DevConf.CZ 2025

Pranita Ghole

Associate Manager, User Experience Engineering, Red Hat | Python Developer | AI Enthusiast exploring the AI world.


Company or affiliation

Red Hat

Job title

Associate Manager


Sessions

06-12
10:15
80min
Llama Stack - AI development made easy !
Pranita Ghole, Pravin Pareekh, Anuj Singla, Abhishek Kumar

Llama stack has become the new talk of the town in the open source AI community. But what exactly is Llama Stack and how to leverage it to build real-world AI applications ? Llama stack is a framework for streamlining development of AI apps. Developers face multiple challenges in building the AI apps such as handling the infrastructure complexity, using different tooling for the essential capabilities like knowledge retrieval, RAG, monitoring, evaluation etc. and lastly the lack of flexibility and choices for provider integrations. In this workshop, we will understand how Llama stack addresses these challenges and standardizes the core building blocks for simplifying AI application development.

In this workshop, the attendees will get to learn the following -

  • What is Llama stack and how it addresses developer challenges ?
  • What are the advantages of using llama stack ?
  • Understand the Llama stack components and APIs.
  • How to setup Llama stack ?
  • Hands-on with Llama stack - Building An App with Llama stack APIs. We will show how to build an AI app that can call two different tools and combine their results to give a final answer. Using Llama Stack and FastAPI, we will demonstrate how an AI agent interacts with tools like APIs to process information. It will be a Python project. Participants need to bring their laptops.

Whether you're an AI enthusiast or developer, this workshop will provide an introduction along with a hands-on session for leveraging the Llama Stack for your next project.

Artificial Intelligence and Data Science
A218 (capacity 20)
06-14
10:35
15min
Exploring the world of Small Language Models
Pranita Ghole

While large language models dominate AI conversations, Small Language Models (SLMs) are proving to be powerful, efficient and more practical for many real-world applications.

In this Lightning Talk, we’ll explore what small Language Models are and how they work. We will see how they compare to their larger counterparts and the advantages they offer in terms of cost, speed, and accessibility. Lastly, we will go through a few real world use cases where SLMs can be used effectively.

This talk would be useful for developers, AI enthusiasts and beginners to know more about the SLMs, their use cases and why they are gaining traction.

Artificial Intelligence and Data Science
A113 (capacity 64)