Building Intelligent Web Applications with Azure OpenAI (TTAI2363)

Building Intelligent Web Applications using Azure OpenAI is a three-day hands-on course that explores the exciting fusion of Generative AI, Machine Learning, and AI in web development. This immersive event will guide you through the end-to-end, cutting edge skills required to create sophisticated machine learning applications that crunch, wrangle and analyze data. You'll learn how to skillfully handle and interpret data from a variety of sources, including user interfaces, web applications, and APIs. You'll immerse yourself in the Azure OpenAI ecosystem, leveraging the most current standards, skills and practices, while learning about recommendation engines, and understanding classification through a mix of statistical algorithms, neural networks, and deep learning. All of this is made approachable and practical, with Python code examples guiding you on how to use intelligent algorithms to draw meaningful insights from data.

The course focuses heavily on practical real-world scenario-based hands-on labs, providing you with ample practice to apply your newly learned skills to scenario-based labs under the valuable guidance of our AI expert instructor. You ll start by building your foundation in Azure OpenAI, then progress to constructing your own APIs, powered by Azure's AI capabilities. Imagine orchestrating these APIs in a middle layer, bringing to life robust business applications. The course culminates with you learning how to weave these AI functionalities into a comprehensive web application. This step-by-step approach is tailored to ensure that by the end, even those new to Azure OpenAI will be able to construct a full-fledged GPT-based application.

By the end of this course, you'll be equipped with the knowledge and confidence required to apply these skills in real-world scenarios. With a newfound understanding and hands-on experience in Azure OpenAI, you ll be ready to enhance your organization's tech capabilities, bringing a fresh perspective to the intelligent web.

Module 1: Getting Started: Building applications for the intelligent web with Azure OpenAI

• An intelligent algorithm in action
• The intelligent-algorithm lifecycle
• Further examples of intelligent algorithms
• Things that intelligent applications are not
• Classes of intelligent algorithm
• Evaluating the performance of intelligent algorithms
• Important notes about intelligent algorithms

Module 2: Extracting structure from data: clustering and transforming your data

• Data, structure, bias, and noise
• The curse of dimensionality
• K-means
• The relationship between k-means and GMM
• Transforming the data axis

Module 3: Recommending relevant content

• Setting the scene: an online movie store
• Distance and similarity
• How do recommendation engines work?
• User-based collaborative filtering
• Model-based recommendation using singular value decomposition
• The Netflix Prize
• Evaluating your recommender

Module 4: Classification: placing things where they belong

• The need for classification
• An overview of classifiers
• Algorithms
• Fraud detection with logistic regression
• Are your results credible?
• Classification with very large datasets

Module 5: Case study: click prediction for online advertising

• History and background
• The exchange
• What is a bidder?
• What is a decisioning engine?
• Click prediction with Vowpal Wabbit
• Complexities of building a decisioning engine
• The future of real-time prediction

Module 6: Developing APIs from Azure OpenAI

• An intuitive approach to building application logic
• Flask APIs and Microservices
• Creating Business Use Cases for Generative AI and Azure OpenAI

Module 7: Building an End-to-End GPT based Web Application

• External API Layer
• Microservices / Web Services Layer + OpenAI + Azure AI
• Business Process Flow Layer (VoiceFlow)
• Front End Layer
• Testing

Module 8: The future of the intelligent web

• Future applications of the intelligent web
• Social implications of the intelligent web

To ensure a smooth learning experience and maximize the benefits of attending this course, you should have the following prerequisite skills:

• Prior programming or scripting experience. Labs are Python-centric, so Python experience would be the most beneficial. Attendees without scripting experience would be able to watch and follow along with the hands-on portion of the training.
• Basic web development experience is recommended (working with HTML5 / CSS3, etc.)
• Comfort with elementary data concepts, such as databases, data structures, and basic data manipulation.
• Students should have incoming practical skills aligned with those in the course(s) below, or should have attended the following course(s) as a pre-requisite: TTPS4872 Python Primer for Data Science and Machine Learning

This foundation level course is geared for experienced technical professionals eager to meld the capabilities of AI with the dynamism of web applications. Roles might include developers, architects, and data scientists who want to learn algorithms that capture, store, and structure data streams coming from the web and web applications, as well as recommendation engines and dive into classification via statistical algorithms, neural networks, and deep learning.