PyData London - 94th Meetup

## Details

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 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

1. Chunking for RAG: Preserve Meaning, Not Just Pieces - Brandon Abreu Smith
At Chroma DB we investigate the effects of different chunking methods. We find that chunking does impact performance in non obvious ways. We look at popular chunking methods like those used by OpenAI and benchmark them. We then present a method to empirically find the best chunking algorithm for your types of documents. Here is a link to the project: https://github.com/brandonstarxel/chunking_evaluation
https://research.trychroma.com/evaluating-chunking

2. Deploying self-hosted LLM applications for the workplace - Dmitri Evseev
We will share ARBI CITY's experience building a fully self-hostable RAG application and deploying LLMs on cost-effective hardware using a modern microservices architecture and open source tooling.

⚡ Lightning Talks
1. Coming soon...

2. Coming soon...

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.