First off, thanks for building and open-sourcing this project @cogentapps. It's extremely helpful and was my gateway into generative AI.
Quick question: In terms of scaling, I'm trying to determine if I need to change any of the code to deploy this across multiple servers to be load balanced. It seems like all auth information is all stored in a database which can be shared amongst servers and none of that info is stored in server memory. For the audio buffers from Eleven Labs though, I'm not sure if this will be a problem. I'm not too familiar with audio buffering/streaming.
I'm curious how you ended up deploying chatwithgpt.ai I'd appreciate your help on this and look forward to hearing from you.
First off, thanks for building and open-sourcing this project @cogentapps. It's extremely helpful and was my gateway into generative AI.
Quick question: In terms of scaling, I'm trying to determine if I need to change any of the code to deploy this across multiple servers to be load balanced. It seems like all auth information is all stored in a database which can be shared amongst servers and none of that info is stored in server memory. For the audio buffers from Eleven Labs though, I'm not sure if this will be a problem. I'm not too familiar with audio buffering/streaming.
I'm curious how you ended up deploying chatwithgpt.ai I'd appreciate your help on this and look forward to hearing from you.