talk-data.com

About this session: During Ignite 2024, attendees heard about many new developments in the AI space, from new models and capabilities to autonomous agents. In this session, we will recap the concepts, tools, and frameworks covered during Ignite that you'll need to build your AI solutions for tomorrow.

Who is it aimed at? Developers and IT professionals interested in building AI solutions.

Why should I attend? 1. Catch Up on Ignite 2024 – Get a recap of the most important AI advancements, tools, and frameworks you may have missed. 2. Explore Cutting-Edge AI – Learn how AI Agents, RAG, and Copilots are shaping the future of intelligent applications. 3. Discover Microsoft’s AI Stack – See how Azure AI services like OpenAI, AI Search, and Copilot Studio can power your next solution. 4. Be Inspired & Engaged – Enjoy an informative, lighthearted session packed with insights, case studies, and practical takeaways.

Learn more and develop your skills with these free Microsoft Learn ressources: https://aka.ms/Mar12AIAgents3 https://aka.ms/Mar12RAGGenAI3

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!

RAG (Retrieval Augmented Generation) is the most common approach used to get LLMs to answer questions grounded in a particular domain's data. RAG is a very good domain adaptation technic but sometimes doesn't meet quality expectations. RAFT (Retrieval augmented fine-tuning) is a new hybrid approach to LLM domain adaptation that combines RAG and fine-tuning. In this session, you'll learn how to implement RAFT using Azure AI Studio and its fine tuning capabilities.

Presented by Cedric Vidal, AI Advocate for Startups

** 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!

Dive into the essentials of connecting AI and ML solutions using Azure AI Studio. This session will guide you through setting up AI Studio with best practices for security and access management, highlighting connections to key services such as Azure Cognitive Services, Azure Search, and Azure Storage Accounts. Whether you're implementing RAG chatbots or deploying models, discover how to protect your resources and ensure compliance across your enterprise. This session will highlight solutions from the Microsoft AI-In-a-Box framework, which you can find at aka.ms/ai-in-a-box.

Presented by Chris Ayers, Customer Engineer, and Marco Aurelio Cardoso, Customer Engineer

** 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!

Dive into the essentials of connecting AI and ML solutions using Azure AI Studio. This session will guide you through setting up AI Studio with best practices for security and access management, highlighting connections to key services such as Azure Cognitive Services, Azure Search, and Azure Storage Accounts. Whether you're implementing RAG chatbots or deploying models, discover how to protect your resources and ensure compliance across your enterprise. This session will highlight solutions from the Microsoft AI-In-a-Box framework, which you can find at aka.ms/ai-in-a-box.

Presented by Chris Ayers, Customer Engineer, and Marco Aurelio Cardoso, Customer Engineer

** 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!

Dive into the essentials of connecting AI and ML solutions using Azure AI Studio. This session will guide you through setting up AI Studio with best practices for security and access management, highlighting connections to key services such as Azure Cognitive Services, Azure Search, and Azure Storage Accounts. Whether you're implementing RAG chatbots or deploying models, discover how to protect your resources and ensure compliance across your enterprise. This session will highlight solutions from the Microsoft AI-In-a-Box framework, which you can find at aka.ms/ai-in-a-box.

Presented by Chris Ayers, Customer Engineer, and Marco Aurelio Cardoso, Customer Engineer

** 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 build a RAG-based custom copilot end-to-end using Azure AI Studio, code-first. We'll walk through "Contoso Chat", a retail copilot scenario with product and customer data. We'll explore prompt engineering using prompty assets, orchestration with promptflow flex-flows and automated provisioning and deployment with azd. You'll learn how to build & test your copilot locally (in VS Code), then deploy & test it in production on Azure.

Presented by Leah Bar-On Simmons (Azure AI PM) and Nitya Narasimhan (Azure AI 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!

Once again we are running a "takeover" at UCExpo North. *** PLEASE NOTE: You need a seperate registraion for UCExpo North (free) to gain entry - https://www.ucxevents.io/ ***

We have three great sessions lined up for the day including:

Untangling Copilot - Different Copilots and their usage In this lightning session we will take a look at the main Copilots that are available, and then dig (a little) deeper into both "standard" Copilot and Copilot for Microsoft 365, showing what kinds of thing you can use it for in the real world Ben Lee, Senior Cloud Architect, CloudWay

Build Next-Gen agent-based AI apps with Microsoft AutoGen In this session, learn about how to use Azure OpenAI and Microsoft AutoGen to create multi-agent based Gen AI applications. We'll introduce Autogen Studio and explain use cases to consider for this emerging technology and where it fits alongside Copilot Studio and RAG (Retrieval Augmented Generation) apps in Azure. Steve Goodman, Field Chief Technology Officer, Advania UK

Queues App - What We Know and What’s Still Missing At Enterprise Connect 2024, the announcement of the Queues App introduced a highly anticipated feature set for Microsoft Teams Phone. In this session, we’ll delve into those upcoming features. We’ll also highlight the gaps that remain, discussing why some organisations might still need to consider a third-party solution to fully meet their needs. Zach Bennett, Principal Architect, LoopUp

Want to build an enterprise AI application with your data, and run it in production? Join us as we build Contoso Chat, an AI-based support agent that implements Retrieval Augmented Generation (RAG) to ground the copilot responses in your product data. Streamline your development workflow with PromptFlow, and manage your Azure AI platform interactions with the Azure AI Studio, SDK and CLI. Learn about Responsible AI practices, and learn how to evaluate your application, and calibrate it for content safety, using built-in capabilities of the Azure AI platform.

Welcome to our March 2024 Data & AI Meetup, We have two great sessions with Pizza and Networking between them.

GPT Unveiled: A Deep Dive into Models, Tools, and Responsible AI This session will explore the following:

• Intricate architecture and mechanics of GPT Models
• A comprehensive comparison across various models from distinct vendors, including open-source models, uncovering why specific models excel in particular scenarios.
• The different tools provided by OpenAI, such as Assistants & Function Calling, and how these innovations enhance solutions to new heights.
• Critical topic of Responsible AI and explore how Azure's content safety studio implements robust content filtering mechanisms to set secure boundaries for large language models.
• Enriched with live demonstrations and an understanding of common use cases that have been seen in the market.

Speaker: Nihal Mushtaq Amin Head of Artificial Intelligence, Coeo Reading, United Kingdom

As the Head of Artificial Intelligence at Coeo, Nihal is responsible for the organisations AI strategy and building out its Generative AI capabilities. He has unique experience working across different industries such as Retail, Telecom, Healthcare, and Financial Services harnessing the power of AI, OpenAI, and data services to deliver valuable business outcomes. In his previous role at Microsoft as Data & AI Cloud Solution Architect, Nihal was the OpenAI lead and made significant contributions to advancing the adoption of Generative AI across client organisations. By designing and delivering solutions using AI, Nihal bridged the gap between technical solutions and business value, driving successful results for clients.

Break for Pizza and Networking

Introduction to Vector Databases. Going beyond the usual ChatGPT response.

This session will focus on introducing the challenges of using ChatGPT, and discuss various approaches to overcome them, including fine-tuning the GPT model and using the Retrieval Augmented Generation (RAG) methodology. We will also discuss in detail the pros and cons of each approach. We will then discuss how to measure the results and how to pick an approach that would best suit based on the needs. Then we will dive deeper into a real-world example along with code and explore how to use vector embeddings and vector databases.

Speaker: Nanda Nainadurai Manager, Avanade Reading, United Kingdom

Nanda has over a decade of work experience in the IT industry and has worked with multiple Fortune 500+ organizations across various industries contributing to their data strategy and AI/ML initiatives. Nanda is passionate about cutting-edge technologies and loves to learn and share his knowledge with everyone. During his free time, he likes to walk along the greenways and read books - Sapiens by Yuval is his all-time favorite thus far, and aspires to learn a new skill every year. Over the years, he has learned to cook, and ice skate, and becoming a copilot is next on his list.

From OpenAI's ChatGPT to the NBA to Mercedes-Benz, Azure Cosmos DB is enabling intelligent apps that change the way we live and work. Join us for an engaging session as we delve into the versatile vector database capabilities of Azure Cosmos DB for MongoDB vCore. Discover the seamless integration of your operational and transactional data with native vector indexing and search functionalities, specifically tailored for AI applications. Learn how to swiftly build RAG solutions by seamlessly connecting with Azure AI Studio to create chatbots using your own data. Explore the power of Azure Cosmos DB's Copilot in simplifying complex query writing, enhancing accuracy, and improving performance. Additionally, we'll showcase our seamless integrations with Semantic Kernel, Langchain, and LlamaIndex. Gain valuable insights into KPMG's success story, where Azure Cosmos DB played a pivotal role in the creation of a generative AI assistant for business operations.

Learning Objectives • Gain a comprehensive understanding of vector database capabilities for Azure Cosmos DB for MongoDB vCore. • Discover how to seamlessly integrate operational and transactional data with vector data within a single database to enhance your AI applications. • Discover how to build RAG solutions, including chatbots, using Azure AI Studio and your own data. • Explore the power of Azure Cosmos DB's Copilot in simplifying complex query writing, enhancing data accuracy, and improving performance. • Gain insights from KPMG's success story of using Cosmos DB for MongoDB vCore for a Generative AI agent in business operations.

This session is ideal for the startup community who are: • Interested in leveraging cutting-edge database technologies for intelligent applications and AI-driven solutions. • Seeking to enhance data integration, query efficiency, and overall performance using Azure Cosmos DB. • Inspired by real-world success stories like KPMG's generative AI assistant. • Looking to seamlessly integrate AI Studio, Semantic Kernel, Langchain, and LlamaIndex for enhanced functionality and efficiency in their applications.

From OpenAI's ChatGPT to the NBA to Mercedes-Benz, Azure Cosmos DB is enabling intelligent apps that change the way we live and work. Join us for an engaging session as we delve into the versatile vector database capabilities of Azure Cosmos DB for MongoDB vCore. Discover the seamless integration of your operational and transactional data with native vector indexing and search functionalities, specifically tailored for AI applications. Learn how to swiftly build RAG solutions by seamlessly connecting with Azure AI Studio to create chatbots using your own data. Explore the power of Azure Cosmos DB's Copilot in simplifying complex query writing, enhancing accuracy, and improving performance. Additionally, we'll showcase our seamless integrations with Semantic Kernel, Langchain, and LlamaIndex. Gain valuable insights into KPMG's success story, where Azure Cosmos DB played a pivotal role in the creation of a generative AI assistant for business operations.

Learning Objectives • Gain a comprehensive understanding of vector database capabilities for Azure Cosmos DB for MongoDB vCore. • Discover how to seamlessly integrate operational and transactional data with vector data within a single database to enhance your AI applications. • Discover how to build RAG solutions, including chatbots, using Azure AI Studio and your own data. • Explore the power of Azure Cosmos DB's Copilot in simplifying complex query writing, enhancing data accuracy, and improving performance. • Gain insights from KPMG's success story of using Cosmos DB for MongoDB vCore for a Generative AI agent in business operations.

This session is ideal for the startup community who are: • Interested in leveraging cutting-edge database technologies for intelligent applications and AI-driven solutions. • Seeking to enhance data integration, query efficiency, and overall performance using Azure Cosmos DB. • Inspired by real-world success stories like KPMG's generative AI assistant. • Looking to seamlessly integrate AI Studio, Semantic Kernel, Langchain, and LlamaIndex for enhanced functionality and efficiency in their applications.

RSVP Here - https://www.eventbrite.com/e/azure-openai-chatgpt-fest-2024-tickets-759336785767

The Azure OpenAI & ChatGPT Fest 2024 will be an in-person 2-day technology event, 10 AM to 4 PM ET, with a hands-on workshop, and a single track, and multiple sessions. The event will be hosted in the new Microsoft offices in Reston, at 11955 Freedom Drive, 2nd Floor, Rooms C- E. There is plenty of parking in Reston Town Center. The event is also right off the Silver Line metro. Day 01: Thursday 18th January 2024 from 10 AM to 4 PM EST Agenda: Hands-On Azure OpenAI & ChatGPT workshop. The following topics will be covered and access to the Azure OpenAI services will be provided. Since this is a hands-on workshop, the tickets are limited.

1. Azure OpenAI Services: We will explore what these services are, their architecture, and their place within the broader AI ecosystem.
2. Azure OpenAI Studio: An in-depth overview of the Azure OpenAI Studio.
3. Prompt Engineering: An in-depth look at this critical aspect of large language model usage. We will cover how prompts work, why they are important, and the factors that influence their effectiveness.
4. Use Case and Common Architecture: Hands-on labs covering the use case and common architecture of the implementation
5. Azure OpenAI Service Embedding Models
6. Semantic Kernel
7. Customizing Azure OpenAI Services
8. Using Azure OpenAI Service to access company data
9. Azure AI Services Overview: Discussion on key components such as Language Services, Speech services, Vision services, and their real-world applications.
10. Conversational AI: A look at the development of AI that can engage in human-like dialogues, including designing, training, and refining conversational models.
11. Azure AI Search: We will cover how we can use this service to create an advanced search experience.
12. Azure Document Intelligence Service: We will cover how this service uses machine learning technology to identify and extract key-value pairs and table data from form documents.
13. Responsible AI
14. Creating Enterprise-Level Applications: Practical guidance on developing robust, scalable applications using Azure OpenAI, ChatGPT, and Cognitive Services, focusing on industry requirements and best practices."
15. Creating Enterprise-Level custom Copilot: Practical guidance on developing robust, scalable copilot using Azure OpenAI, ChatGPT, and Cognitive Services, focusing on industry requirements and best practices."

Day 02: Friday 19th January 2024 from 10 am to 4 PM EST Agenda: Single-track break-out sessions on the following topics.

1. Azure OpenAI Services and ChatGPT Overview
2. How to use Azure OpenAI services to create an enterprise application
3. Prompt Engineering
4. Copilots in Microsoft Ecosystem ( Microsoft 365 Copilot, Power Platform Copilots, Github Copilots )
5. Embedding, Vector Databases, RAG Pattern, Knowledge Repository
6. How to create a custom copilot using Copilot Studio and Semantic Kernel?
7. Azure AI Services like Azure AI Search, Semantic Search, Azure Document Intelligent Services
8. Azure OpenAI Services Architecture Patterns
9. Model testing Validation, Accuracy, Bias testing, Detecting Hallucination
10. Content filtering and Abuse Monitoring
11. Responsible AI

Confirmed speakers are

1. Vishwas Lele ( Microsoft Regional Director, Microsoft MVP, CTO, AIS )
2. Henk Boelman (Henk Boelman , Senior Cloud Advocate, Artificial Intelligence and Machine Learning, Microsoft )
3. Kiran Bakshi (Principal Cloud Solution Architect – Data and AI, Microsoft),
4. Steve Winward ( Director, Business Applications @ Microsoft Federal )
5. Craig Harris ( Sr Technical Specialist, Business Applications, Microsoft Federal )
6. Jagannath Chakravarty (Product Design Manager at Appian Corporation)
7. Frank LaVigne (Microsoft AI MVP), and
8. Prashant G Bhoyar ( Microsoft AI and Business Applications MVP ).

We will be posting the final agenda in the first week of January 2023.

The Azure OpenAI & ChatGPT Fest 2024 will be an in-person 2-day technology event, 10 AM to 4 PM ET, with a hands-on workshop, and a single track, and multiple sessions. The event will be hosted in the new Microsoft offices in Reston, at 11955 Freedom Drive, 2nd Floor, Rooms C- E. There is plenty of parking in Reston Town Center. The event is also right off the Silver Line metro. Day 01: Thursday 18th January 2024 from 10 AM to 4 PM EST Agenda: Hands-On Azure OpenAI & ChatGPT workshop. The following topics will be covered and access to the Azure OpenAI services will be provided. Since this is a hands-on workshop, the tickets are limited.

1. Azure OpenAI Services: We will explore what these services are, their architecture, and their place within the broader AI ecosystem.
2. Azure OpenAI Studio: An in-depth overview of the Azure OpenAI Studio.
3. Prompt Engineering: An in-depth look at this critical aspect of large language model usage. We will cover how prompts work, why they are important, and the factors that influence their effectiveness.
4. Use Case and Common Architecture: Hands-on labs covering the use case and common architecture of the implementation
5. Azure OpenAI Service Embedding Models
6. Semantic Kernel
7. Customizing Azure OpenAI Services
8. Using Azure OpenAI Service to access company data
9. Azure AI Services Overview: Discussion on key components such as Language Services, Speech services, Vision services, and their real-world applications.
10. Conversational AI: A look at the development of AI that can engage in human-like dialogues, including designing, training, and refining conversational models.
11. Azure AI Search: We will cover how we can use this service to create an advanced search experience.
12. Azure Document Intelligence Service: We will cover how this service uses machine learning technology to identify and extract key-value pairs and table data from form documents.
13. Responsible AI
14. Creating Enterprise-Level Applications: Practical guidance on developing robust, scalable applications using Azure OpenAI, ChatGPT, and Cognitive Services, focusing on industry requirements and best practices."
15. Creating Enterprise-Level custom Copilot: Practical guidance on developing robust, scalable copilot using Azure OpenAI, ChatGPT, and Cognitive Services, focusing on industry requirements and best practices."

Day 02: Friday 19th January 2024 from 10 am to 4 PM EST Agenda: Single-track break-out sessions on the following topics.

1. Azure OpenAI Services and ChatGPT Overview
2. How to use Azure OpenAI services to create an enterprise application
3. Prompt Engineering
4. Copilots in Microsoft Ecosystem ( Microsoft 365 Copilot, Power Platform Copilots, Github Copilots )
5. Embedding, Vector Databases, RAG Pattern, Knowledge Repository
6. How to create a custom copilot using Copilot Studio and Semantic Kernel?
7. Azure AI Services like Azure AI Search, Semantic Search, Azure Document Intelligent Services
8. Azure OpenAI Services Architecture Patterns
9. Model testing Validation, Accuracy, Bias testing, Detecting Hallucination
10. Content filtering and Abuse Monitoring
11. Responsible AI

Confirmed speakers are

1. Vishwas Lele ( Microsoft Regional Director, Microsoft MVP, CTO, AIS )
2. Kiran Bakshi (Principal Cloud Solution Architect – Data and AI, Microsoft),
3. Steve Winward ( Director, Business Applications @ Microsoft Federal )
4. Craig Harris ( Sr Technical Specialist, Business Applications, Microsoft Federal )
5. Jagannath Chakravarty, Product Design Manager at Appian Corporation
6. Frank LaVigne (Microsoft AI MVP), and
7. Prashant G Bhoyar ( Microsoft AI and Business Applications MVP ).

We will be posting the final agenda in the first week of January 2023.

Intro on RAG and demo how RAG functions in the new Azure AI Studio.

Pre-registration is required: https://www.aicamp.ai/event/eventdetails/W2023121414 ***

As the year winds down and the holiday spirits ramp up, we invite you to the most electrifying AI meetup (end-of-year edition). Instead of our usual scheduled talks, we will throw the most exciting holiday bash for people who build AI!

Join AI developers, ML engineers, Data scientists and practitioners to celebrate all your hard work this year, with tech talks, food, and drinks.

Agenda: * 5:00pm\~5:45pm: Checkin, Food/drink and networking * 5:45pm\~6:00pm: Welcome/community update * 6:00pm\~7:30pm: Tech talks, Q&A and Community showcase * 7:30pm\~8:00pm: Open discussion and Mixer

Tech Talk 1: RAG in the new Azure AI Studio Speaker: Elijah Straight @Microsoft Abstract: Intro on RAG and demo how RAG functions in the new Azure AI Studio.

Tech Talk 2: The next level of RAG applications - building multimodal applications with Vector Databases Speaker: Byron Voorbach @Weaviate Abstract: In this talk, we are going to explore how vector databases like Weaviate can be used to build the next level of RAG applications. Based on examples we are looking at the possibilities of RAG architectures that can handle multimodal context like images, videos and much more and how vector databases work in such a setting

Topics/Speakers: Stay tuned as we are updating speakers and schedules. If you have a keen interest in speaking, we invite you to submit topics for consideration: Submit Topics

Startup Showcase: We have 5\~10 demo desks available for the community showcases and \~5 minutes quick demo on the stage. You are invited to apply here Community Showcase

*** Registration Instructions **** ** RSVP: https://www.aicamp.ai/event/eventdetails/W2023111510 *******

Description: I LOVE AI (a series of events for AI developers) is coming to London! Are you building Generative AI agents that will use in-context data with LLMs? Join AI developers, practitioners, and strategists to unlock the power of Generative AI. We will explore how to: - Create Generative AI apps with the accuracy and relevance you need - Make GenAI enterprise-ready by conquering major obstacles - Build on the most powerful Vector Database - Implement the only vector database capable of synchronous\, low-latency writes and reads without performance degradation - Harness the potential of your data\, with the industry’s most advanced vector database\, to accelerate your AI journey

Agenda: * 6:00pm\~6:30pm: Checkin, Food/Drink and networking * 6:30pm\~8:00pm: Tech talks * 8:30pm: Q&A and Open discussion

Tech Talk 1: Lessons Learned Building a GenAI Powered App Speaker: Marc Cohen @Google Cloud Abstract: Everyone is excited about AI and justifiably so, but can it help us build better apps? This session will focus on a case study: a GenAI powered interactive trivia quiz app running in the Cloud. We will explore the challenges we faced while building the app and how GenAI proved to be a game changer. Join me for a fun and educational session featuring a live demo with audience participation, and some valuable lessons learned.

Tech Talk 2: Generative AI with Azure Machine Learning Service Speaker: Anil Sener @Microsoft Abstract: Learn how Azure Machine Learning AI Studio became central to develop, assess, deploy and monitor intelligent agents based on foundation models. Explore its use with OpenAI, open source and partner models and the options to integrate it with databases and knowledge bases.

Tech Talk 3: Building a Petabyte-Scale Vector Store: Powering Future AGI Speaker: Cedric Lunven @Datastax Abstract: A laptop proof of concept won’t cut it for this impending era of generative AI. Let’s dig into the mechanics of building and using a petabyte-scale vector store and the future of handling data in generative AI models. This talk will focus on the work in the Apache Cassandra® project to develop a vector store capable of handling petabytes of data, discussing why this capacity is critical for future AI applications. I will also connect how this pertains to the exciting new generation of AI technologies like Improved Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Forward-Looking Active Retrieval Augmented Generation (FLARE) that all contribute to the growing need for such scalable solutions. Finally, we’ll discuss the importance of planning for future scalability and how to effectively manage AI agents in this new age of data.

Speakers/Topics: Stay tuned as we are updating speakers and schedules. If you have a keen interest in speaking to our community, we invite you to submit topics for consideration: Submit Topics

Community on Slack - Event chat: chat and connect with speakers and attendees - Sharing blogs\, events\, job openings\, projects collaborations Join Slack (search and join the #london channel)