Introduction to LLM-based agents in Python

Introduction to LLM-based agents in Python

Overview

DataScience@UL-FRI Workshop

Summary

The workshop offers a concise introduction to LLM-based agents. We will be exploring key concepts such as reasoning, tool use, state management and retrieval-augmented generation. We will start with some essential theory and look at practical implementation examples. Finally, we will put these ideas together by building a simple agent that combines these core concepts. Prerequisite: Basic familiarity with language models.

Syllabus

  • Introduction to LLMs and agents
  • Getting familiar with the environment: LLMs in Python & Google Colab
  • Exploring the key agentic concepts & practical implementation
  • Putting it all together: building an agent

Instructor

Matej Klemen is a researcher and (finishing) PhD student at University of Ljubljana. His research focuses on knowledge injection and inspection methods for language models, as well as their adaptation for various practical applications.

Attendee equipment prerequisites

Laptop with internet access - the notebooks will be runnable on online environments such as Google Colab.


Access to the materials (code and instructions) will be provided before the workshop.

DataScience@UL-FRI Workshop

Summary

The workshop offers a concise introduction to LLM-based agents. We will be exploring key concepts such as reasoning, tool use, state management and retrieval-augmented generation. We will start with some essential theory and look at practical implementation examples. Finally, we will put these ideas together by building a simple agent that combines these core concepts. Prerequisite: Basic familiarity with language models.

Syllabus

  • Introduction to LLMs and agents
  • Getting familiar with the environment: LLMs in Python & Google Colab
  • Exploring the key agentic concepts & practical implementation
  • Putting it all together: building an agent

Instructor

Matej Klemen is a researcher and (finishing) PhD student at University of Ljubljana. His research focuses on knowledge injection and inspection methods for language models, as well as their adaptation for various practical applications.

Attendee equipment prerequisites

Laptop with internet access - the notebooks will be runnable on online environments such as Google Colab.


Access to the materials (code and instructions) will be provided before the workshop.

Good to know

Highlights

  • 3 hours
  • In person

Location

Lecture room 3 at UL-FRI, Večna pot 113, Ljubljana

Večna pot 113

1000 Ljubljana

How do you want to get there?

Map
Organized by
Report this event

More events from Data Science@UL-FRI

Discover more events from Data Science@UL-FRI, from Science & Tech to other experiences you might love.

Still looking for the right event?

Explore all events in Ljubljana and filter by date, category, and more to find the perfect fit.