TypingMind

I would love to have more control over automatic chat title generation. Perhaps even to have a chance to select: a preferred model (do not need to call o1 to generate title for a chat with o1, where a cheap model would do just as well) custom prompt (would love not to have all titles forced to be in English, when it could be based on the language of the chat).

Option to select a language for automatically generating titles for created chats.

For opensource models like r1 that do thinking in tags, and then respond, its a bother to have to find where the thinking ends, it would be great if we could customize that if x tag appears, make it collapsable so that the output would either only be answer tags or no tags

As described in the typingmind perplexity help pages ( https://docs.typingmind.com/chat-models-settings/use-with-perplexity-ai ) we are currently able to use perplexity both as a model and via the perplexity plugin. Perplexity plugin already supports citations, as described in requests like https://typingmind.canny.io/feature-requests/p/perplexity-citations . This feature request is for a way to display citations when we're using perplexity models directly. Maybe there could be a "Support Citations" slider underneath the other "Support" sliders for custom models?

Add multiple sorting options to the left panel interface to facilitate conversation history management. These would include sorting by creation date, modification date, or last accessed date. At present, selecting an old chat moves it to the top of the history, complicating its reading and categorization. The new sorting features would enable a more efficient and organized user experience.

When the sidebar is collapsed, the chat name is not visible. Therefore, having the chat name (and possible folder name) at the top of the chat is beneficial. Or implement a breadcrumb.

I use GPT-4-32k through OpenRouter a lot, and this is a slight annoyance, especially with how expensive the token usage adds up for that model. I know it would be hard to get the exact cost of each prompt, but an estimation would be great. Would it be possible to include tokens utilized next to a prompt/reply and the estimated cost?

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

As a TypingMinds user I want to be able to automate a sequence of saved prompts so that I can complete repetitive tasks more easily. See: SuperPowerChatGPT Chrome Add-On for one version of an implementation of this style of feature.

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.