Name: PyData Prague #24 - The Large, the Weed and the Compliant
Start: 2024-12-03T17:30:00.000Z
End: 2024-12-03T20:30:00.000Z
Location: CreativeDock

**About this Webinar**
Join us for an insightful session where you’ll learn to deploy applications powered by large language models (LLMs) using serverless technology.
Explore how serverless architecture simplifies application deployment, eliminating the need to manage infrastructure while ensuring scalability and efficiency.
**Key Highlights:**

* Learn to process audio files by combining automatic speech recognition (ASR) with LLMs.
* Build an automated system that detects customer inquiries, transcribes audio, and generates concise summaries using Amazon Bedrock.
* Discover how to enable logging to enhance security and maintain compliance.

**What You'll Gain:**

* Insights into customizing LLM responses with Amazon Bedrock.
* A step-by-step approach to transcribing audio recordings and summarizing them using LLMs.
* Skills to deploy an event-driven workflow for audio summarization with AWS Lambda.
* A hands-on understanding of using models like Amazon Titan and more through Amazon Bedrock.

**Who Should Attend?**
This webinar is ideal for developers familiar with Python and AWS who are eager to explore quick and efficient deployment of LLM applications using Amazon Bedrock.
**Why Join Us?**
Walk away with the expertise to build and deploy your serverless LLM apps in days, harnessing the power of Amazon Bedrock and AWS services.

PyData OMR

karuppaiya

 SENTHIL KUMARAN.M

Indu

Building Serverless LLM Applications with Amazon Bedrock

Online event

**PyDataMCR December Talks**

Continuing with some more great talks we are hosted this month by Krakenflex.

**THE TALKS**

**Beyond Traditional Recommenders: Leveraging Graph Neural Networks for Food Delivery Platforms - [Chris Dambamuromo](https://www.linkedin.com/in/chrisdamba/) (he/him)**

In this talk, Chris will demonstrate how to implement a Graph Neural Network (GNN) based recommendation system for food delivery platforms. Drawing from real-world examples, he'll explore how GNNs can effectively balance the complex dynamics of a three-sided marketplace - customers, restaurants, and delivery partners. The presentation will cover practical aspects of working with limited data, implementing GraphSAGE, and handling multiple optimisation objectives. This independent project represents his exploration of recommendation systems and graph-based machine learning, bringing together his technical expertise and interest in practical AI applications.

Chris is a Data Engineer with over a decade of software development experience, specialising in data engineering and machine learning. With a background in Applied Mathematics and Intelligent Computer Systems, he's passionate about applying advanced AI techniques to solve real-world problems. Currently focusing on recommendation systems and graph-based machine learning, Chris brings practical insights from his experience in both software development and data engineering.

The talk will include code examples and is suitable for data scientists, ML/Data engineers, and anyone interested in practical applications of Graph Neural Networks.

**Building Seamless Pipelines with DBT and Python - [Andy Stafford Hughes](https://www.linkedin.com/in/andrew-stafford-hughes-63b04632/) (he/him)**

I will discuss how we successfully automated testing with DBT and Python in our Data Products team.

Andrew is an Enterprise Data & AI Test Architect with extensive experience in quality assurance across industries like healthcare, gaming, and retail. Currently at AstraZeneca, he is enhancing test automation frameworks for data science and GenAI projects while mentoring teams to improve their automation testing capabilities globally.

**LOCATION**
We'll be at Krakenflex, who are also kindly supplying catering. The capacity is limited to 90.

After the talks we'll all head somewhere local for some post-event socialising.

**EVENT GUIDELINES**
PyDataMCR is a strictly professional event, as such professional behaviour is expected.

PyDataMCR is a chapter of PyData, an educational program of NumFOCUS and thus abides by the NumFOCUS Code of Conduct

https://pydata.org/code-of-conduct.html

Please take a moment to familiarise yourself with its contents.

**ACCESSIBILITY**
Under 16s welcome with a responsible guardian. There is a quiet room available if needed. Toilets are accessible.

**SPONSORS**
Thank you to NUMFocus for sponsoring Meetup and further support
Thank you to AutoTrader for sponsoring PyDataMCR.
Thank you to Krakenflex for sponsoring PyDataMCR, as well as hosting this event!

PyData Manchester

Grace Wilding

Fiona Pye

John Carney

PyDataMCR December

Krakenflex (13th Floor)

**PyData Global 2024 is a 3-day virtual event for the international community of data scientists, data engineers, and developers of data analysis tools to share ideas and learn from each other.**

**During the conference, attendees will have the opportunity to attend live keynote sessions and talks, lightning talks, and get to know fellow members of the PyData Community.**

**The event will be virtually hosted.**

**Schedule: [https://pydata.org/global2024/schedule](https://pydata.org/global2024/schedule)**

**Buy tickets here: [https://pydata.org/global2024/tickets](https://pydata.org/global2024/tickets)**

[https://pydata.org/global2024/](https://pydata.org/global2024/)

PyData L'Aquila

NumFOCUS, Inc.

Lisa

Mai Nong

PyData Global 2024

DataScience and AI: in person in Darmstadt and live on PyData.TV on YouTube

**Agenda**
17:30 Doors open
18:00 Welcome
18:15 **Boosting Time Series Accuracy: The Power of Ensemble Methods** - **Robert Haase (Paretos)**
18:45 Break: Networking with snacks and beverages
19:45 **Unleashing Confidence in SQL Development through Unit Testing -** **Tobias Lampert (Lotum)**
20:15 Lightning Talks
20:30 Networking with snacks and beverages
21:00 End

**⚡️ Lightning Talks**:
Feel free to submit a proposal

**How to sign up for on site**
It's important for us to make this meet up happen in a responsible way. We have limited seats available only.
**No limits to sign up remotely!**

**How to join remotely**
Join the Zoom meeting or you can also watch the talks on [YouTube](https://www.youtube.com/channel/UCOjD18EJYcsBog4IozkF_7w).

This event will be in English.

\-\-\-\-

Talk #1
**Boosting Time Series Accuracy: The Power of Ensemble Methods** - **Robert Haase (Paretos)**
This talk explores the practical application of ensemble methods in time series analysis, based on Robert’s extensive experience at Pareto. It covers various ensembling approaches, highlighting their effectiveness in different real-world scenarios. Attendees will gain insights into which methods perform best in practice, supported by behind-the-scenes examples of successful implementations. The session provides valuable strategies for improving predictive accuracy, making it ideal for anyone looking to leverage ensemble techniques in their time series projects.
**Robert** earned both his Bachelor's and Master's degrees in Physics from the University of Heidelberg, specializing in Condensed Matter Physics and Computational Physics. During his Master's thesis in 2020, he advanced existing NLP Transformer architectures for timeseries applications. This involved Robert working extensively with uncertainty quantifications and normalizing flows. Since the beginning of 2021, he has been employed at Paretos, where the primary focus of his work lies in Timeseries Forecasting, specifically demand forecasting. Robert has a keen interest in combining traditional statistical methods with deep learning techniques.

Talk #2
**Unleashing Confidence in SQL Development through Unit Testing -** **Tobias Lampert (Lotum Media)**
As data-driven applications grow, robust SQL development practices are crucial. This talk explores the challenges of maintaining complex SQL models in Data Warehouses and highlights the importance of unit testing in ensuring data quality. Attendees will learn how SQL unit testing validates modeling logic, prevents breaking changes, and supports faster deployment cycles. The session features Lotum’s Python-based SQL unit testing framework for BigQuery, which processes millions of daily events from mobile games. Discover how using small, static mock data simplifies testing and helps identify code errors efficiently.

**Tobias Lampert** is an experienced technical leader with expertise in Data Science and Data Engineering. With over 20 years of experience, he has designed and implemented data-intensive applications end-to-end, covering everything from data ingestion to deployment. He has developed solutions that generate insights from data using statistical analysis and machine learning. His passion lies in building user-friendly, high-performance, and cost-efficient data platforms.
\-\-\-\-
**Acknowledgements**
Also a big thank you to our partners:

* [Hessian.AI](https://hessian.ai/), for hosting the meetup.
* [PIONEERS HUB](https://pioneershub.de), for organising.

**Contact**
If you have any questions or suggestions, please feel free to contact us via:

* Meetup
* Want to speak? [Submit a talk here](https://bit.ly/talk-at-pydata-rm).
* Interested in hosting an event? Here's our [Info-Deck](https://bit.ly/pydata-sw-infodeck) & [contact to the organisers](https://www.linkedin.com/groups/12851256/)!

PyData Rhein-Main - Artificial Intelligence in Python

Alexander C. S. Hendorf

Anna Tentscher

Jurik Sommer

PyData Rhein-Main - Forecasting & Testing

S1 I 03 Altes Hauptgebäude TU Darmstadt · Raum 121

Hello plant developers and language twisters!

The 24th Prague PyData meetup will take place at **CreativeDock**. As usual, the talks will start at 18:30 but we encourage you to come as soon as **18:00** to enjoy the opportunity to socialise and refresh yourselves (which you can continue doing during the break and after the talks).

Our main goal is to build the community around Python and data and make it welcoming to people of various skills and experience levels.

⚡ If you are interested in giving a lightning talk (up to 5 minutes to present an idea, tool or results related at least to some degree to Python and/or data), please contact us before or during the event.

**📢 Processing problematic plants with python**
**Adam Hruška**
Weed detection techniques are essential in modern precision agriculture, where accurately detecting and identifying species can lead to effective crop yields and sustainable resource use. Python has emerged as a powerful tool in this domain, providing versatile libraries and frameworks for data gathering, processing, and model training. By leveraging Python's capabilities, we can efficiently manage large-scale datasets, preprocess images, and potentially automate the annotation process, streamlining the development of machine learning models for weed detection. The integration of computer vision and machine learning tools, including OpenCV, scikit-image, and TensorFlow, serves as a basis for creation of models capable of distinguishing between crops and weed species with high precision. As a result, Python-driven weed detection models offer a promising path toward improved crop health, resource conservation, and sustainable farming practices.

**📢 Beyond Accuracy: Engineering EU-Compliant LLM Systems**
**[Soheyla Mirshahi](https://www.linkedin.com/in/soheyla-m-336961251), [Jan Kryštůfek](https://www.linkedin.com/in/jan-kry%C5%A1t%C5%AFfek-1780844a/) (CreativeDock)**
Building production-ready LLM systems is challenging, but designing solutions that comply with the EU AI Act introduces layers of complexity far beyond prompt engineering and API integration. This talk takes you through the journey of creating a compliant LLM system for one of the most demanding domains: AI-driven recruitment.
We share our journey from a naive PoC to a production ready solution under the AI Act. Through this case study, we will explore:

* Compliance-first approach: Designing LLM systems to meet security, legal and ethical standards from the ground up
* Taming LLM in Python: Using prompts, function calls and scoring model to get results in structured and auditable form
* Evaluation: Testing on synthetic data, human evaluation and user feedback
* Numbers: Statictics from production and percieved benefits

Attendees will leave equipped with practical tools, architectural patterns for building LLM systems that meet both engineering and regulatory challenges, supported by real-world example.

The venue will open at 6.00pm but the intro won't take place sooner than at 6:30pm. **We should enter via the Expo 58 gallery (in the middle floor of the 3-floor building).** There will be food and drinks available, 🤗 sponsors.

Please, RSVP here.
See you soon,
PyData Prague team

PyData Prague

Jan Pipek

Ostap Semenchuk

Petr Moravek

PyData Prague #24 - The Large, the Weed and the Compliant

CreativeDock

PyData

Cerca {networkName}

Gruppi

{PRO_NETWORK_NAME} fa parte di Meetup Pro con più di {PRO_MEMBER_COUNT} iscritti in {PRO_GROUP_COUNT} Meetup in tutto il mondo. Meetup Pro è lo strumento professionale per organizzare e comunicare in un network di utenti, partner, contributori e partecipanti.

This group is operated by NumFOCUS, Inc. PyData is a program of NumFOCUS, a U.S.-based 501(c)3 non-profit. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including Python, Julia, R, and more.

The PyData Code of Conduct (http://pydata.org/code-of-conduct.html) governs this meetup. You can submit a report of any potential Code of Conduct violation here: https://numfocus.typeform.com/to/ynjGdT 

Thanks for making PyData a welcoming and friendly community!

PyData

PyData

Chi siamo

Cerca PyData

Prossimi eventi

Gruppi