Vladyslav Fliahin has a strong foundation in CV, NLP, DL, Mathematics and Algorithms. Have expertise in the understanding of project data, business analysis, management, and architecture designs. His responsibilities as a Data Scientist span the entire data cycle, from preprocessing to developing decision-making systems running in production.
Vlad is presenting his session, streaming live from Kraków, Poland, during the 24 hour Artificial (Un)Intelligence Conference.
Session Description
In this session I will talk about two projects using LLMs.
The first, creation of custom assistants with RAG/Agents+RAG, describes a path to implement a custom RAG-based assistant for the structured and unstructured data. The transition from MongoDB-based RAG to Neo4j-based RAG as a path to the knowledge graph. The main question we had was how could we evaluate such systems? Do we need agents to assist us? If so, how would we evaluate their efficiency?
The second project I will talk about is the creation of an LLM-powered metadata extraction algorithm. We wanted to determine if an LLM could be used, and how powerful it might be in the information extraction process.
Tools, Technologies, and Concepts Featured
+ bonus recommendations on working with LLMs
About Vladyslav Fliahin
I have over three years of experience in Programming & Data Science, specializing in NLP, CV, ML, and Optimization algorithms. As a Team Lead, I have successfully managed projects in these areas. My responsibilities as a Data Scientist span the entire data cycle, from preprocessing to developing decision-making systems running in production.
I have a strong foundation in CV, NLP, DL, Mathematics and Algorithms. Have expertise in the understanding of project data, business analysis, management, and architecture designs.
The Artificial (Un)Intelligence Conference is a global, 24 hour live online conference. Registration is free, and includes access to all sessions, including on-demand, at the conclusion of the event. No sales pitches, no marketing. Just the good stuff.
We're trying to find the unheralded people around the world who are doing cool things with AI. Is that you?
Check out our speaker gallery and then let us know what you're working on. We look forward to hearing your story.
Comments