Typing Mind Custom

We have plethora of questions to prompting the right way, finding better prompts, colalborating on prompts, exchanging prompts etc...

Currently, only email or externalUserID is visible.

Guarantee that TypingMind remains fully compatible with a RAG infrastructure comprising AzureAI Cognitive Search, Langchain RAG, and Llama Index, supporting chat completions and document uploads to backend vector stores, with the RAG infrastructure deployable from the admin panel as a specific model with a dedicated API endpoint.

the same as auto assigning the voice on the Character level feature recently added, having an option to change the model settings for the AI Character would allow a ton of additional use cases and also help with token usage. at the moment I have an AI Character that is designed for a very specific task and if the context window is too long then it runs up the token count unnecessarily. I would like to limit this character to as few messages as possible to preserve the token usage and prevent the end user from running up a high bill.

When creating personalized and bespoke AI characters for users, with almost identical setup, EXCEPT for the custm features of each student (name, personality profile etc): It would make sense to be able to clone AI characters and then change personal data in the text description field and/or system prompt.

I'm looking to embed the widget in many of my company's web apps. For each web app, I'm going to create an Agent that is an expert in supporting that app. Being able to specify the default agent some way for each individual use would be very nice.

Ability to upload training data (documents) specific to a character. Separate it out from the master training data section.

The AI Agents menu keps getting bigger and bigger. Furthermore, the nature of each agent and use cases differ significantly, making categorization of AI Agents a required feature.