Microsoft Reactor Berlin Pop-Up

Our third stream in the Python + AI series is all about vision models!

Vision models are LLMs that can accept both text and images, like GPT 4o and 4o-mini. You can use those models for image captioning, data extraction, question-answering, classification, and more!

We'll use Python to send images to vision models, build a basic chat-on-images app, and build a multimodal search engine.

In our fifth stream of the Python + AI series, we'll discover how to get LLMs to output structured responses that adhere to a schema. In Python, all we need to do is define a @dataclass or a Pydantic BaseModel, and we get validated output that meets our needs perfectly.

We'll focus on the structured outputs mode available in OpenAI models, but you can use similar techniques with other model providers. Our examples will demonstrate the many ways you can use structured responses, like entity extraction, classification, and agentic workflows.

You’ve hacked, you’ve learned, you’ve created and now it’s time to wrap up and submit your project.

In this session, we will walk you through the complete submission process for the FabCon Hackathon. You will learn how to package your solution, including your code, docs, and demo video, and where to upload everything. We will share tips for creating a clear and compelling demo that highlights your innovation and meets the judging criteria.

Finally, we will cover what happens next: timelines for judging and how winners will be announced. Bring your questions and we will leave time for Q&A to make sure you leave confident and ready to submit.

What you will learn

• How to submit your project details, code, and demo video
• Tips for creating a strong documentation and demo
• Key dates and what to expect after submission