Typing Mind

Have the ability to export a single chat or multiple chats.

I'd like to suggest adding LaTeX rendering support in Typingmind for inline equations, like \( ax^2 + bx + c = 0 \) , not just for the displayed equations wrapped in \[ ... \] . It'd make a big difference for users to have that flexibility.

It would be great to display the last message date in the folder view. I know the list is sorted by Date, but as i use folders, i often do not know what is the latest chat on a topic, as i mostly leave the autogenerated titles. It would be helpful to see how "old" a chat is, so i can see what i used recently. Would not need to be exact (time of a day) but rather how many days, months, years ago it was.

I often have multiple steps I want the bot to go through 1 at a time. It would be cool to be able to submit the initial input, and while the bot is answering, queue more inputs to the bot that is fed 1 at a time after it finishes the current input. For instance when generating text or code I can get it to initially generate using some specific specs, but then I can queue multiple inputs to have the bot review the code or text after processing. It gives me better results than trying to make it do reviews in the original prompt. In that way I dont have to have hands on through the process but can make it a bit agent-like doing revisions itself but using my "input queue".

Auto-delete feature for chats older than a certain time (e.g. 24 hours), unless they're starred or inside a folder.

Show approximately how much of the chat history fits in the context window of the current model.

Would like the ability to have multiple profiles so that it doesn't need to be manually changed if you want to provide context about a different person or organization.

It would be great to be able to chain characters in a chat (eg introduce a new character who could act on the context in a chat to take it to the next stage)

As a professional spreadsheets user, I often need and ask for output in the form of tables. However, TypingMind's markdown rendering of tables lacks the vertical lines, making it sometimes confusing to distinguish separate "cells" from single, merged fields. I'd like pretty, clear tables like the ChatGPT version, as shown in these screenshots.

Each chat applies to a different scenario and needs to be set to a different prompt, temperature, Context Limit, or whatever. And need to memorize it. It would also be nice to have support for modifying conversations after they are opened, just giving a hint that subsequent conversations will use the new settings. There is a native client that is set up like this for reference: https://opencat.app