Typing Mind Custom

Support seamless integration with OpenAI's Assistant API and the current AI Character system.

Each document or piece of information in the knowledgebase should have an editable title and/or description, for better clarity and overview.

Adding checkboxes to INPUT/OUTPUT fields makes it possible to faster remove specific text entries from the context. This would REDUCE TOKEN COST, and improve the management of context quality.

Redesign the chat logs interface in the admin panel to display a comprehensive table view with additional columns Token consumption in/out, Training datasets used

Ability to use AzureAI OpenAI Assistant & code interpreter

Currently the only way to find out what agents a user has access to is by accessing all agents and verify users associated to the agent. This makes user/agent association and management very cumbersume - or literally impossible with 50+ agents. Suggestion: Add all agents accessible by user to the user overview page and make it possible to pause or delete agant from the user overview page. The current setup becomes unmanageable with increasing number of users paying for access to dedicated agents, or switching to different agents depending on changing coaching goals month-over-month etc. Or users not renewing coaching contracts, or cards getting rejected, requiring us to pause or cancel access to specific agents. We just need something user-centric, not agent-centric. Thanks

"👋 Questions? Chat with our AI!" can only be set globally for all AI agents. This should be possible to be changed per AI Agent. Our use case is that we need to create different AI agents for the chatbot feature for each language of our company. Now we can only set one language.

This popup "👋 Questions? Chat with our AI!" keeps coming back on each new page load. I contacted support about this but was told this won't be changed soon, which to me is confusing because it's bad UX, while from my understanding it is TypingMind's main mission to improve UI/UX.

This feature request aims to integrate an Internal Python Code Execution Module into the application, allowing it to dynamically execute Python code on demand. The module will enable the processing of user-defined functions or scripts and return the output in real-time. The system should handle standard use cases such as querying the current time, performing calculations, or processing data. This functionality would provide an interactive layer of computation directly within the application. Objectives Real-Time Execution: Support the ability to run Python code snippets and return outputs immediately. Dynamic Functionality: Enable dynamic interpretation and execution of user-provided Python scripts, offering a flexible tool for debugging, testing, and automation. Error Handling: Provide detailed error messages and logs to assist in identifying and resolving issues within the executed code. Integration with Other Features: Allow the output to be utilized in other modules or displayed in an interactive interface for users. Key Functionalities Code Parsing and Execution: A sandboxed environment to securely parse and execute Python code dynamically. Built-in Libraries: Support standard Python libraries for operations like time, math, and data handling. Result Display: Return results as strings, objects, or formatted data (e.g., JSON) for further processing. Secure Execution: Implement safeguards to restrict malicious or resource-intensive operations. Example Use Case A user inputs a function to retrieve the current time: python Copy code from datetime import datetime datetime.now ().strftime("%Y-%m-%d %H:%M:%S") The module executes the code and returns the output: "2025-01-15 09:19:38". A script to perform calculations or analyze data could also be executed with similar ease. Benefits Enhances interactivity by enabling users to run custom scripts without leaving the application. Reduces dependency on external tools for simple coding and debugging tasks. Empowers users to create, test, and execute small programs efficiently.