From RAG to AI Agents: Function Calling and Tool Use
This is the 3rd workshop in our series to update the LLM Zoomcamp content.
This workshop updates Module 2: Introduction to Agents.
In this hands-on session, Alexey Grigorev will show how to turn a basic RAG application into an agentic AI assistant.
You’ll start with a simple RAG pipeline over Zoomcamp FAQ documents, then add agentic behavior: search decisions, multiple tool calls, function calling, and structured interaction with external tools.
What you’ll learn:
How to build a basic RAG application over course FAQ documents
What makes a RAG flow “agentic”
How agents decide when to search and when to answer
How to make the LLM generate search queries based on the user question
How to run agentic search over multiple iterations
How to use previous actions and search history as context
How OpenAI function calling works
How to define tools that an LLM can call
How to let an assistant search the FAQ database using tools
How to add multiple tools, including a tool for adding new FAQ entries
How to structure the assistant logic into reusable components
How to use PydanticAI to simplify tool definitions and agent implementation
By the end, you’ll have an agentic course assistant that can search the FAQ database, decide when it needs more information, call tools, and answer student questions with context.
Like the other workshops, this will be a live demo with practical tips and time for Q&A.
All events in these series:
Vector Databases: Embeddings, Semantic Search, and Hybrid Retrieval
RAG and Agents Evaluation: Measuring Retrieval and LLM Answer Quality
Monitoring LLM Applications: Traces, Feedback, and Production Quality
Thinking about Joining LLM Zoomcamp?
This workshop covers the updated content for Module 2 of the LLM Zoomcamp, our free course on building practical LLM applications with RAG, vector search, evaluation, monitoring, and AI agents.
You start with a simple RAG pipeline, then improve it with better retrieval, semantic search, function calling, evaluation, monitoring, and production practices.
The course covers the full lifecycle of an LLM application: from the first working prototype to evaluation, monitoring, and a complete final project.
The new cohort of LLM Zoomcamp starts on June 8, 2026. You can join it by registering here.
About the Speaker
Alexey Grigorev is the Founder of DataTalks.Club and creator of the Zoomcamp series.
Alexey is a software and ML engineer with over 10 years in engineering and 6+ years in machine learning. He has deployed large-scale ML systems at companies like OLX Group and Simplaex, authored several technical books, including Machine Learning Bookcamp, and is a Kaggle Master with a 1st place finish in the NIPS’17 Criteo Challenge.
DataTalks.Club is the place to talk about data. Join our Slack community!