Advanced Certificate Program in GenerativeAI 

Introduction to Python and Programming

Python Data Types, Variables, Operators, Data Structures

Python Programming Constructs: Conditionals, Loops, Functions

UDFs, Best Coding Practices and Exception Handling

Python for Data Science and Pandas: Working with relational databases, Data Cleaning, Preprocessing, Analysis

Advanced Text Processing using Pandas

Basics of Linux: Commands, Setting up Local Environment

Define the different components of the bot and design the workflow for creating the bot

Apply prompting techniques to create prompts for asking questions and evaluating the customer's response

Prompt Engineering: Improve the assistant's responses by applying simple (non-reasoning) prompting techniques

Prompt Engineering: Improve the assistant's accuracy by applying Chain of Thought reasoning-based prompting techniques

Apply fine-tuning using OpenAI APIs to train an LLM on your custom data

Integrate speech input using OpenAI's Whisper API

Deploy and launch ShopAssistAI application on Flask/Gradio

Iterate and improve the UI of the app using ChatGPT's code writing capabilities

Understand the working of multimodal models like

Understand the working of multimodal models like Stable Diffusion: Denoising, Diffusion, Autoencoders, Contrastive Learning, Shared Embedding Spaces

Apply image prompting techniques on Dall-E and Midjourney to generate desired product images using various stable diffusion methods and prompt parameters such as style, ratios, seeds, FPS

Understand and apply the fundamentals of style, design and photography to improve image quality and accuracy with prompt iteration and few-shot prompting

Apply self-consistency, seeding and standardised formatting in prompting to create consistent styles and designs across hundreds of product images

Generate product descriptions along with images using various instructor-tuned models and APIs

Understand prompting for code generation and generate accurate codes for data science tasks in a larger ML problem using GPT and Copilot

Read, load and embed large datasets and tables to read your data with GPT/Copilot

Perform data cleaning and analysis by both generating code & writing direct prompts to GPT

Write prompts for data analysis tasks and insights in accordance to the business problem and objectives

Perform semi-automated modelling, fine-tuning and evaluation for various regression, classification and clustering problems

Define the components of Chatbot

Understand when to use embedding over fine tuning

Understand the working of embeddings and how they help in semantic search

Create and analyse embeddings for semantic search

Create embeddings for large documents by creating chunks

Create a Q/A system that fetches answer using similarilty search over embeddings

Scale the Q/A system by making use of vectorstores like Pinecone

Embed, index large documents and search in Vectorstore

Integrate LLM chat models over the searched embeddings to respond to the customer

Experiment with different vectorstores, search and index algorithms and LLMs to improve the chatbot

Define the components of the knowledge retrieval system and design the workflow

Explore how LangChain can connect the different components of the system

Understand the different parts of LangChain - Models, Prompts, Indexes, Chains, Memory and Agents

Explore the different tools in LangChain and initialise an agent that uses the tools to read different types of files or data present in the company database

Build the backend for the system using Vectorstore options present in LangChain

Divide the documents into chunks and apply the LLM to create the embeddings and extract entity for the chunks of document and store them in the Vectorstore

Construct the Search Index and Entity Store and create a functionality to update it with every question that the user asks

Use the Chain functionality of LangChain to connect all the components

Evaluate the results and improve them by experimenting with different LLMs, indexing and embedding algorithms

Explore other agents and tools to improve the system like adding features like automatic email notifications on some issues, etc

Explore the Generative AI services offered by Azure: Azure OpenAI services

Modify the workflow design of knowledge retrieval system for scalability

Identify the Azure services required for creating the scalable system

Expose the system through a chat based front end to the user

Mitigating risks in AI: Responsible AI

RLHF as a Product to train your own LLM

Multimodal Learning: Audio, Image, Text, Heatmap among others within a LLM