PyData London - 84th Meetup

Venue: Riverbank House, 2 Swan Ln, London EC4R 3AD -
IMPORTANT: LOCATION UPDATED!
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 the event.

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 you know.

***

Code of Conduct:
This event follows the NumFOCUS Code of Conduct. Please get in touch with the organisers with any questions or concerns regarding the Code of Conduct.

***

As always, there'll be free food & drinks, generously provided by our host, Man Group.

***

Main Talks

Building Retrieval Augmented Generation (RAG) powered applications - Aniket Maurya

RAG extends the capability and knowledge base of large language models (LLMs) by augmenting prompts with proprietary and domain-specific knowledge without the need to retrain the LLM. It ensures information stays current and reduces hallucination by attributing the source. In this talk, the audience will get an overview of building RAG powered applications using open-source tools.

Getting python out of the way when taking ML models from research to production. A deep dive into the Open Neural Network Exchange (ONNX) - Aditya Goel

The Python data science ecosystem is unparalleled when it comes to model development and training. When moving models from research to production, Python creates many challenges from latency through to managing environments and dependencies. The Open Neural Network Exchange (ONNX) enables data practitioners to export their model to a self-contained, target independent protobuf representation. When paired with highly performant runtime and compiler technology, this leads to exceptionally high performance inference across many hardware targets, while massively simplifying to process of getting models from research into production. This talk will explore how data practitioners and software engineers can exploit ONNX to rapidly speed up the transfer of models from research to production.

⚡ Lightning Talks

1. Using Google Location Data and Reverse Geocoding to Explore your Personal Travel History - Jessica Walkenhorst

In this talk I will demonstrate how you can use reverse geocoding on your Google location data to gain a detailed understanding of your past travel history. Apart from being a fun exercise and bringing back great memories, the results of this analysis can be used to understand times spent abroad, information that is often required in the process of applying for residency permits and foreign passports.

2. Community Lightning Talk - Bring your own!

This is an opportunity for guests to bring their own lightning talk and spontaneously present on the evening!

Logistics
Doors open at 6.30 pm (get there early as you have to sign-in via building security), talks start at 7 pm, drinks from 9 pm in the bar. We will 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!

Follow @pydatalondon (https://twitter.com/pydatalondon) for updates and early announcements.