I'm currently using it to interact with an entire book, and it works really well...and, the possibilities are vast with this technique.

Looking forward to it and thank you again for your ChatGPT APP, it's awesome!

— M.