Typing Mind

Simplified workflow to create RAGs (knowledge stacks) and use them. I would like to be able to create a knowledge stack (RAG) using TypingMind interface. I would specify a local folder or local PDFs on my computer and typingmind would use either openAI's embedding model or a local embedding model to create a RAG. Then, when creating a chat, I would be able to call upon a local knowledge stack. knowledge stack and files should be local since knowledge stack can contain large files All should be done through typingmind's UI without using endpoints etc. Currently, typingmind supports RAGs, but it's through a complicated API. It should all be done locally using the typingmind interface. It shouldn't just input the whole document as input. That would consume a lot of tokens like in agents system instructions.

Implement the MCP protocol that Anthropic has just open sourced, so that we can add any of the MCP servers that have been and will be developed to increase the capabilities of TM. Would be extra cool if it were done in such a way that we could use them with any LLM we have configured in TM, similar to what you did with your answer to Anthropics artifacts.

Can you please stop re-enabling, re-adding and moving new AI models to the top of the list? I don't use the official APIs - I have a proxy for that. I don't want to use any models I have not added.

Please implement password-based login (in addition to the email version). Getting a code via email is so much more friction than a password manager auto-filling the username and password. It's very frustrating. This would be less of an issue if the app didn't log me out every couple of weeks. Increasing the remember-me logged in period would also help remove this frustration.

so we dont have to keep updating version and be behind passively

I am excited to see what plugins and extension people are creating.

As I find myself using these agents more and more every day for simple, one-off tasks and questions, my conversation history gets messy. Could there be a mode, like a dedicated conversation, (optionally default) that isn't saved and prompts and responses more than X old self-destruct?

Currently there is an option to export the chat as MD, but would be good to export also only the message, not the full chat

When using the interactive canvas, it works great on simple prompts, but gets into an infinite loop when asked to update a complex UI. Prompt was: > Generate a search UI with products using (canvas) then > Add facets ... and then it goes into an infinite loop!