Prerequisites

• I am running the latest code. Mention the version if possible as well.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

Through the WebUI when receiving a long answer and updating the window view token by token has a high CPU usage I would prefer to have an option to specify a low update rate that uses less CPU, maybe an option to specify minimum number of tokens to update the window view.

Looking through devtools I saw that there is an option in the post data stream: true and then I saw on answer per token (that seems too much fine grained, probably batch then would be a good idea).

Motivation

Lowering CPU/energy/climate usage.

Possible Implementation

No response