Concept Flow

An LGUI interaction paradigm for systematic knowledge retrieval

Concept Flow is an LGUI interaction paradigm that is aimed at efficient systematic knowledge retrieval.

The experience of LLM Chatbot for systematic information retreieval is still painful.

Say I'd like to learn about a new subject, like "trip to new york", which includes aspects of dining, accomodation, shopping, etc.

To deep dive into one of the aspects, we need to formulate and type prompts.
Also, we may lose context and forget to learn other aspects after deep diving into one.

Mind map is a non-linear layout for information, which enables us to deep dive without losing the global view. Closed source products like Albus have already pioneered using this paradigm.

A node stands for a concept. Each node is pre-programmed to explore and exploit with just a click.

To exploit current concept, click the yellow spark button. To explore related concepts, click the blue cube button. To add custom concepts, click the green plus button.

Try it out☝️!

Try out this paradigm in playground. Tell us how you feel by creating an issue in Github or reach out on Twitter. Hope that it helps you (or amuses you🐶).

The content generated in each explore/exploit action is by RAG-augmented LLM to ensure both readability and credibility. The parent context will be carried when making RAG query so that the reponse is correctly scoped.

React Flow