Search – talk-data.com

Title & Speakers	Event
Hands-On LLM Engineering with Python (Part 1) 2025-12-18 · 18:00 REGISTER BELOW FOR MORE AVAILABLE DATES! ↓↓↓↓↓ https://luma.com/stelios ----------------------------------------------------------------------------------- Who is this for? Students, developers, and anyone interested in using Large Language Models (LLMs) to build real software solutions with Python. Tired of vibe coding with AI tools? Want to actually understand and own your code, instead of relying on black-box magic? This session shows you how to build LLM systems properly, with full control and clear engineering principles. Who is leading the session? The session is led by Dr. Stelios Sotiriadis, CEO of Warestack, Associate Professor and MSc Programme Director at Birkbeck, University of London, specialising in cloud computing, distributed systems, and AI engineering. Stelios holds a PhD from the University of Derby, completed a postdoctoral fellowship at the University of Toronto, and has worked on industry and research projects with Huawei, IBM, Autodesk, and multiple startups. Since moving to London in 2018, he has been teaching at Birkbeck. In 2021, he founded Warestack, building software for startups around the world. What we’ll cover? A hands-on introduction to building software with LLMs using Python, Ollama, and LiteLLM, including: How LLMs, embeddings, and agents work. Calling local models with Ollama or cloud models (OpenAI, Gemini and more). Using LiteLLM for custom prompts and tool-calling. Building simple agents from scratch. Introduction to RAG (Retrieval-Augmented Generation). Working with vector databases (ChromaDB) and vector similarity search library (FAISS). Storing, searching, and retrieving embeddings. Introduction to Streamlit for interactive data apps. End-to-end examples you can run on your own machine. This session focuses on theory, fundamentals and real code you can re-use. Why LiteLLM? LiteLLM gives you low-level control to build custom LLM solutions your own way, without a heavy framework like LangChain, so you understand how everything works and design your own architecture. A dedicated LangChain session will follow for those who want to go further. What are the requirements? Bring a laptop with Python installed (Windows, macOS, or Linux), along with Visual Studio Code or a similar IDE, with at least 10GB of free disk space and 8GB of RAM*. This space is needed for running local models during the workshop.* If you don’t have a suitable laptop, please contact Stelios ([email protected]) before registering. What is the format? A 3-hour live session with: Interactive theory blocks Hands-on coding Step-by-step exercises Small group support Three 10-minute breaks Q&A and class quizzes This is a highly practical, hands-on class focused on code and building working LLM systems. What are the prerequisites? A good understanding of programming with Python is required (basic to intermediate level). I assume you are already comfortable writing Python scripts. What comes after? Participants will receive an optional mini capstone project with one-to-one personalised feedback. Is it just one session? This is the first session in a new sequence on applied AI, covering agents, RAG systems, vector databases, and production-ready LLM workflows. Later sessions will dive deeper into topics such as embeddings with deep neural networks, LangChain, advanced retrieval, and multi-agent architectures. You can decide afterwards whether you’d like to join future sessions. How many participants? To keep this interactive, only 15 spots are available. Please register as soon as possible.	Hands-On LLM Engineering with Python (Part 1)
How to make datamap web-apps of embedding vectors via open source tooling 2025-11-09 · 19:00 John Tigue Datamaps are ML-powered visualizations of high-dimensional data, and in this talk the data is collections of embedding vectors. Interactive datamaps run in-browser as web-apps, potentially without any code running on the web server. Datamap tech can be used to visualize, say, the entire collection of chunks in a RAG vector database. The best-of-breed tools of this new datamap technique are liberally licensed open source. This presentation is an introduction to building with those repos. The maths will be mentioned only in passing; the topic here is simply how-to with specific tools. Talk attendees will be learning about Python tools, which produce high-quality web UIs. DataMapPlot is the premiere tool for rendering a datamap as a web-app. Here is a live demo thereof: https://connoiter.com/datamap/cff30bc1-0576-44f0-a07c-60456e131b7b 00-25: Intro to datamaps 25-45: Pipeline architecture 45-55: demos touring such tools as UMAP, HDBSCAN, DataMapPlot, Toponomy, etc. 55-90: Group coding A Google account is required to log in to Google Colab, where participants can run the workshop notebooks. A Hugging Face API key (token) is needed to download Gemma models. AI/ML API Python RAG Vector DB	PyData Seattle 2025
RAG Apps with Python, SurrealDB & Streamlit 2025-07-09 · 17:00 An online session on building production-ready RAG apps using Python, SurrealDB, and Streamlit. Learn the fundamentals in pure Python before using a framework, how to manage multi-model data with SurrealDB, and how to build a front end for your RAG app with Streamlit. Python surrealdb streamlit	RAG apps using Python, SurrealDB and Streamlit
RAG Apps with Python, SurrealDB & Streamlit 2025-07-09 · 17:00 Overview of building production-ready RAG applications using only Python, SurrealDB, and Streamlit; covers fundamentals in pure Python, managing multi-model data with SurrealDB, and building a front end for a RAG app with Streamlit. Python surrealdb streamlit	RAG apps using Python, SurrealDB and Streamlit
The AI Showdown: Python, Rust & The Future of RAG 2025-03-25 · 18:30 Details Futures Forum is back in London! Explore the cutting-edge of Retrieval-Augmented Generation (RAG) through an exciting showdown between two powerful ecosystems: Python and Rust. Join us as we unpack the strengths and trade-offs of each language, illuminating the path forward in AI development. Whether you’re a seasoned Rust advocate, a Python enthusiast curious about what’s next, or an AI developer exploring your options, this event promises valuable insights and vibrant discussions about the future of AI tooling. Talks RAG Pipelines with Rig, Rust & SurrealDB - Joshua Mo\, DevRel Engineer @ Playgrounds RAG apps using Python, SurrealDB and Streamlit - Alexander Fridriksson\, Senior Product Marketing Manager @ SurrealDB Agenda 18:30 - 19:00 Welcome drinks & networking Grab a drink, explore the space and meet the SurrealDB team. 19:00 - 19:30 RAG Pipelines with Rig, Rust & SurrealDB Interested in Rust for AI? In this talk, we'll dive into how you can write RAG pipelines using Rig, a Rust AI framework that aims to prioritize developer experience. We'll also be discussing the state of the Rust AI/ML ecosystem. 19:30 - 20:00 Refreshments, pizza and networking 20:00 - 20:30 RAG apps using Python, SurrealDB and Streamlit This talk walks you through why LangChain might be weighing you down and how you can use pure Python - along with SurrealDB and Streamlit - to make production-ready AI apps effortlessly. 20:30 - 21:00 Wrap up & Networking 21:00 End of event -- About the speakers Joshua Mo - Joshua Mo is a DevRel Engineer at Playgrounds Analytics inc. He is currently maintaining the Rig agentic AI framework, as well as writing high-impact technical content to help drive Rust adoption. In his spare time, he contributes to FOSS software. Alexander Fridriksson - Alexander is a Senior Product Marketing Manager at SurrealDB\, where he's been involved with both the product and community from the start. Building out much of the messaging and education\, such as SurrealDB University. He has a wealth of experience from both a commercial (Marketing\, Sales\, Consulting) and Technical ( Analytics\, Data Science\, Data Engineering) perspective\, which he draws upon to help people solve the most challenging problems. FAQs Is the venue accessible? Absolutely! There is a lift that takes you up to Level 4 where the event is held. Is this event for me? SurrealDB events are for software engineers, developers, architects, data scientists, data engineers, or any tech professionals keen to discover more about SurrealDB: a scalable multi-model database that allows users and developers to focus on building their applications with ease and speed. Am I guaranteed a ticket at this event? Our events are tech-focused and in the interest of keeping our events relevant and meaningful for those attending, tickets are issued at our discretion. We therefore reserve the right to refund ticket orders before the event and to request proof of identity and/or professional background upon entry. Are there any House Rules? At SurrealDB, we are committed to providing live and online events that are safe and enjoyable for all attending. Please review our Code of Conduct and Privacy Policy for more information. It is compulsory for all attendees to be registered with a first and last name in order to attend. Any attendees who do not adhere to these requirements will be refused a ticket.	The AI Showdown: Python, Rust & The Future of RAG
The AI Showdown: Python, Rust & The Future of RAG 2025-03-25 · 18:30 Details Futures Forum is back in London! Explore the cutting-edge of Retrieval-Augmented Generation (RAG) through an exciting showdown between two powerful ecosystems: Python and Rust. Join us as we unpack the strengths and trade-offs of each language, illuminating the path forward in AI development. Whether you’re a seasoned Rust advocate, a Python enthusiast curious about what’s next, or an AI developer exploring your options, this event promises valuable insights and vibrant discussions about the future of AI tooling. Talks RAG Pipelines with Rig, Rust & SurrealDB - Joshua Mo\, DevRel Engineer @ Playgrounds RAG apps using Python, SurrealDB and Streamlit - Alexander Fridriksson\, Senior Product Marketing Manager @ SurrealDB Agenda 18:30 - 19:00 Welcome drinks & networking Grab a drink, explore the space and meet the SurrealDB team. 19:00 - 19:30 RAG Pipelines with Rig, Rust & SurrealDB Interested in Rust for AI? In this talk, we'll dive into how you can write RAG pipelines using Rig, a Rust AI framework that aims to prioritize developer experience. We'll also be discussing the state of the Rust AI/ML ecosystem. 19:30 - 20:00 Refreshments, pizza and networking 20:00 - 20:30 RAG apps using Python, SurrealDB and Streamlit This talk walks you through why LangChain might be weighing you down and how you can use pure Python - along with SurrealDB and Streamlit - to make production-ready AI apps effortlessly. 20:30 - 21:00 Wrap up & Networking 21:00 End of event -- About the speakers Joshua Mo - Joshua Mo is a DevRel Engineer at Playgrounds Analytics inc. He is currently maintaining the Rig agentic AI framework, as well as writing high-impact technical content to help drive Rust adoption. In his spare time, he contributes to FOSS software. Alexander Fridriksson - Alexander is a Senior Product Marketing Manager at SurrealDB\, where he's been involved with both the product and community from the start. Building out much of the messaging and education\, such as SurrealDB University. He has a wealth of experience from both a commercial (Marketing\, Sales\, Consulting) and Technical ( Analytics\, Data Science\, Data Engineering) perspective\, which he draws upon to help people solve the most challenging problems. FAQs Is the venue accessible? Absolutely! There is a lift that takes you up to Level 4 where the event is held. Is this event for me? SurrealDB events are for software engineers, developers, architects, data scientists, data engineers, or any tech professionals keen to discover more about SurrealDB: a scalable multi-model database that allows users and developers to focus on building their applications with ease and speed. Am I guaranteed a ticket at this event? Our events are tech-focused and in the interest of keeping our events relevant and meaningful for those attending, tickets are issued at our discretion. We therefore reserve the right to refund ticket orders before the event and to request proof of identity and/or professional background upon entry. Are there any House Rules? At SurrealDB, we are committed to providing live and online events that are safe and enjoyable for all attending. Please review our Code of Conduct and Privacy Policy for more information. It is compulsory for all attendees to be registered with a first and last name in order to attend. Any attendees who do not adhere to these requirements will be refused a ticket.	The AI Showdown: Python, Rust & The Future of RAG
Evolving Responsibilities in AI Data Management 2025-02-16 · 16:09 Bartosz Mikulski – guest , Tobias Macey – host Summary In this episode of the Data Engineering Podcast Bartosz Mikulski talks about preparing data for AI applications. Bartosz shares his journey from data engineering to MLOps and emphasizes the importance of data testing over software development in AI contexts. He discusses the types of data assets required for AI applications, including extensive test datasets, especially in generative AI, and explains the differences in data requirements for various AI application styles. The conversation also explores the skills data engineers need to transition into AI, such as familiarity with vector databases and new data modeling strategies, and highlights the challenges of evolving AI applications, including frequent reprocessing of data when changing chunking strategies or embedding models. Announcements Hello and welcome to the Data Engineering Podcast, the show about modern data managementData migrations are brutal. They drag on for months—sometimes years—burning through resources and crushing team morale. Datafold's AI-powered Migration Agent changes all that. Their unique combination of AI code translation and automated data validation has helped companies complete migrations up to 10 times faster than manual approaches. And they're so confident in their solution, they'll actually guarantee your timeline in writing. Ready to turn your year-long migration into weeks? Visit dataengineeringpodcast.com/datafold today for the details. Your host is Tobias Macey and today I'm interviewing Bartosz Mikulski about how to prepare data for use in AI applicationsInterview IntroductionHow did you get involved in the area of data management?Can you start by outlining some of the main categories of data assets that are needed for AI applications?How does the nature of the application change those requirements? (e.g. RAG app vs. agent, etc.)How do the different assets map to the stages of the application lifecycle?What are some of the common roles and divisions of responsibility that you see in the construction and operation of a "typical" AI application?For data engineers who are used to data warehousing/BI, what are the skills that map to AI apps?What are some of the data modeling patterns that are needed to support AI apps?chunking strategies metadata managementWhat are the new categories of data that data engineers need to manage in the context of AI applications?agent memory generation/evolution conversation history managementdata collection for fine tuningWhat are some of the notable evolutions in the space of AI applications and their patterns that have happened in the past ~1-2 years that relate to the responsibilities of data engineers?What are some of the skills gaps that teams should be aware of and identify training opportunities for?What are the most interesting, innovative, or unexpected ways that you have seen data teams address the needs of AI applications?What are the most interesting, unexpected, or challenging lessons that you have learned while working on AI applications and their reliance on data?What are some of the emerging trends that you are paying particular attention to?Contact Info WebsiteLinkedInParting Question From your perspective, what is the biggest gap in the tooling or technology for data management today?Closing Announcements Thank you for listening! Don't forget to check out our other shows. Podcast.init covers the Python language, its community, and the innovative ways it is being used. The AI Engineering Podcast is your guide to the fast-moving world of building AI systems.Visit the site to subscribe to the show, sign up for the mailing list, and read the show notes.If you've learned something or tried out a project from the show then tell us about it! Email [email protected] with your story.Links SparkRayChunking StrategiesHypothetical document embeddingsModel Fine TuningPrompt CompressionThe intro and outro music is from The Hug by The Freak Fandango Orchestra / CC BY-SA AI/ML BI Data Engineering Data Management Data Modelling Datafold DWH GenAI MLOps Python RAG Vector DB	Data Engineering Podcast Listen
Internationalization for RAG apps 2024-09-09 · 23:00 Building a RAG app for a non-English audience? Fortunately, language models and embedding models is that they understand a wide range of languages. Unfortunately, they have a bias towards English, so you need to choose your approach carefully when deploying them in other languages. In this session, we'll dive into tokenization, optimal data chunking strategies, and other best practices for internationalization. Presented by Anthony Shaw, Python Cloud Advocate and Renee Noble, Regional Cloud 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!	Internationalization for RAG apps
Building RAG apps with Azure Cosmos DB for MongoDB 2024-09-05 · 17:00 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 build a RAG app using vCore-based Azure Cosmos DB for MongoDB and its new vector search capabilities. We'll walk through a Python web app that uses the LangChain package to orchestrate a RAG flow in order to answer questions about a restaurant's data. Presented by Khelan Modi, Product Manager on Azure Cosmos DB team, and John Aziz, Software Developer and Microsoft MVP 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!	Building RAG apps with Azure Cosmos DB for MongoDB
Building RAG apps with Azure Cosmos DB for MongoDB 2024-09-05 · 17:00 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 build a RAG app using vCore-based Azure Cosmos DB for MongoDB and its new vector search capabilities. We'll walk through a Python web app that uses the LangChain package to orchestrate a RAG flow in order to answer questions about a restaurant's data. Presented by Khelan Modi, Product Manager on Azure Cosmos DB team, and John Aziz, Software Developer and Microsoft MVP 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!	Building RAG apps with Azure Cosmos DB for MongoDB
Building RAG apps with Azure Cosmos DB for MongoDB 2024-09-05 · 17:00 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 build a RAG app using vCore-based Azure Cosmos DB for MongoDB and its new vector search capabilities. We'll walk through a Python web app that uses the LangChain package to orchestrate a RAG flow in order to answer questions about a restaurant's data. Presented by Khelan Modi, Product Manager on Azure Cosmos DB team, and John Aziz, Software Developer and Microsoft MVP 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!	Building RAG apps with Azure Cosmos DB for MongoDB
Building RAG apps with Langchain4J 2024-09-04 · 15:00 RAG (Retrieval Augmented Generation) is the most common approach used to get LLMs to answer questions grounded in a particular domain's data. Langchain4J is a great way to use large language models from Java, and is modeled on the most popular Python orchestrator, Langchain. Learn how to use Langchain4J to build a RAG solution, connecting to different LLMs, embedding models, and vector stores. We'll share multiple open-source solutions so that you can get started with Langchain4J today. Presented by Julien Dubois, Principal Manager of Java Developer Relations at Microsoft 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!	Building RAG apps with Langchain4J
Building RAG apps with Langchain4J 2024-09-04 · 15:00 RAG (Retrieval Augmented Generation) is the most common approach used to get LLMs to answer questions grounded in a particular domain's data. Langchain4J is a great way to use large language models from Java, and is modeled on the most popular Python orchestrator, Langchain. Learn how to use Langchain4J to build a RAG solution, connecting to different LLMs, embedding models, and vector stores. We'll share multiple open-source solutions so that you can get started with Langchain4J today. Presented by Julien Dubois, Principal Manager of Java Developer Relations at Microsoft 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!	Building RAG apps with Langchain4J
Building RAG apps with Langchain4J 2024-09-04 · 15:00 RAG (Retrieval Augmented Generation) is the most common approach used to get LLMs to answer questions grounded in a particular domain's data. Langchain4J is a great way to use large language models from Java, and is modeled on the most popular Python orchestrator, Langchain. Learn how to use Langchain4J to build a RAG solution, connecting to different LLMs, embedding models, and vector stores. We'll share multiple open-source solutions so that you can get started with Langchain4J today. Presented by Julien Dubois, Principal Manager of Java Developer Relations at Microsoft 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!	Building RAG apps with Langchain4J
Building RAG apps in Python 2024-09-03 · 22:00 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!	Building RAG apps in Python
Google I/O Extended 2024 London 2024-07-27 · 08:20 Google I/O Extended London is your chance to immerse yourself in the Google developer community right here in the heart of London. Organised by Google Developer Group (GDG) London, this event is open to anyone interested in Google technologies. Imagine experiencing the buzz of Google I/O, the company's major developer conference, without the need to travel across the globe. I/O Extended London brings that energy to you, offering a platform for: Technical Talks by Experts: Gain insights and practical knowledge through sessions led by Google developers and enthusiasts. Learn about the latest advancements in Android, Web, Cloud, AI, Machine Learning, and other cutting-edge areas. Deep Dives into Google Updates: Stay on top of the latest announcements and developments from Google. Get hands-on experience with new tools and platforms directly from those who build them. Networking with Fellow Developers: Connect with a vibrant community of developers based in London. Share knowledge, ideas, and experiences, and build lasting connections within the tech scene. Whether you're a seasoned programmer or just starting your development journey, Google I/O Extended London offers something for everyone. It's a fantastic opportunity to learn, network, and be part of the exciting world of Google technologies! Agenda 9:20 AM: Registration 9:50 AM: Opening Remarks 10:00 AM: Building beautiful camera experiences in Android by Tom Colvin Join me in this live-coding demo, together we're going to write a modern camera app for Android! Using the latest Jetpack CameraX library we can capture photos and videos super-easily. On the way we'll discuss: - The latest updates to CameraX as seen in Google I/O '24 - The smartest way to capture and preview images and video - How to use device-specific features like portrait mode, night mode and face retouching - Applying transformations such as rotations and cropping - or passing output to AI methods. 10:30 AM: Break 10:35 AM: Building an Exchange Rate Chatbot with Gemini Function Calling by Nishi Ajmera, Jyoti Katragadda This talk dives into Gemini Function Calling, a feature that empowers generative AI models to connect with external APIs. We'll build a real-time exchange rate chatbot using Python and the Gemini API. Learn how to define functions, call external APIs through Gemini, and create a user-friendly experience with the latest currency data. 11:05 AM: Break 11:10 AM: What you need to know about third-party cookies by Natalia Markoborodova Learn how to transition away from third-party cookies to privacy-preserving alternatives. Gain an understanding of the user options for third-party cookies, and learn how to audit cookie usage and test for breakage to ensure a smooth transition. 11:40 AM: Break 11:45 AM: Create your own Q&A System Using Python: Build a RAG Model for Answering Questions from ePubs with Gemini by Lisa Carpenter Learn how to utilise Gemini's fantastic APIs with Langchain, to chunk content from your favourite EPubs and build your very own RAG system that can accurately answer your questions! 12:45 PM: Lunch 1:45 PM: Complement your media editing pipeline with Media3 by Kristina Simakova Learn how to use Media3 Editing libraries to edit, trim, concatenate and apply effects to video frames on Android. Implementing video editing has always been a challenge for Android developers. Media3 is a jetpack library that is meant to make video editing easy, performant and reliable. In this session you will learn about Transformer APIs, how to apply effects and concatenate multiple media files. 2:15 PM: Break 2:20 PM: From Pixels to Meaning: The Evolving Landscape of Computer Vision with Google AI by Roushanak Rahmat The ability of machines to understand visual information has come a long way. This talk will explore the fascinating journey of computer vision, from the early days of image processing to the cutting-edge world of vision language models. We'll see how advancements in deep learning have revolutionised how machines "see" and interpret the world. We'll also delve into Google's contributions to this field and its application in projects like Imagen are pushing the boundaries of what's possible. Get ready to discover how computers are learning to not only see the world, but also understand and interact with it in new and exciting ways. 2:50 PM: Break 2:55 PM: Crafting Creative Prompts and Developing Flutter Apps with AI: Structuring Response Schema by Renuka Kelkar, Sumith Damodaran Join us for an interactive session on using AI to enhance your Flutter app development. Learn how to craft creative prompts with Gemini and structure responses using JSON. We'll demonstrate practical techniques to generate code, UI elements, and more, making your development process faster and more efficient. This session is perfect for developers looking to integrate AI into their workflow and boost productivity. Above are our talk details 3:25 PM: Break 3:30 PM: Closing Remarks 3:45 PM: Leaving the building Speakers Natalia Markoborodova - Google (Developer Relations Engineer) Natalia is a Developer Relations Engineer for the Privacy Sandbox initiatives @ Google. She's actively involved in facilitating the transition away from third-party cookies and shaping the future of online identity solutions. Kristina Simakova - Google (Engineering Manager) Kristina is an Engineering Manager at Google. She is managing Android Media Editing team. The team is working on Media3 Editing Tom Colvin - Apptaura (CTO) Tom Colvin is CTO of Apptaura, the app development specialists; and Conseal Security, the mobile app security experts. He has been a developer for over 20 years and worked with Android since Cupcake. He is a Google Developer Expert in Android Lisa Carpenter - Digital Futures (Data Science Instructor Lead) Lisa is the lead data science instructor at Digital Futures, with responsibility for the design of our Data Science programme and delivery of a world-class learning experience for our engineers. Lisa has over 10 years experience in the data industry. Lisa has worked with organisations to deliver value from their data, building technical solutions and statistical models to produce actionable in… Roushanak Rahmat - IBM (Data scientist) "Roushanak is an accomplished Data scientist at IBM with a wealth of experience in computer vision, medical imaging, and data science. With a PhD in AI from Heriot-Watt University in collaboration with the University of Edinburgh, she possesses deep expertise in developing advanced algorithms and models for healthcare applications. Her expertise spanned a range of areas including computer visi… Nishi Ajmera - Publicis Sapient (Lead Engineer) Lead Engineer at Publicis Sapient, AI enthusiast, and Women in Tech Ambassador. With a passion for Gen AI, I have delivered multiple talks on the workings of Large Language Models (LLMs), sharing insights into this rapidly evolving field. My expertise spans both technical implementation and the broader implications of AI in today's digital landscape. As a Women in Tech Ambassador, I am also co… Jyoti Katragadda - Publicis Sapient (Technical Lead) Jyoti Katragadda is a seasoned Technical Lead at Publicis Sapient, where she expertly navigates the complex responsibilities of a senior technologist. With a fervent drive for innovation and a keen eye for architectural design and system optimization, Jyoti is at the forefront of adopting new technologies to propel projects to success. Jyoti's career is marked by notable achievements tha… Renuka Kelkar - TechPowerGirtls (Founder) Renuka is the founder of @TechPowerGirtls! She has 15+ years of experience in Web design and development, with the last 2+ years in Mobile App development with Flutter/DART! Her main focus is building the Flutter Community for Tech Moms! My Talk will give different options available in the market to create Responsive WebApp, Navigation in the web & deploying the App with different Hosting opt… Sumith Damodaran Hosts Caroline Veloso - The Arch Company (Junior Software Developer) I'm from Brazil and I completed a coding bootcamp. In my free time, I run a social media account focused on tech and I'm interested in expanding my knowledge in biotechnology. Ishita Narsiker - Amazon (Business Intelligence Engineer) Ishita has been actively involved in Google communities since DevFest 2022, serving as a GDG Glasgow organiser and a former GDSC Lead. She is currently pursuing her Master's degree in Computer Science while working as a Business Intelligence Engineer at Amazon. With a keen interest in Frontend web development and Large Language Model applications, Ishita enjoys combining her passion for techno… Complete your event RSVP here: https://gdg.community.dev/events/details/google-gdg-london-presents-google-io-extended-2024-london/.	Google I/O Extended 2024 London
MLOps London July 2024 - Talks on Vector Databases, LLMs, and Python Packaging 2024-07-23 · 17:00 Livestream (Zoom): https://us02web.zoom.us/j/87027601120?pwd=cLtUUlDoNCYSiVqW2ywI5XqWZmAFWj.1 In Person Form: https://forms.gle/jAzzhJcsX62kUNtw6 * MLOps London is back again in July 2024 with talks on vector databases, LLMs, and Python Packaging. The plan, as usual, is to run another hybrid event so please come along in person if you're local or need an excuse to travel to London, or join us live otherwise. ⚠️ Don't forget to fill out the form above if you are coming to the in-person event. The venue needs the list of attendees to let you in. ⚠️ AGENDA: ⏱️ 6:00 pm onwards - Arrival, drinks, food, and networking ⏱️ 6:30 pm - Kick off and welcome ⏱️ 6:35 pm The Evolutionary Saga of Python Packaging Quazi Nafiul Islam - Developer Advocate at Sonar Join us on a journey through the evolution of Python packaging, where we'll untangle the web of tools and formats that have shaped Python development. From the humble beginnings of Eggs to the sophisticated elegance of Poetry, this talk is a tribute to the ingenuity of the Python community. Along the way, we'll nod to Conda's cameo, recognising its unique contribution to making scientific packages more accessible. This story is for anyone who's ever wondered about the magic behind pip install and why packaging is so hard to get right in the Python world. ⏱️ 7:15 pm - Drinks, food, and networking ⏱️ 7:30 pm Let’s build a vector search application with Python and Elasticsearch Miguel Grinberg - Principal Software Engineer at Elastic In this presentation Miguel is going to live code a complete vector search application with Elasticsearch and the Python Elasticsearch-DSL client. ⏱️ 8:15 pm - Break ⏱️ 8:25 pm What Nobody Tells You About Building LLM Products Ed Shee - AI Engineer & Founder @ Ignitus Curious about building awesome apps with Large Language Models (LLMs)? Come join Ed as he shares everything he wishes he knew before he got started. This talk is packed with real-world insights, including: Clever techniques for Retrieval-Augmented Generation (RAG) Crafting prompts that actually work Keeping LLMs on track and under control Ensuring your text outputs are top-notch Building smart and efficient agents Plus, Ed will give you a look into the future of LLM apps and what to expect next. Whether you're new to the game or a seasoned developer, you'll leave with practical tips and fresh ideas to power up your projects. ⏱️ 9:00 pm - Wrap Up, aka Adios 👋 :) * ⚠️ If you are attending in person please complete the registration form (link at the top of this description). ⚠️	MLOps London July 2024 - Talks on Vector Databases, LLMs, and Python Packaging
VS Code Day 2024 2024-04-24 · 17:00 VS Code Day is our annual event where you'll learn how to elevate your development workflow with the latest and greatest features of VS Code. This year, we’re excited to delve into AI and you’ll hear from the VS Code team and other industry experts on topics like AI-powered programming with GitHub Copilot, building and deploying generative AI apps to the cloud, enhancing the C# development experience, and more. Whether you’re just starting out or you’re an experienced developer, join us on April 24, 2024 for a day focused on the editor that lets you code anything, cross-platform and free! SESSIONS Welcome to VS Code Day 2024 with Gwyneth Peña-Siguenza and Reynald Adolphe View Source: What gets into VS Code and why with Burke Holland JavaScript developers: Build fast and have fun with VS Code and Azure AI CLI with Natalia Venditto Generating Synthetic Datasets with GitHub Copilot with Alfredo Deza Real World Development with VS Code and C# with Scott Hanselman and Leslie Richardson Building a RAG-powered AI chat app with Python and VS Code with Pamela Fox Beyond the Editor: Tips to get the Most out of GitHub Copilot with Kedasha Kerr LangChain Examples with Azure OpenAI Service + VS Code with Rishab Kumar AI Made Clear: Practical AI Coding Sessions in VS Code with Bruno Capuano Asking Copilot about your workspace with Matt Bierner Pre-requisites: Resources we think you may find useful related to VS Code Day 2024: LinkedIn Clone Repo - https://aka.ms/linkedin-clone VS Code Day Cloud Skills Challenge - https://aka.ms/VSCodeDayChallenge	VS Code Day 2024

Hands-On LLM Engineering with Python (Part 1) 2025-12-18 · 18:00

REGISTER BELOW FOR MORE AVAILABLE DATES! ↓↓↓↓↓ https://luma.com/stelios

-----------------------------------------------------------------------------------

Who is this for?

Students, developers, and anyone interested in using Large Language Models (LLMs) to build real software solutions with ** Python.

Tired of vibe coding with AI tools? Want to actually understand and own your code, instead of relying on black-box magic? This session shows you how to build LLM systems properly, with full control and clear engineering principles. Who is leading the session?

The session is led by Dr. Stelios Sotiriadis, CEO of Warestack, Associate Professor and MSc Programme Director at Birkbeck, University of London, specialising in cloud computing, distributed systems, and AI engineering.

Stelios holds a PhD from the University of Derby, completed a postdoctoral fellowship at the University of Toronto, and has worked on industry and research projects with Huawei, IBM, Autodesk, and multiple startups. Since moving to London in 2018, he has been teaching at Birkbeck. In 2021, he founded Warestack, building software for startups around the world. What we’ll cover?

A hands-on introduction to building software with LLMs using Python, Ollama, and LiteLLM, including:

How LLMs, embeddings, and agents work.
Calling local models with Ollama or cloud models (OpenAI, Gemini and more).
Using LiteLLM for custom prompts and tool-calling.
Building simple agents from scratch.
Introduction to RAG (Retrieval-Augmented Generation).
Working with vector databases (ChromaDB) and vector similarity search library (FAISS).
Storing, searching, and retrieving embeddings.
Introduction to Streamlit for interactive data apps.
End-to-end examples you can run on your own machine.

This session focuses on theory, fundamentals and real code you can re-use.

Why LiteLLM?

LiteLLM gives you low-level control to build custom LLM solutions your own way, without a heavy framework like LangChain, so you understand how everything works and design your own architecture. A dedicated LangChain session will follow for those who want to go further.

What are the requirements?

Bring a laptop with Python installed (Windows, macOS, or Linux), along with Visual Studio Code or a similar IDE, with at least 10GB of free disk space and 8GB of RAM.

This space is needed for running local models during the workshop. If you don’t have a suitable laptop, please contact Stelios ([email protected]) before registering.

What is the format?

A 3-hour live session with:

Interactive theory blocks
Hands-on coding
Step-by-step exercises
Small group support
Three 10-minute breaks
Q&A and class quizzes

This is a highly practical, hands-on class focused on code and building working LLM systems.

What are the prerequisites?

A good understanding of programming with Python is required (basic to intermediate level). I assume you are already comfortable writing Python scripts.

What comes after?

Participants will receive an optional mini capstone project with one-to-one personalised feedback.

Is it just one session?

This is the first session in a new sequence on applied AI, covering agents, RAG systems, vector databases, and production-ready LLM workflows. Later sessions will dive deeper into topics such as embeddings with deep neural networks, LangChain, advanced retrieval, and multi-agent architectures.

You can decide afterwards whether you’d like to join future sessions.

How many participants?

To keep this interactive, only 15 spots are available. Please register as soon as possible.

Hands-On LLM Engineering with Python (Part 1)

How to make datamap web-apps of embedding vectors via open source tooling 2025-11-09 · 19:00

John Tigue

Datamaps are ML-powered visualizations of high-dimensional data, and in this talk the data is collections of embedding vectors. Interactive datamaps run in-browser as web-apps, potentially without any code running on the web server. Datamap tech can be used to visualize, say, the entire collection of chunks in a RAG vector database.

The best-of-breed tools of this new datamap technique are liberally licensed open source. This presentation is an introduction to building with those repos. The maths will be mentioned only in passing; the topic here is simply how-to with specific tools. Talk attendees will be learning about Python tools, which produce high-quality web UIs.

DataMapPlot is the premiere tool for rendering a datamap as a web-app. Here is a live demo thereof: https://connoiter.com/datamap/cff30bc1-0576-44f0-a07c-60456e131b7b

00-25: Intro to datamaps 25-45: Pipeline architecture 45-55: demos touring such tools as UMAP, HDBSCAN, DataMapPlot, Toponomy, etc. 55-90: Group coding

A Google account is required to log in to Google Colab, where participants can run the workshop notebooks. A Hugging Face API key (token) is needed to download Gemma models.

AI/ML API Python RAG Vector DB

PyData Seattle 2025

RAG Apps with Python, SurrealDB & Streamlit 2025-07-09 · 17:00

An online session on building production-ready RAG apps using Python, SurrealDB, and Streamlit. Learn the fundamentals in pure Python before using a framework, how to manage multi-model data with SurrealDB, and how to build a front end for your RAG app with Streamlit.

Python surrealdb streamlit

RAG apps using Python, SurrealDB and Streamlit

RAG Apps with Python, SurrealDB & Streamlit 2025-07-09 · 17:00

Overview of building production-ready RAG applications using only Python, SurrealDB, and Streamlit; covers fundamentals in pure Python, managing multi-model data with SurrealDB, and building a front end for a RAG app with Streamlit.

Python surrealdb streamlit

RAG apps using Python, SurrealDB and Streamlit

The AI Showdown: Python, Rust & The Future of RAG 2025-03-25 · 18:30

Details

Futures Forum is back in London!

Explore the cutting-edge of Retrieval-Augmented Generation (RAG) through an exciting showdown between two powerful ecosystems: Python and Rust. Join us as we unpack the strengths and trade-offs of each language, illuminating the path forward in AI development.

Whether you’re a seasoned Rust advocate, a Python enthusiast curious about what’s next, or an AI developer exploring your options, this event promises valuable insights and vibrant discussions about the future of AI tooling.

Talks

RAG Pipelines with Rig, Rust & SurrealDB - Joshua Mo\, DevRel Engineer @ Playgrounds
RAG apps using Python, SurrealDB and Streamlit - Alexander Fridriksson\, Senior Product Marketing Manager @ SurrealDB

Agenda

18:30 - 19:00 Welcome drinks & networking Grab a drink, explore the space and meet the SurrealDB team.

19:00 - 19:30 RAG Pipelines with Rig, Rust & SurrealDB Interested in Rust for AI? In this talk, we'll dive into how you can write RAG pipelines using Rig, a Rust AI framework that aims to prioritize developer experience. We'll also be discussing the state of the Rust AI/ML ecosystem.

19:30 - 20:00 Refreshments, pizza and networking

20:00 - 20:30 RAG apps using Python, SurrealDB and Streamlit This talk walks you through why LangChain might be weighing you down and how you can use pure Python - along with SurrealDB and Streamlit - to make production-ready AI apps effortlessly.

20:30 - 21:00 Wrap up & Networking

21:00 End of event

--

About the speakers

Joshua Mo - Joshua Mo is a DevRel Engineer at Playgrounds Analytics inc. He is currently maintaining the Rig agentic AI framework, as well as writing high-impact technical content to help drive Rust adoption. In his spare time, he contributes to FOSS software.
Alexander Fridriksson - Alexander is a Senior Product Marketing Manager at SurrealDB\, where he's been involved with both the product and community from the start. Building out much of the messaging and education\, such as SurrealDB University. He has a wealth of experience from both a commercial (Marketing\, Sales\, Consulting) and Technical ( Analytics\, Data Science\, Data Engineering) perspective\, which he draws upon to help people solve the most challenging problems.

FAQs

Is the venue accessible? Absolutely! There is a lift that takes you up to Level 4 where the event is held.

Is this event for me? SurrealDB events are for software engineers, developers, architects, data scientists, data engineers, or any tech professionals keen to discover more about SurrealDB: a scalable multi-model database that allows users and developers to focus on building their applications with ease and speed.

Am I guaranteed a ticket at this event? Our events are tech-focused and in the interest of keeping our events relevant and meaningful for those attending, tickets are issued at our discretion. We therefore reserve the right to refund ticket orders before the event and to request proof of identity and/or professional background upon entry.

Are there any House Rules? At SurrealDB, we are committed to providing live and online events that are safe and enjoyable for all attending. Please review our Code of Conduct and Privacy Policy for more information. It is compulsory for all attendees to be registered with a first and last name in order to attend. Any attendees who do not adhere to these requirements will be refused a ticket.

The AI Showdown: Python, Rust & The Future of RAG

The AI Showdown: Python, Rust & The Future of RAG 2025-03-25 · 18:30

Details

Futures Forum is back in London!

Explore the cutting-edge of Retrieval-Augmented Generation (RAG) through an exciting showdown between two powerful ecosystems: Python and Rust. Join us as we unpack the strengths and trade-offs of each language, illuminating the path forward in AI development.

Whether you’re a seasoned Rust advocate, a Python enthusiast curious about what’s next, or an AI developer exploring your options, this event promises valuable insights and vibrant discussions about the future of AI tooling.

Talks

RAG Pipelines with Rig, Rust & SurrealDB - Joshua Mo\, DevRel Engineer @ Playgrounds
RAG apps using Python, SurrealDB and Streamlit - Alexander Fridriksson\, Senior Product Marketing Manager @ SurrealDB

Agenda

18:30 - 19:00 Welcome drinks & networking Grab a drink, explore the space and meet the SurrealDB team.

19:00 - 19:30 RAG Pipelines with Rig, Rust & SurrealDB Interested in Rust for AI? In this talk, we'll dive into how you can write RAG pipelines using Rig, a Rust AI framework that aims to prioritize developer experience. We'll also be discussing the state of the Rust AI/ML ecosystem.

19:30 - 20:00 Refreshments, pizza and networking

20:00 - 20:30 RAG apps using Python, SurrealDB and Streamlit This talk walks you through why LangChain might be weighing you down and how you can use pure Python - along with SurrealDB and Streamlit - to make production-ready AI apps effortlessly.

20:30 - 21:00 Wrap up & Networking

21:00 End of event

--

About the speakers

Joshua Mo - Joshua Mo is a DevRel Engineer at Playgrounds Analytics inc. He is currently maintaining the Rig agentic AI framework, as well as writing high-impact technical content to help drive Rust adoption. In his spare time, he contributes to FOSS software.
Alexander Fridriksson - Alexander is a Senior Product Marketing Manager at SurrealDB\, where he's been involved with both the product and community from the start. Building out much of the messaging and education\, such as SurrealDB University. He has a wealth of experience from both a commercial (Marketing\, Sales\, Consulting) and Technical ( Analytics\, Data Science\, Data Engineering) perspective\, which he draws upon to help people solve the most challenging problems.

FAQs

Is the venue accessible? Absolutely! There is a lift that takes you up to Level 4 where the event is held.

Is this event for me? SurrealDB events are for software engineers, developers, architects, data scientists, data engineers, or any tech professionals keen to discover more about SurrealDB: a scalable multi-model database that allows users and developers to focus on building their applications with ease and speed.

Am I guaranteed a ticket at this event? Our events are tech-focused and in the interest of keeping our events relevant and meaningful for those attending, tickets are issued at our discretion. We therefore reserve the right to refund ticket orders before the event and to request proof of identity and/or professional background upon entry.

Are there any House Rules? At SurrealDB, we are committed to providing live and online events that are safe and enjoyable for all attending. Please review our Code of Conduct and Privacy Policy for more information. It is compulsory for all attendees to be registered with a first and last name in order to attend. Any attendees who do not adhere to these requirements will be refused a ticket.

The AI Showdown: Python, Rust & The Future of RAG

Evolving Responsibilities in AI Data Management 2025-02-16 · 16:09

Bartosz Mikulski – guest , Tobias Macey – host

Summary In this episode of the Data Engineering Podcast Bartosz Mikulski talks about preparing data for AI applications. Bartosz shares his journey from data engineering to MLOps and emphasizes the importance of data testing over software development in AI contexts. He discusses the types of data assets required for AI applications, including extensive test datasets, especially in generative AI, and explains the differences in data requirements for various AI application styles. The conversation also explores the skills data engineers need to transition into AI, such as familiarity with vector databases and new data modeling strategies, and highlights the challenges of evolving AI applications, including frequent reprocessing of data when changing chunking strategies or embedding models.

Announcements Hello and welcome to the Data Engineering Podcast, the show about modern data managementData migrations are brutal. They drag on for months—sometimes years—burning through resources and crushing team morale. Datafold's AI-powered Migration Agent changes all that. Their unique combination of AI code translation and automated data validation has helped companies complete migrations up to 10 times faster than manual approaches. And they're so confident in their solution, they'll actually guarantee your timeline in writing. Ready to turn your year-long migration into weeks? Visit dataengineeringpodcast.com/datafold today for the details. Your host is Tobias Macey and today I'm interviewing Bartosz Mikulski about how to prepare data for use in AI applicationsInterview IntroductionHow did you get involved in the area of data management?Can you start by outlining some of the main categories of data assets that are needed for AI applications?How does the nature of the application change those requirements? (e.g. RAG app vs. agent, etc.)How do the different assets map to the stages of the application lifecycle?What are some of the common roles and divisions of responsibility that you see in the construction and operation of a "typical" AI application?For data engineers who are used to data warehousing/BI, what are the skills that map to AI apps?What are some of the data modeling patterns that are needed to support AI apps?chunking strategies metadata managementWhat are the new categories of data that data engineers need to manage in the context of AI applications?agent memory generation/evolution conversation history managementdata collection for fine tuningWhat are some of the notable evolutions in the space of AI applications and their patterns that have happened in the past ~1-2 years that relate to the responsibilities of data engineers?What are some of the skills gaps that teams should be aware of and identify training opportunities for?What are the most interesting, innovative, or unexpected ways that you have seen data teams address the needs of AI applications?What are the most interesting, unexpected, or challenging lessons that you have learned while working on AI applications and their reliance on data?What are some of the emerging trends that you are paying particular attention to?Contact Info WebsiteLinkedInParting Question From your perspective, what is the biggest gap in the tooling or technology for data management today?Closing Announcements Thank you for listening! Don't forget to check out our other shows. Podcast.init covers the Python language, its community, and the innovative ways it is being used. The AI Engineering Podcast is your guide to the fast-moving world of building AI systems.Visit the site to subscribe to the show, sign up for the mailing list, and read the show notes.If you've learned something or tried out a project from the show then tell us about it! Email [email protected] with your story.Links SparkRayChunking StrategiesHypothetical document embeddingsModel Fine TuningPrompt CompressionThe intro and outro music is from The Hug by The Freak Fandango Orchestra / CC BY-SA

AI/ML BI Data Engineering Data Management Data Modelling Datafold DWH GenAI MLOps Python RAG Vector DB

Data Engineering Podcast

Listen

Internationalization for RAG apps 2024-09-09 · 23:00

Building a RAG app for a non-English audience? Fortunately, language models and embedding models is that they understand a wide range of languages. Unfortunately, they have a bias towards English, so you need to choose your approach carefully when deploying them in other languages. In this session, we'll dive into tokenization, optimal data chunking strategies, and other best practices for internationalization.

Presented by Anthony Shaw, Python Cloud Advocate and Renee Noble, Regional Cloud 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!

Internationalization for RAG apps

Building RAG apps with Azure Cosmos DB for MongoDB 2024-09-05 · 17:00

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 build a RAG app using vCore-based Azure Cosmos DB for MongoDB and its new vector search capabilities. We'll walk through a Python web app that uses the LangChain package to orchestrate a RAG flow in order to answer questions about a restaurant's data.

Presented by Khelan Modi, Product Manager on Azure Cosmos DB team, and John Aziz, Software Developer and Microsoft MVP

** 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!

Building RAG apps with Azure Cosmos DB for MongoDB

Building RAG apps with Azure Cosmos DB for MongoDB 2024-09-05 · 17:00

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 build a RAG app using vCore-based Azure Cosmos DB for MongoDB and its new vector search capabilities. We'll walk through a Python web app that uses the LangChain package to orchestrate a RAG flow in order to answer questions about a restaurant's data.

Presented by Khelan Modi, Product Manager on Azure Cosmos DB team, and John Aziz, Software Developer and Microsoft MVP

** 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!

Building RAG apps with Azure Cosmos DB for MongoDB

Building RAG apps with Azure Cosmos DB for MongoDB 2024-09-05 · 17:00

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 build a RAG app using vCore-based Azure Cosmos DB for MongoDB and its new vector search capabilities. We'll walk through a Python web app that uses the LangChain package to orchestrate a RAG flow in order to answer questions about a restaurant's data.

Presented by Khelan Modi, Product Manager on Azure Cosmos DB team, and John Aziz, Software Developer and Microsoft MVP

** 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!

Building RAG apps with Azure Cosmos DB for MongoDB

Building RAG apps with Langchain4J 2024-09-04 · 15:00

RAG (Retrieval Augmented Generation) is the most common approach used to get LLMs to answer questions grounded in a particular domain's data. Langchain4J is a great way to use large language models from Java, and is modeled on the most popular Python orchestrator, Langchain. Learn how to use Langchain4J to build a RAG solution, connecting to different LLMs, embedding models, and vector stores. We'll share multiple open-source solutions so that you can get started with Langchain4J today.

Presented by Julien Dubois, Principal Manager of Java Developer Relations at Microsoft

** 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!

Building RAG apps with Langchain4J

Building RAG apps with Langchain4J 2024-09-04 · 15:00

RAG (Retrieval Augmented Generation) is the most common approach used to get LLMs to answer questions grounded in a particular domain's data. Langchain4J is a great way to use large language models from Java, and is modeled on the most popular Python orchestrator, Langchain. Learn how to use Langchain4J to build a RAG solution, connecting to different LLMs, embedding models, and vector stores. We'll share multiple open-source solutions so that you can get started with Langchain4J today.

Presented by Julien Dubois, Principal Manager of Java Developer Relations at Microsoft

** 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!

Building RAG apps with Langchain4J

Building RAG apps with Langchain4J 2024-09-04 · 15:00

RAG (Retrieval Augmented Generation) is the most common approach used to get LLMs to answer questions grounded in a particular domain's data. Langchain4J is a great way to use large language models from Java, and is modeled on the most popular Python orchestrator, Langchain. Learn how to use Langchain4J to build a RAG solution, connecting to different LLMs, embedding models, and vector stores. We'll share multiple open-source solutions so that you can get started with Langchain4J today.

Presented by Julien Dubois, Principal Manager of Java Developer Relations at Microsoft

** 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!

Building RAG apps with Langchain4J

Building RAG apps in Python 2024-09-03 · 22:00

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!

Building RAG apps in Python

Google I/O Extended 2024 London 2024-07-27 · 08:20

Google I/O Extended London is your chance to immerse yourself in the Google developer community right here in the heart of London. Organised by Google Developer Group (GDG) London, this event is open to anyone interested in Google technologies. Imagine experiencing the buzz of Google I/O, the company's major developer conference, without the need to travel across the globe. I/O Extended London brings that energy to you, offering a platform for:

Technical Talks by Experts: Gain insights and practical knowledge through sessions led by Google developers and enthusiasts. Learn about the latest advancements in Android, Web, Cloud, AI, Machine Learning, and other cutting-edge areas.

Deep Dives into Google Updates: Stay on top of the latest announcements and developments from Google. Get hands-on experience with new tools and platforms directly from those who build them.

Networking with Fellow Developers: Connect with a vibrant community of developers based in London. Share knowledge, ideas, and experiences, and build lasting connections within the tech scene.

Whether you're a seasoned programmer or just starting your development journey, Google I/O Extended London offers something for everyone. It's a fantastic opportunity to learn, network, and be part of the exciting world of Google technologies!

Agenda

9:20 AM: Registration

9:50 AM: Opening Remarks

10:00 AM: Building beautiful camera experiences in Android by Tom Colvin

Join me in this live-coding demo, together we're going to write a modern camera app for Android! Using the latest Jetpack CameraX library we can capture photos and videos super-easily. On the way we'll discuss: - The latest updates to CameraX as seen in Google I/O '24 - The smartest way to capture and preview images and video - How to use device-specific features like portrait mode, night mode and face retouching - Applying transformations such as rotations and cropping - or passing output to AI methods.

10:30 AM: Break

10:35 AM: Building an Exchange Rate Chatbot with Gemini Function Calling by Nishi Ajmera, Jyoti Katragadda

This talk dives into Gemini Function Calling, a feature that empowers generative AI models to connect with external APIs. We'll build a real-time exchange rate chatbot using Python and the Gemini API. Learn how to define functions, call external APIs through Gemini, and create a user-friendly experience with the latest currency data.

11:05 AM: Break

11:10 AM: What you need to know about third-party cookies by Natalia Markoborodova

Learn how to transition away from third-party cookies to privacy-preserving alternatives. Gain an understanding of the user options for third-party cookies, and learn how to audit cookie usage and test for breakage to ensure a smooth transition.

11:40 AM: Break

11:45 AM: Create your own Q&A System Using Python: Build a RAG Model for Answering Questions from ePubs with Gemini by Lisa Carpenter

Learn how to utilise Gemini's fantastic APIs with Langchain, to chunk content from your favourite EPubs and build your very own RAG system that can accurately answer your questions!

12:45 PM: Lunch

1:45 PM: Complement your media editing pipeline with Media3 by Kristina Simakova

Learn how to use Media3 Editing libraries to edit, trim, concatenate and apply effects to video frames on Android. Implementing video editing has always been a challenge for Android developers. Media3 is a jetpack library that is meant to make video editing easy, performant and reliable. In this session you will learn about Transformer APIs, how to apply effects and concatenate multiple media files.

2:15 PM: Break

2:20 PM: From Pixels to Meaning: The Evolving Landscape of Computer Vision with Google AI by Roushanak Rahmat

The ability of machines to understand visual information has come a long way. This talk will explore the fascinating journey of computer vision, from the early days of image processing to the cutting-edge world of vision language models. We'll see how advancements in deep learning have revolutionised how machines "see" and interpret the world. We'll also delve into Google's contributions to this field and its application in projects like Imagen are pushing the boundaries of what's possible. Get ready to discover how computers are learning to not only see the world, but also understand and interact with it in new and exciting ways.

2:50 PM: Break

2:55 PM: Crafting Creative Prompts and Developing Flutter Apps with AI: Structuring Response Schema by Renuka Kelkar, Sumith Damodaran

Join us for an interactive session on using AI to enhance your Flutter app development. Learn how to craft creative prompts with Gemini and structure responses using JSON. We'll demonstrate practical techniques to generate code, UI elements, and more, making your development process faster and more efficient. This session is perfect for developers looking to integrate AI into their workflow and boost productivity. Above are our talk details

3:25 PM: Break

3:30 PM: Closing Remarks

3:45 PM: Leaving the building

Speakers

Natalia Markoborodova - Google (Developer Relations Engineer)

Natalia is a Developer Relations Engineer for the Privacy Sandbox initiatives @ Google. She's actively involved in facilitating the transition away from third-party cookies and shaping the future of online identity solutions.

Kristina Simakova - Google (Engineering Manager)

Kristina is an Engineering Manager at Google. She is managing Android Media Editing team. The team is working on Media3 Editing

Tom Colvin - Apptaura (CTO)

Tom Colvin is CTO of Apptaura, the app development specialists; and Conseal Security, the mobile app security experts. He has been a developer for over 20 years and worked with Android since Cupcake. He is a Google Developer Expert in Android

Lisa Carpenter - Digital Futures (Data Science Instructor Lead)

Lisa is the lead data science instructor at Digital Futures, with responsibility for the design of our Data Science programme and delivery of a world-class learning experience for our engineers. Lisa has over 10 years experience in the data industry. Lisa has worked with organisations to deliver value from their data, building technical solutions and statistical models to produce actionable in…

Roushanak Rahmat - IBM (Data scientist)

"Roushanak is an accomplished Data scientist at IBM with a wealth of experience in computer vision, medical imaging, and data science. With a PhD in AI from Heriot-Watt University in collaboration with the University of Edinburgh, she possesses deep expertise in developing advanced algorithms and models for healthcare applications. Her expertise spanned a range of areas including computer visi…

Nishi Ajmera - Publicis Sapient (Lead Engineer)

Lead Engineer at Publicis Sapient, AI enthusiast, and Women in Tech Ambassador. With a passion for Gen AI, I have delivered multiple talks on the workings of Large Language Models (LLMs), sharing insights into this rapidly evolving field. My expertise spans both technical implementation and the broader implications of AI in today's digital landscape. As a Women in Tech Ambassador, I am also co…

Jyoti Katragadda - Publicis Sapient (Technical Lead)

Jyoti Katragadda is a seasoned Technical Lead at Publicis Sapient, where she expertly navigates the complex responsibilities of a senior technologist. With a fervent drive for innovation and a keen eye for architectural design and system optimization, Jyoti is at the forefront of adopting new technologies to propel projects to success. Jyoti's career is marked by notable achievements tha…

Renuka Kelkar - TechPowerGirtls (Founder)

Renuka is the founder of @TechPowerGirtls! She has 15+ years of experience in Web design and development, with the last 2+ years in Mobile App development with Flutter/DART! Her main focus is building the Flutter Community for Tech Moms! My Talk will give different options available in the market to create Responsive WebApp, Navigation in the web & deploying the App with different Hosting opt…

Sumith Damodaran

Hosts

Caroline Veloso - The Arch Company (Junior Software Developer)

I'm from Brazil and I completed a coding bootcamp. In my free time, I run a social media account focused on tech and I'm interested in expanding my knowledge in biotechnology.

Ishita Narsiker - Amazon (Business Intelligence Engineer)

Ishita has been actively involved in Google communities since DevFest 2022, serving as a GDG Glasgow organiser and a former GDSC Lead. She is currently pursuing her Master's degree in Computer Science while working as a Business Intelligence Engineer at Amazon. With a keen interest in Frontend web development and Large Language Model applications, Ishita enjoys combining her passion for techno…

Complete your event RSVP here: https://gdg.community.dev/events/details/google-gdg-london-presents-google-io-extended-2024-london/.

Google I/O Extended 2024 London

MLOps London July 2024 - Talks on Vector Databases, LLMs, and Python Packaging 2024-07-23 · 17:00

Livestream (Zoom): https://us02web.zoom.us/j/87027601120?pwd=cLtUUlDoNCYSiVqW2ywI5XqWZmAFWj.1 In Person Form: https://forms.gle/jAzzhJcsX62kUNtw6 ***

MLOps London is back again in July 2024 with talks on vector databases, LLMs, and Python Packaging. The plan, as usual, is to run another hybrid event so please come along in person if you're local or need an excuse to travel to London, or join us live otherwise.

⚠️ Don't forget to fill out the form above if you are coming to the in-person event. The venue needs the list of attendees to let you in. ⚠️

AGENDA: ⏱️ 6:00 pm onwards - Arrival, drinks, food, and networking ⏱️ 6:30 pm - Kick off and welcome ⏱️ 6:35 pm The Evolutionary Saga of Python Packaging Quazi Nafiul Islam - Developer Advocate at Sonar Join us on a journey through the evolution of Python packaging, where we'll untangle the web of tools and formats that have shaped Python development. From the humble beginnings of Eggs to the sophisticated elegance of Poetry, this talk is a tribute to the ingenuity of the Python community. Along the way, we'll nod to Conda's cameo, recognising its unique contribution to making scientific packages more accessible. This story is for anyone who's ever wondered about the magic behind pip install and why packaging is so hard to get right in the Python world.

⏱️ 7:15 pm - Drinks, food, and networking

⏱️ 7:30 pm Let’s build a vector search application with Python and Elasticsearch Miguel Grinberg - Principal Software Engineer at Elastic In this presentation Miguel is going to live code a complete vector search application with Elasticsearch and the Python Elasticsearch-DSL client.

⏱️ 8:15 pm - Break

⏱️ 8:25 pm What Nobody Tells You About Building LLM Products Ed Shee - AI Engineer & Founder @ Ignitus Curious about building awesome apps with Large Language Models (LLMs)? Come join Ed as he shares everything he wishes he knew before he got started. This talk is packed with real-world insights, including:

Clever techniques for Retrieval-Augmented Generation (RAG)
Crafting prompts that actually work
Keeping LLMs on track and under control
Ensuring your text outputs are top-notch
Building smart and efficient agents

Plus, Ed will give you a look into the future of LLM apps and what to expect next. Whether you're new to the game or a seasoned developer, you'll leave with practical tips and fresh ideas to power up your projects.

⏱️ 9:00 pm - Wrap Up, aka Adios 👋 :)

*** ⚠️ If you are attending in person please complete the registration form (link at the top of this description). ⚠️

MLOps London July 2024 - Talks on Vector Databases, LLMs, and Python Packaging

VS Code Day 2024 2024-04-24 · 17:00

VS Code Day is our annual event where you'll learn how to elevate your development workflow with the latest and greatest features of VS Code. This year, we’re excited to delve into AI and you’ll hear from the VS Code team and other industry experts on topics like AI-powered programming with GitHub Copilot, building and deploying generative AI apps to the cloud, enhancing the C# development experience, and more. Whether you’re just starting out or you’re an experienced developer, join us on April 24, 2024 for a day focused on the editor that lets you code anything, cross-platform and free!

SESSIONS

Welcome to VS Code Day 2024 with Gwyneth Peña-Siguenza and Reynald Adolphe
View Source: What gets into VS Code and why with Burke Holland
JavaScript developers: Build fast and have fun with VS Code and Azure AI CLI with Natalia Venditto
Generating Synthetic Datasets with GitHub Copilot with Alfredo Deza
Real World Development with VS Code and C# with Scott Hanselman and Leslie Richardson
Building a RAG-powered AI chat app with Python and VS Code with Pamela Fox
Beyond the Editor: Tips to get the Most out of GitHub Copilot with Kedasha Kerr
LangChain Examples with Azure OpenAI Service + VS Code with Rishab Kumar
AI Made Clear: Practical AI Coding Sessions in VS Code with Bruno Capuano
Asking Copilot about your workspace with Matt Bierner

Pre-requisites: Resources we think you may find useful related to VS Code Day 2024:

LinkedIn Clone Repo - https://aka.ms/linkedin-clone
VS Code Day Cloud Skills Challenge - https://aka.ms/VSCodeDayChallenge

VS Code Day 2024

Activities & events

Details

Details