talk-data.com

4-Day Hands-on Workshop: Building Multimodal Applications, Custom Copilots, and AI Agents using GenAI (Azure OpenAI and ChatGPT) October 22-25, 2024 9:00AM – 5:00PM (Central)

Registration Link : https://live360events.com/events/training-seminars/2024/oct22/home.aspx

With ChatGPT, other large language models and generative AI have caught the attention of global consumers, enterprises, and C-suites. AI has a big role to play in the enterprise space and it is progressing rapidly. Without understanding the concepts behind these advanced technologies, developers and administrators will struggle to evaluate the potential impact of new tools and solutions. A multimodal GenAI application seamlessly generates high-quality content across text, images, video, and audio, all at once. Such applications would more accurately capture the multimodal nature of the world and human comprehension, seamlessly consolidate information from a wide range of sources, and enable strong immersion in human-AI interactions. This could transform the way humans interact with computers on various tasks, including assistive technology, custom learning tools, ambient computing, and content generation. Azure OpenAI Service provides REST API access to OpenAI's powerful language models including the GPT-3, GPT-4, Codex and Embeddings model series and DALL-E. These models can be easily adapted to your specific task including but not limited to content generation, summarization, semantic search, and natural language to code translation. Users can access the service through REST APIs, Python SDK, or our web-based interface in the Azure OpenAI Studio. In this 4-day virtual hands-on workshop, Microsoft AI and Business Applications MVP and Microsoft Certified Trainer Prashant G Bhoyar will cover the following topics in detail:

• What are Multimodal GenAI Applications?
• What are AI Agents?
• What are Custom Copilots?
• Azure OpenAI Services: We will explore what these services are, their architecture, and their place within the broader AI ecosystem.
• Azure AI Studio: An in-depth overview of the Azure AI Studio.
• 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.
• Use Case and Common Architecture: Hands-on labs covering the use case and common architecture of the implementation
• Azure OpenAI Service Embedding Models
• Semantic Kernel is an open-source SDK that lets you easily combine AI services like OpenAI, Azure OpenAI, and Hugging Face with conventional programming languages like C# and Python. By doing so, you can create AI apps that combine the best of both worlds.
• Microsoft Copilot Studio lets you create powerful AI-powered copilots for a range of requests—from providing simple answers to common questions to resolving issues requiring complex conversations. Engage with customers and employees in multiple languages across websites, mobile apps, Facebook, Microsoft Teams, or any channel supported by the Azure Bot Framework.
• Customizing Azure OpenAI Services: From configuration to deployment, we'll show you how to tailor these services to suit a range of specific needs.
• Deep dive into Azure OpenAI Services: We'll specifically focus on several of the models like GPT, Ada, and DALL-E, discussing their unique features and optimal use cases.
• Using Azure OpenAI Service to access company data
• Azure AI Services Overview
• Azure AI Search
• Document Intelligence Service
• A thorough examination of the AutoGen Framework and its capabilities.
• Responsible AI: Delve into the ethics and responsible use of AI.
• How to evaluate a use case and find the ROI?
• Enterprise-Level Applications, Custom Copilots, AI Agents: Learn to develop robust, scalable multimodal applications, Custom Copilots, and AI Agents using C#, Python and also using low code no code tools like Azure Logic Apps, and Microsoft Power Platform, focusing on industry requirements and best practices.

At the end of the workshop, attendees will have a working knowledge of how to build next-gen multimodal applications, Custom Copilots, and AI Agents with Azure OpenAI and Azure AI services. Access to Azure and Azure OpenAI services will be provided to follow the labs and create enterprise-grade multimodal applications. The labs will be a mixture of Python and C#.

Keeping up to date with Microsoft 365 is important and getting most out of it is even more essential! Join us online for free on Microsoft Teams and bring your questions!

Agenda (UK Time): 17:00-17:10 - Welcome & Introductions

17:10-18:00 - Architecting an end-to-end data driven solution in M365 - Vanessa Toves Business problems that need data driven solutions don't all require massive investments in infrastructure (native or cloud). We will discover the power of solution architecture and Microsoft 365 apps to solve everyday business problems.

18:00-18:50 - Unleash Your Business Data: Supercharge Copilot for Microsoft 365 with Custom Graph Connectors - Ejaz Hussain MVP Struggling to find the information you need within Microsoft 365? This session dives into Microsoft Graph Connectors, a powerful tool that unlocks the potential of your line-of-business data for Copilot for Microsoft 365. Learn how to: - Surface your data: Ingest your unstructured data directly into Microsoft Graph\, empowering Copilot to understand and reason over all your enterprise content. - Craft user-friendly experiences: Enable users to find\, summarize\, and learn from your data using natural language prompts in Copilot. - Build custom connectors: We'll walk you through the process of creating custom Graph connectors using the Microsoft Graph Connectors API. - Optimize for Copilot: Discover best practices for configuring your connectors to ensure Copilot surfaces your content effectively. By the end of this session, you'll be equipped to leverage Graph Connectors and empower Copilot for a truly intelligent information discovery experience.

18:50-19:00 - Break

19:00-19:50 - Streamline customer requests and improve consultant productivity - Karl-Johan Spiik This session shows how to automate customer requests from shared email and integrate them into Azure DevOps backlog with Power Automate and notify developer via Teams group chat offering possibility to assign the task for me with a click of a button. As consultants, we face multiple channels of customer contact, such as email, phone, chat, etc. This creates challenges, such as: • Keeping track of data and requests from different sources. • Losing or forgetting some requests in the information flood. • Lack of visibility and control over the status and progress of the requests. • Low efficiency and quality of the service due to fragmentation and confusion. Session take aways - Learn how to automate the creation of tasks in Azure DevOps from customer emails using Power Automate - Simplify the communication and collaboration among consultants by using a shared mailbox and a group Teams chat - Increase the visibility and control of customer requests by using adaptive cards and tracking the progress in Azure DevOps - Improve the customer satisfaction and retention by serving them in their preferred channel and providing transparent work

Speaker Profiles: Vanessa Toves, Microsoft 365 Solutions Architect, Druva, USA When I was young I wanted to be an architect. As it turns out, I'm a different type of architect. I am a Microsoft 365 Solutions Architect. What does that mean? I help companies to solve business problems using Microsoft 365.

Ejaz Hussain MVP, Developer Architect, Advania, UK A seasoned Developer Architect, I live and breathe innovation on Microsoft 365 and Azure. Combining deep tech expertise with a passion for impactful solutions, I craft robust, scalable applications that unlock the full cloud potential. From designing intricate architectures to building secure, efficient apps, I bring ideas to life, always one step ahead in the dynamic tech landscape. As a Microsoft Valuable Professional (MVP), I remain at the forefront of emerging trends, consistently expanding my knowledge to offer clients the most effective and future-proof solutions. Passionate about tech beyond the workplace, I contribute to open-source projects, share knowledge through writing and discussions, and actively engage in the tech community through events and conferences. Let's collaborate, innovate, and empower businesses with Microsoft solutions – together!

Karl-Johan Spiik, Power Platform Architect & Senior Consultant, Sulava, Finland Karl-Johan has done 16 years projects with Microsoft technologies. Past four years he has been working with the Power Platform, particularly with Power Automate, and have extended its capabilities with Microsoft 365 and Dynamics 365 products as well as Azure resources. Karl-Johan has completed about 60 projects with various industries and organization sizes as role of architect and Scrum Master. Latest projects with AI Builder and Azure OpenAI.

About London Reactor Meetup Microsoft Reactor London Meetups are a community of like-minded engineers, developers, professionals and students, allowing you to connect with people, skills, and technology to enhance your career or personal learning. Our regular meetups are an opportunity to hear from leaders in the industry about challenges, tooling and best practices. If you are interested in speaking or want to suggest a talk you’ve heard before, please do let us know (no vendor / recruitment / sales pitches please).

Agenda

6:00 PM - Arrivals: Registration and welcoming of guests 6:30 PM - 6:40 PM - Welcome Address 6:40 PM - 7:00 PM - Understanding AI: build your own enterprise ChatGPT with LangChain4J by Sandra Ahlgrimm 7:00 PM - 7:30 PM - Break 7:30 PM – 7:50 PM - Deploying a Python Web App with Azure by Marlene Mhangami 7:50 PM - 8:10 PM - Accelerating Development: Harnessing Service Bus and Azure Functions for Event-Driven Solutions by Chandan Bhagat 8:10 PM - 8:45 PM - Networking / Questions & Closing

Session Descriptions:

Understanding AI: build your own enterprise ChatGPT with LangChain4J

In this session we will build a chatbot from based on OpenAI models and implementing the Retrieval Augmented Generation (RAG) pattern. Using a reference document database, the model will be able to answer questions in natural language and generate complete, sourced responses from your documents. To do this, we will create a Quarkus service based on the open-source LangChain4J framework and a website to test our chatbot.

Accelerating Development: Harnessing Service Bus and Azure Functions for Event-Driven Solutions

In this session, dive into the world of event-driven development with Service Bus and Azure Functions. Discover how to leverage these powerful Azure services to create robust, scalable, and responsive applications that react to events in real-time. We'll start by exploring the fundamentals of event-driven architecture and how it enables loosely coupled and highly scalable systems. You'll learn how Service Bus acts as the backbone of event communication, allowing seamless publishing and consuming of events across your application. Next, we'll delve into Azure Functions and understand how they can be used to process events triggered by Service Bus. We'll walk through real-world scenarios and explore best practices for designing and implementing event-driven solutions using Azure Functions.

Throughout the session, you'll gain practical insights and tips for designing resilient architectures, handling message processing, and optimizing performance. Whether you're building microservices, IoT applications, or real-time analytics pipelines, this session will equip you with the knowledge and tools to accelerate your development with event-driven architecture on Azure.

In this demo intensive session Alan will show you how to use Azure Open AI Service to build natural language solutions from scratch. He will explain basic concepts of natural language processing, such as tokens, embeddings, and transformers. He will demonstrate how to use the Azure Open AI Service portal to create and deploy natural language models using pre-trained or custom data. He will also show you how to use the Azure Open AI Service SDK to interact with the models programmatically and integrate them with other Azure services.

What is this session about?

Azure Open AI Service is a new cloud-based platform that enables developers to create natural language solutions using state-of-the-art models such as GPT-4 and Codex. The Service provides a simple and intuitive interface to access these models, as well as tools to customize, optimize, and monitor their performance. Whether you want to build a chat bot, a code generator, a text summarizer, or any other natural language application, Azure Open AI Service can help you achieve your goals.

Why should you attend?

In this demo intensive session Alan will show you how to use Azure Open AI Service to build natural language solutions from scratch. He will start by explaining the basic concepts of natural language processing, such as tokens, embeddings, and transformers. He will then demonstrate how to use the Azure Open AI Service portal to create and deploy natural language models using pre-trained or custom data. He will also show you how to use the Azure Open AI Service SDK to interact with the models programmatically and integrate them with other Azure services.

Join us for this session if you want to learn how to leverage the power of Azure Open AI Service in your own solutions.