PyData London - 101st Meetup

Venue: Riverbank House, 2 Swan Ln, London EC4R 3AD

Please note:

1. 🚨🚨🚨A valid photo ID is required by building security. 🚨🚨🚨
2. This event follows the NumFOCUS Code of Conduct. Please familiarise yourself with it before attending.

If your RSVP status says "You're going" you will be able to get in. No need to show your RSVP confirmation when signing in.
If you can no longer make it, please unRSVP as soon as possible.
***
Code of Conduct:
This event follows the NumFOCUS Code of Conduct. Please get in touch with the organisers with any questions or concerns.
***
As always, there will be free food and drinks, generously provided by our host, Man Group.
***

Main Talks

1. Using Hugging Face's smolagents framework to create a Fantasy Premier League AI Agent - Geir Freysson

How do you ground AI agents in real-world data so they don’t hallucinate? This talk shows how I built a Fantasy Premier League agent using Hugging Face’s smolagents - a minimal, ~1,000-line framework. It connects directly to structured FPL data to give accurate, context-aware answers. Even if football isn’t your thing, it’s a practical talk of how to expose real data to LLMs and build useful agents without heavy infrastructure. The agent is at fpl.withrobots.ai and the source-code for the agent template so you can build your own is at https://github.com/geirfreysson/smolagents-template

2. No More Boilerplate: Data-Driven Testing Made Easy - Antonio Feregrino

Learn how to streamline that process using PyTest fixtures. We’ll look at a fixture-based approach to reading test data across multiple formats (JSON, CSV, YAML, JSONL, plain text), and how it can make your tests cleaner, more maintainable, and easier to scale. I’ll also introduce a decorator that lets you parametrise tests directly from data files, enabling true data-driven testing without the clutter.

⚡ Lightning Talks

1. Mise and easy: managing environments the fun way - Connor Adams
2. USearch: The Engine Behind Most New Search & RAG Pipelines - Ash Vardanian

Logistics
Doors open at 6.30 pm (get there early as you'll need to sign in with building security). Talks start at 7:00 pm, with drinks afterwards from 9:00 pm at The Banker (EC4).

We have reduced capacity for this event, but there will be plenty of people to discuss data science questions with!

Please unRSVP in good time if you realise you can't make it. We're limited by building security on the number of attendees, so please free up your place for your fellow community members!