Generative AI for Business with Microsoft Azure OpenAI

The outcome from this week is to understand the Generative AI Landscape, fundamentals and possibilities for businesses to solve problems and create products

• Defining AI, ML, DL, LLM and Generative Models
• Learning supervised and unsupervised ML tasks
• Understanding Generative and Discriminative AI
• A brief timeline of Generative AI
• A peek into generative models
• Deconstructing the behavior of a large language models
• ML, DL and GenAI applications in business
• Hands-on Demonstration of popular tools (ChatGPT, DALL-E, BLIP)

Focus on recognizing features of typical AI workloads, understanding principles for responsible AI, and gaining familiarity with common machine learning techniques. 

• Identify features of common AI workloads
• Identify guiding principles for responsible AI
• Identify common machine learning techniques
• Describe core machine learning concepts
• Describe Azure Machine Learning capabilities

Recognize various computer vision solution types and discover Azure tools for handling computer vision tasks. Additionally, Identify features of typical NLP workload scenarios and explore Azure tools and services applicable to NLP workloads.

• Identify common types of computer vision solution
• Identify Azure tools and services for computer vision tasks
• Identify features of common NLP Workload Scenarios
• Identify Azure tools and services for NLP workloads

Focus on recognizing features of generative AI solutions and understanding the capabilities offered by the Azure OpenAI Service.

• Identify features of generative AI solutions
• Identify capabilities of Azure OpenAI Service

The outcome from this week is to gain practical knowledge of Prompt Engineering and the ability to do it without code for various business use-cases.

• LLMs and the genesis of Prompting
• How does the Attention mechanism work? 
• A brief history of the GPT model series
• Accessing GPT through Azure
• Designing prompts for business use-cases using playground templates
• Prompting techniques (Prompt templates, precise instructions, chain of thought prompting)
• Ideating for prompts (prompt generation by induction, prompt paraphrasing)

Problem Statement: Amazon needs an automated system that can efficiently analyze product reviews, extract critical information, and determine the sentiments expressed by customers. The solution should help the company gain insights into product performance and customer satisfaction

Objective: The objective of this project is to create a prompt template that performs sentiment analysis on product reviews. The model should extract relevant information, such as product names, reviewer names, review ratings, review descriptions, and sentiment (positive or negative), to assist the company in understanding customer feedback better.

The outcome from this week is to get up to speed on the python concepts that are needed to automate prompt engineering at scale, and understand the cost implications of using APIs

• Variables
• Data types
• Data Structures 
• Conditions and Loops
• Functions
• String Operations
  • Concatenation 
  • String formatting 
  • String Indexing 
  • Slicing 
  • String length 
  • String methods 
  • String searching and Manipulation 
  • String Conversion

The outcome from this week is to get up to speed on the python concepts that are needed to automate prompt engineering at scale, and understand the cost implications of using APIs

• Store text in python
• Edit, add and delete text in python
• How to read files in Python
• How to work with a database
• Manipulate string columns

The outcome from this week is to learn how to use the Azure Open AI API key and the python SDK to leverage generative AI at scale for solving business problems

• Getting setup with your Azure Open AI key and Python SDK
• Completions and Chat API
• Kinds of APIs, Models, Token, Rate Limits and Pricing
• Evaluating Generative AI Outputs

The outcome from this week is to learn how to use Prompt Engineering to solve classification type problems.

• Framing text classification tasks as Generative AI problem
• Sentiment classification
• Assigning themes to a body of text 
• Aspect-based sentiment analysis

The outcome from this week is to learn how to use Generative AI for content generation tasks across various business problem spaces.

• Content generation using Generative AI 
• Abstractive summarization
• Text generation 
• Image generation

The outcome from this week is to learn how to setup an information retrieval and synthesis workflow on Azure or a local environment for a business use-case.

• Overview of advanced application of Generative AI 
• Critical components of architecting conversational agents
• Demonstration of a conversational agent implementation

Problem Statement: The objective of this problem statement is to use aspect-based classification for sentiment analysis to identify the aspects of a product or service that customers are most satisfied with and those that need improvement. This will help businesses understand their customers better and make data-driven decisions to improve their products or services. By improving customer satisfaction and loyalty, businesses can increase customer retention rates, reduce churn rates, and ultimately increase revenue.