PyData Trójmiasto #30

We are happy for the opportunity to welcome you to 30th edition of PyData Trójmiasto meetup!

When: 23rd April at 6 PM.

Where: Room AB, Building C, at Gdańsk Science-Technology Park (different than the one during the last event)

Registration: The event is free to enter. Just let us know you're coming via RSVP to help us determine pizza demand;)

About "Building a reliable Kafka consumer in Python" talk:

Roman will be talking about why you might want to introduce Kafka into your system, what potential challenges you may face and how to overcome them.

A few words about Roman:

Roman is a software engineer with 10+ years of experience, with the most work done by building real-time and batch data processing pipelines. Currently working as Staff Software Engineer at people.ai.

About "Coding Agent is all you need (?) - an overview of AI-based code writing tools" talk:

In the rapidly evolving tech landscape, developers are always on the lookout for tools that can make their coding work more efficient. GitHub Copilot, despite its flaws, has emerged as a significant aid for many. The AI bubble we are currently in has also brought many new solutions - Large Language Models (LLMs) has got us swapping our regular dives into StackOverflow for quick sessions with ChatGPT. But can language models offer more, like explaining complex code repositories or analyzing your coding practices as peers might during code reviews?

Imagine going further: what if we could integrate these AI models into our code repositories for a collaborative coding experience? Or even more ambitious, create an autonomous software developer agent capable of crafting an entire codebase from scratch to meet specific requirements? You've probably all seen the demo of Devin, an AI software engineer who supposedly creates systems from scratch. Do we actually have anything to be afraid of? Should we think about changing our career path before it’s too late? Maybe the plumber's job won't be replaced so soon?

The domain of AI code-writing tools is quite fresh and, frankly, filled with a fair share of junk. Yet, there are some solid foundations right there, and I've made an effort to test them - I want to share my thoughts with you. I also want to show you our own Data Scientist Agent intended to automate machine learning model training, evaluation, and deployment. Join me on this journey to discover how LLMs can amplify our coding capabilities and imagine a future where AI is integral to the coding process.

A few words about Maksymilian:

I obtained my master’s degree in Computer Science from Gdańsk University of Technology. Currently, I’m a Machine Learning Engineer at deepsense.ai where my work revolves around Large Language Models and their wide-ranging applications - from implementing personalized RAG systems (using both closed and open-source models) to developing and testing AI Coding Agents. I also collaborated with the authors of the LangChain library, focusing on the topic of privacy of input data for language models. Besides work, I feel a constant need to learn about new cultures - this mainly manifests itself in traveling and learning languages. Additionally, I often find myself compulsively buying books that I most probably won’t have enough time to read.