Slava Tykhonov and Alexy Khrabrov: Palefire, an advanced Context Graph AI Project
Pale Fire combines the use of Large Language Models and Knowledge Graphs (semantic artifacts) to support navigation through collections. Situated in the research area of Retrieval Augmented Generation, this specific workflow represents the creation of local and adaptable chatbots. Based on the tool-suite EverythingData at the backend, GhostWriter provides an interface that enables querying and “chatting” with a collection. Applied iteratively, the workflow supports the information needs of researchers when interacting with a collection of papers, whether it be to gain an overview, to learn more about a specific concept and its context, and helps the researcher ultimately to refine their research question in a controlled way. Pale Fire is developed by Slava Tykhonov, Head of AI and Interoperability at CODATA, the European open data consortium. Codata collaborates with the Community Research Center for Reliable AI at Northeastern Oakland, lead by Alexy Khrabrov, who is presenting this talk. Pale Fire is now a part of the AgStack, a Linux Foundation project dedicated to Open Source for Agriculture.