Changelog

Updated the concepts generated from sources such as PDF files, YouTube videos, etc., to return a text snippet that shows how the concept is mentioned in the source file.

Updated the concepts to return a definition alongside the concept name. This way, you should be able to assess which concepts are worth adding to your concept map much better.

I recently updated the position and design of Quick Links (now called Quick Context) and the left-hand sidebar to make them more accessible and increase the screen space for the concept map. I hope you enjoy it!

Note Node has been renamed Editable Node. Additionally, it is now free to use for non-subscribed users. However, AI operations on this node for non-subscribed users are not supported.

Updates the Arxiv research modal to support sorting for date, relevancy, etc.

Flashcards and quizzes created using the free tools are now publishable and can be shared with anyone via their link.

You can now define custom instructions to customize the responses you get from the LLM model.

You can now click on the Concepts button on a YouTube video, Podcast, Wikipedia article or a Web link to extract interesting or unique concepts mentioned in them. Previously, this was a much more tedious process and required you to extract snippets manually. Now, AI can help you with this.

Interesting and Controversy buttons now return much more comprehensive information.

Added the Qwen 2.5 72B model, which fares much better at math-related problems than other open-source models.