PyData Southampton - 17th Meetup

Venue: Carnival House, 100 Harbour Parade, Southampton, SO15 1ST
📢 Want to speak 📢: submit your talk proposal

Please note:

1. 🚨🚨🚨A valid photo ID is required by building security. You MUST use your initial/first name and surname on your meetup profile, otherwise, you will NOT make it on the guest list! 🚨🚨🚨
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 further confirmation required. You will NOT need to show your RSVP confirmation when signing in.
If you can no longer make it, please unRSVP as soon as you know so we can assign your place to someone on the waiting list.

***
Code of Conduct:
This event follows the NumFOCUS Code of Conduct, please familiarise yourself with it before the event. Please get in touch with the organisers with any questions or concerns regarding the Code of Conduct.
***
There will be pizza & drinks, generously provided by our host, Carnival UK.
***

AI Agents in the Data Pipeline - Craig West
Can we build an Agentic AI Data Analyst (intern)?
In this 90-minute workshop we will work almost exclusively with notebooks. The aims for the workshop are:

1. To see that it can be just ‘AI as API’, albeit a very magical API.
2. To show that AI based apps need not be all AI or not at all, but we can have ‘a bit of AI’ in our apps.
3. To show that it is ‘business as usual’ as Pythonistas, using our experience and skills to create AI Apps.

PART ONE

1. We will learn how to build AI Agents from scratch and see that they can be considered to use ‘AI as API’. A new way of coding is involved, and we will spend time understanding how Generative AI is used.
2. We will look at the fundamental patterns and explore Tool/Function calling.
3. We will examine how Multi Agents frameworks use traditional design patterns.
4. We will also look briefly at how we test Agentically and evaluate our Agents.

PART TWO

1. We will look at some AI Agents and see how they can be used in a Data Pipeline, from ETL to Query Analysis and Text2SQL.
2. We will have a conversation about how capable our AI Agents are and what we can expect from them.

Access to an LLM will be required.
Groq provides a free tier which will be more than sufficient for our use. It uses the same interface as OpenAI so an OpenAI API key or Groq API key will be sufficient. Code is wired for both Groq and OpenAI except for one or two demo examples.

Free Tier with Groq: https://console.groq.com/login
GitHub Repository: [To be available a few days prior to event]

Please follow the instructions in advance of attending the workshop

Please note this is a practical session and you will need to bring your own laptop. We recommend you bring it fully charged, if you can, as there may not be enough plug sockets for everyone to use at the same time.

Logistics
Doors open at 6.30 pm, talks start at 7 pm. For those who wish to continue networking and chatting we will move to a nearby pub/bar for drinks from 9 pm.

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 @pydatasoton (https://twitter.com/pydatasoton) for updates and early announcements. We are also on Instagram/Threads as @pydatasoton; and find us on LinkedIn.