talk-data.com

Join Pamela Fox, Burke Holland, Bruno Capuano, and Jon Galloway for a fast-paced showcase of GPT-5 integration across Microsoft developer tools, featuring practical demos, code samples, and insights for Python, .NET, JavaScript, and more.

Join Pamela Fox, Burke Holland, Bruno Capuano, and Jon Galloway for a fast-paced showcase of GPT-5 integration across Microsoft developer tools, featuring practical demos, code samples, and insights for Python, .NET, JavaScript, and more.

Join Pamela Fox, Burke Holland, Bruno Capuano, and Jon Galloway for a fast-paced showcase of GPT-5 integration across Microsoft developer tools, featuring practical demos, code samples, and insights for Python, .NET, JavaScript, and more.

Join us this month for an exciting and insightful evening exploring the frontiers of health data pipelines and AI product platforms.

The Talks

From Wrist to Insights - Building Health Data Pipelines - Pamela Ibude The integration of wearable technologies has transformed personal health monitoring by enabling real-time tracking of physiological parameters. This presentation outlines a practical end-to-end workflow for health data analytics, covering data extraction in XML format, transformation to structured CSV files, data cleaning using Python libraries, analysis in Jupyter Notebooks, and visualisations to reveal health trends. In this talk, Pamela will emphasise open-source tools like Apache Kafka for real-time data streaming and Hadoop for scalable storage and batch processing.

Platforms for Valuable AI Products- John Carney In data science, experimentation is vital. The more we can experiment, the more we can learn. However, quick iteration isn't sufficient; we also need to be able to promote these experiments to production to deliver value easily. This requires all the stability and reliability of any production system. John will discuss building platforms that treat iteration as a first-class consideration, the role of open source libraries, and balancing trade-offs.

Whether you're a data professional or simply curious, this is your chance to learn, network, and be part of our growing data community

Tune in for another re-release! Shane and Alcine are back with this on-FIRE conversation with Cincinnati math educators Crystal Watson and Dr. Dawn Williams who remind us that “The sun does not ask permission to shine, and neither do I.” These Black women leaders take us on a journey to understanding the type of math pedagogy that will transform and empower future generations of learners. We learn from Dr. Dawn why it’s important for leaders to create a place called home for teachers and, in turn, for students. Crystal and Dawn model a culture of listening to students, always asking, “How will that one child feel…?” and engaging in learning alongside students, all in efforts to affirm to students that the classroom is “your space.” They also teach us how to have a student-centered Data Meeting, how to support teachers to practice active listening- even when it’s uncomfortable! They explain how anxiety specifically with math triggers fight or flight, diminished executive function, and distracting behaviors in the classroom, and how building authentic and trusting relationships can help teachers guide students through that anxiety. Finally, we celebrate the truth that Black educators are “everything” while acknowledging the emotional labor of being a Black woman educational leader.

For Further Learning: 

Principles for the Design of Mathematics Curricula: Promoting Language and Content Development with specific Math Language routines classroom teachers can implement The Memo and Right Within by Minda Harts on overcoming racial trauma and discrimination in the workplace Choosing to See by Dr. Pamela Seda and Kendall Brown Crystal Watson is co-author of Shane's upcoming book Pedagogies of Voice: Street Data and the Path to Student Agency! Pre-Order at Corwin Check out this Webinar about Pedagogies of Voice: Street Data and the Path to Student Agency which features Crystal Watson on 5/21:

Join us for Episode 07 of Season 1 of #ModelMondays as we put the spotlight on open-source and AI development with a look at the Meta #Llama4 herd of recently released models. Huge props to Alexander Hughes for giving us an introduction to the Llama4 capabilities and to Pamela Fox for a hands-on look at multimodal features and more.

• https://aka.ms/model-mondays - Explore All Resources
• https://aka.ms/model-mondays/chat - Continue The Conversation
• https://aka.ms/model-mondays/collection - Explore The Model Cards
• https://aka.ms/model-mondays/newsletter - Get The Weekly Recaps

How do we help citizens vote for the political parties and candidates that match their preferences? How can we ensure that elected officials act in our best interests and uphold their promises? How do we verify their integrity and scrutinise their activities?

In our March meetup, we reflect on the recent election and look ahead to the next parliamentary cycle. We will hear from organisations dedicated to supporting democracy and enhancing transparency within our government system.

• Anne Hoppe, project manager, abgeordnetenwatch.de
• Pamela Brandt, project lead Wahl-O-Mat, Bundeszentrale für politische Bildung

CityLAB Berlin hosts the event in their stunning 1920s space, a former airport building.

All presentations will be given in English. Questions in the later discussion part can be raised either in English or German.

–––

Wie können wir den Bürger*innen dabei helfen, die politischen Parteien und Kandidaten zu wählen, die ihren Präferenzen entsprechen? Wie können wir sicherstellen, dass gewählte Amtsträger in unserem besten Interesse handeln und ihre Versprechen einhalten? Wie können wir ihre Integrität überprüfen und ihre Aktivitäten unter die Lupe nehmen?

Bei unserer März-Veranstaltung werden wir die Bundestagswahlen betrachten und einen Blick auf die nächste Legislaturperiode werfen. Wir werden von Organisationen hören, die sich der Unterstützung der Demokratie und der Verbesserung der Transparenz in unserem Staatswesen verschrieben haben.

• Anne Hoppe, Projektmanagerin, abgeordnetenwatch.de
• Pamela Brandt, Projektverantwortliche Wahl-O-Mat, Bundeszentrale für politische Bildung

Das CityLAB Berlin ist Gastgeber der Veranstaltung und lädt zu seinen beeindruckenden Räumlichkeiten im früheren Abfertigungsterminal des Flughafens Tempelhof ein.

Alle Vorträge werden in englischer Sprache gehalten. Fragen im anschließenden Diskussionsteil können sowohl auf Englisch als auch auf Deutsch gestellt werden.

RAG (Retrieval Augmented Generation) is the most popular approach used to get LLMs to answer user questions grounded in a domain. How can you be sure that the answers are accurate, clear, and well formatted? Evaluation! In this session, we'll show you how to use Azure AI Studio and the Promptflow SDK to generate synthetic data and run bulk evaluations on your RAG app. Learn about different GPT metrics like groundedness and fluency, and consider other ways you can measure the quality of your RAG app answers.

Presented by Nitya Narasimhan, AI Advocate, and Pamela Fox, Python Advocate

** Part of RAGHack, a free global hackathon to develop RAG applications. Join at https://aka.ms/raghack **

**📌 Check out the RAGHack 2024 series here! **

Pre-requisites: - Read the official rules and join the hack at https://aka.ms/raghack. No Purchase Necessary. Must be 18+ to enter. Contest ends 9/16/24.

• Want more hands-on RAG training? Visit the Reactor series home page to see all the RAGHack 2024 sessions!

RAG (Retrieval Augmented Generation) is the most popular approach used to get LLMs to answer user questions grounded in a domain. How can you be sure that the answers are accurate, clear, and well formatted? Evaluation! In this session, we'll show you how to use Azure AI Studio and the Promptflow SDK to generate synthetic data and run bulk evaluations on your RAG app. Learn about different GPT metrics like groundedness and fluency, and consider other ways you can measure the quality of your RAG app answers.

Presented by Nitya Narasimhan, AI Advocate, and Pamela Fox, Python Advocate

** Part of RAGHack, a free global hackathon to develop RAG applications. Join at https://aka.ms/raghack **

**📌 Check out the RAGHack 2024 series here! **

Pre-requisites: - Read the official rules and join the hack at https://aka.ms/raghack. No Purchase Necessary. Must be 18+ to enter. Contest ends 9/16/24.

• Want more hands-on RAG training? Visit the Reactor series home page to see all the RAGHack 2024 sessions!

If you're trying to get an LLM to accurately answer questions about your own documents, you need RAG: Retrieval Augmented Generation. With a RAG approach, the app first searches a knowledge base for relevant matches to a user's query, then sends the results to the LLM along with the original question. What if you have documents that should only be accessed by a subset of your users, like a group or a single user? Then you need data access controls to ensure that document visibility is respected during the RAG flow. In this session, we'll show an approach using Azure AI Search with data access controls to only search the documents that can be seen by the logged in user. We'll also demonstrate a feature for user-uploaded documents that uses data access controls along with Azure Data Lake Storage Gen2.

Presented by Matt Gotteiner, Product Manager for Azure AI Search, and Pamela Fox, Developer Advocate for Python

** Part of RAGHack, a free global hackathon to develop RAG applications. Join at https://aka.ms/raghack **

📌 Check out the RAGHack 2024 series here!

Pre-requisites: - Read the official rules and join the hack at https://aka.ms/raghack. No Purchase Necessary. Must be 18+ to enter. Contest ends 9/16/24.

• Want more hands-on RAG training? Visit the Reactor series home page to see all the RAGHack 2024 sessions!

RAG (Retrieval Augmented Generation) is a way to get LLMs to answer questions grounded in a particular knowledge base. What do you do when your knowledge base includes images, like graphs or photos? You first need to generate embeddings using a multimodal model, like the one available from Azure Computer Vision, search those embeddings using a powerful vector search like Azure AI Search, and then send any retrieved text and images to a multimodal LLM like GPT-4o. Learn how to get started quickly with a RAG on multimodal documents in this session.

Presented by Pamela Fox, Python Advocate at Microsoft

** Part of RAGHack, a free global hackathon to developer RAG applications. Join at https://aka.ms/raghack **

📌 Check out the RAGHack 2024 series here!

Pre-requisites: - Read the official rules and join the hack at https://aka.ms/raghack. No Purchase Necessary. Must be 18+ to enter. Contest ends 9/16/24.

• Want more hands-on RAG training? Visit the Reactor series home page to see all the RAGHack 2024 sessions!

RAG (Retrieval Augmented Generation) is the most common approach used to get LLMs to answer questions grounded in a particular domain's data. Discover the many ways you can build RAG applications on top of Azure Database for PostgreSQL Flexible Servers. We'll start by using the pgvector extension for vector similarity search. Then we'll explore the new azure_ai extension which provides built-in functions for embeddings, summarization, sentiment analysis, and more. Finally, we'll demo the new azure_local_ai extension to efficiently run pre-trained models on our database server, which can be a great fit for RAG applications that require custom embedding models.

Presented by Joshua Johnson, Principal TPM on Azure PostgreSQL, and Pamela Fox, Developer Advocate for Python

** Part of RAGHack, a free global hackathon to develop RAG applications. Join at https://aka.ms/raghack **

📌 Check out the RAGHack 2024 series here!

Pre-requisites: - Read the official rules and join the hack at https://aka.ms/raghack. No Purchase Necessary. Must be 18+ to enter. Contest ends 9/16/24.

• Want more hands-on RAG training? Visit the Reactor series home page to see all the RAGHack 2024 sessions!

RAG (Retrieval Augmented Generation) is the most common approach used to get LLMs to answer questions grounded in a particular domain's data. Azure AI Search is a powerful search engine, with many features designed specifically for RAG applications. We'll demonstrate optimal retrieval using hybrid search with the semantic ranker, show the new integrated vectorization feature for cloud-based data ingestion, and discuss vector storage optimization.

Presented by Farzad Sunavala, Product Manager on Azure AI Search, and Pamela Fox, Developer Advocate for Python

** Part of RAGHack, a free global hackathon to develop RAG applications. Join at https://aka.ms/raghack **

📌 Check out the RAGHack 2024 series here!

Pre-requisites: - Read the official rules and join the hack at https://aka.ms/raghack. No Purchase Necessary. Must be 18+ to enter. Contest ends 9/16/24.

• Want more hands-on RAG training? Visit the Reactor series home page to see all the RAGHack 2024 sessions!

RAG (Retrieval Augmented Generation) is the most common approach used to get LLMs to answer questions grounded in a particular domain's data. Azure AI Search is a powerful search engine, with many features designed specifically for RAG applications. We'll demonstrate optimal retrieval using hybrid search with the semantic ranker, show the new integrated vectorization feature for cloud-based data ingestion, and discuss vector storage optimization.

Presented by Farzad Sunavala, Product Manager on Azure AI Search, and Pamela Fox, Developer Advocate for Python

** Part of RAGHack, a free global hackathon to develop RAG applications. Join at https://aka.ms/raghack **

📌 Check out the RAGHack 2024 series here!

Pre-requisites: - Read the official rules and join the hack at https://aka.ms/raghack. No Purchase Necessary. Must be 18+ to enter. Contest ends 9/16/24.

• Want more hands-on RAG training? Visit the Reactor series home page to see all the RAGHack 2024 sessions!

RAG (Retrieval Augmented Generation) is the most common approach used to get LLMs to answer questions grounded in a particular domain's data. Azure AI Search is a powerful search engine, with many features designed specifically for RAG applications. We'll demonstrate optimal retrieval using hybrid search with the semantic ranker, show the new integrated vectorization feature for cloud-based data ingestion, and discuss vector storage optimization.

Presented by Farzad Sunavala, Product Manager on Azure AI Search, and Pamela Fox, Developer Advocate for Python

** Part of RAGHack, a free global hackathon to develop RAG applications. Join at https://aka.ms/raghack **

📌 Check out the RAGHack 2024 series here!

Pre-requisites: - Read the official rules and join the hack at https://aka.ms/raghack. No Purchase Necessary. Must be 18+ to enter. Contest ends 9/16/24.

• Want more hands-on RAG training? Visit the Reactor series home page to see all the RAGHack 2024 sessions!

RAG (Retrieval Augmented Generation) is the most common approach used to get LLMs to answer questions grounded in a particular domain's data. Learn how to develop apps using RAG with Python and the OpenAI SDK. We'll walk through our most popular RAG solution, showing the process of data ingestion with Azure Document Intelligence and AI Search, then walking through the RAG steps of query rewriting, hybrid search, and question answering. You'll learn how to easily bring your own data into the RAG solution, and how to customize the prompts and UI for your domain.

Presented by Pamela Fox, Developer Advocate for Python

** Part of RAGHack, a free global hackathon to develop RAG applications. Join at https://aka.ms/raghack **

📌 Check out the RAGHack 2024 series here!

Pre-requisites: - Read the official rules and join the hack at https://aka.ms/raghack. No Purchase Necessary. Must be 18+ to enter. Contest ends 9/16/24.

• Want more hands-on RAG training? Visit the Reactor series home page to see all the RAGHack 2024 sessions!

Join Dona Sarkar and Pamela Cortez as they discuss and demo responsible AI for copilot.

Join Dona Sarkar and Pamela Cortez as they discuss and demo responsible AI for copilot.