Ukulele

6 months project made at the LabBoite fablab while in highschool in 2019.

Project Story

We introduce a novel agent-based framework that leverages conversational data to enhance Large Language Models (LLMs) with personalized knowledge, enabling the creation of Artificial Personal Intelligence (API) systems. The proposed framework addresses the challenge of collecting and analysing unstructured conversational data by utilizing LLM agents and embeddings to efficiently process, organize, and extract insights from conversations. The system architecture integrates knowledge data aggregation and agent-based conversational data extraction. The knowledge data aggregation method employs LLMs and embeddings to create a dynamic, multi-level hierarchy for organizing information based on conceptual similarity and topical relevance. The agent-based component utilizes an LLM Agent to handle user queries, extracting relevant information and generating specialized theme datasets for comprehensive analysis. The framework's effectiveness is demonstrated through empirical analysis of real-world conversational data. While the proposed framework presents significant advancements, limitations such as the need for high-quality conversational data and limited user interaction testing are acknowledged. Future research should explore optimization techniques, the integration of additional conversational qualities, and extensive real-world testing to further enhance the framework's capabilities in the domain of Artificial Personal Intelligence, ultimately enabling more personalized and context-aware AI assistance.