Masters in AI [Generative & Agentic]

Objective: Build programming foundation required for AI/ML & GenAI development

Topics Covered:

• Introduction to Python Programming
• Variables, Data Types, Operators
• Control Statements (if-else, loops)
• Functions & Lambda Expressions
• Data Structures:
  • Lists, Tuples, Sets, Dictionaries
• File Handling
• Exception Handling

Libraries for AI:

• NumPy (Numerical Computing)
• Pandas (Data Manipulation)
• Matplotlib / Seaborn (Visualization)
• Introduction to Jupyter Notebook / Google Colab

Hands-On:

• Data preprocessing using Pandas
• Basic data visualization
• Mini Project: Data analysis use-case

Objective: Understand text processing before moving into LLMs

Topics Covered:

• Introduction to NLP
• Text Preprocessing:
  • Tokenization
  • Stopwords Removal
  • Stemming & Lemmatization
• Text Representation Techniques:
  • Bag of Words (BoW)
  • TF-IDF
• Word Embeddings:
  • Word2Vec
  • GloVe
  • FastText

NLP Tasks:

• Text Classification
• Sentiment Analysis
• Named Entity Recognition (NER)
• Language Translation Basics

Hands-On:

• Sentiment Analysis using Python
• Text classification project
• Real-world NLP pipeline

What is a Large Language Model

Encoders and Decoders

Model Ontology

Encoders

Decoders

Encoders-Decoders

Architectures at a glance

Affecting the distribution over Vocabulary

Affecting the distribution over Vocabulary

Prompting

Prompt Engineering

In-context Learning and Few-shot Prompting

Example Prompts

Advanced Prompting Strategies

Prompt Injection

Memorization

Training

Hardware Costs

Decoding

Greedy Decoding

Non-Deterministic Decoding

Temperature

Hallucination

Groundedness and Attributability

Retrieval Augmented Generation

Code Models

Multi-Modal

Language Agents

OCI Generative AI Service

How does OCI Generative AI service work

Pretrained Foundational Models

Fine-tuning

Dedicated AI Clusters

Tokens

Pretrained Chat Models

Chat Model Parameters

Preamble Override

Temperature

Chat Model Parameters

Top k

Top p

Frequency and Presence Penalties

Demo Chat Models

Demo OCI Generative AI Service Inference API

Demo Setting up OCI Config for Generative AI API

Embeddings

Word Embeddings

Semantic Similarity

Sentence Embeddings

Embeddings use case

Embedding Models in Generative AI

Embedding Models in Generative AI

Demo Embedding Model

Prompt & Prompt Engineering

LLMs as next word predictors

Aligning LLMs to follow instructions

In-context Learning and Few-shot Prompting

Prompt Formats

Advanced Prompting Strategies

Training LLMs from scratch with my data

In-context Learning / Few-shot Prompting

Fine-tuning a pretrained model

Fine-tuning Benefits

Retrieval Augmented Generation (RAG)

Customize LLMs with your data

Fine-tuning and Inference

Fine-tuning workflow in OCI Generative AI

Inference workflow in OCI Generative AI

Dedicated AI Clusters

T-Few Fine-tuning

T-Few fine-tuning process

Reducing Inference costs

Inference serving with minimal overhead

Dedicated AI Cluster Units

Dedicated AI Cluster Units Sizing

Dedicated AI Clusters Sizing

Example Pricing

Demo Dedicated AI Clusters

Fine-tuning Configuration

Fine-tuning Parameters (T-Few)

Understanding Fine-tuning Results

Demo Fine-tuning and Custom Models

Demo Inference using Endpoint

Dedicated GPU and RDMA Network

Model Endpoints

Customer Data and Model Isolation

Generative AI leverages OCI Security Services

Retrieval Augmented Generation

RAG Framework

RAG Techniques

RAG Pipeline

NNX compatible

Database-Native Vector Embedding Generation

Vector Index

Vector Index Syntax

Similarity Searches in Oracle 23i

Vector Search SQL

Vector Search

AI Vector Search powers Gen AI pipelines

Application Development

Agentic AI Introduction

AI Agents vs. Agentic AI

Comparison: Agentic AI, Generative AI, and Traditional AI

Agentic AI Building Blocks

Autonomous Agents

Human in the Loops Systems

Single and Multi Agent AI Systems

Agentic AI Frameworks Overview

Ethical and Responsible AI

Agentic AI Best Practices

AI Implementation Success Stories: Case Studies

Agentic AI Architecture

Agentic Architecture Types

Key Components of the Agentic AI Framework

Perception Module

Cognitive Module

Action Module

Learning Module

Collaboration Module

Security Module

Agentic AI Design Patterns

Reflection Pattern

Tool Use Pattern

Planning Pattern

ReAct (Reasoning and Acting) and ReWOO (Reasoning with Open Ontology)

Multi Agent Pattern

Design Considerations

Components and Modules

Data Ingestion and Document Loaders

Text Splitting

Embeddings

Integration with Vector Databases

Introduction to Langchain Expression Language (LCEL)

Runnables

Chains

Building and Deploying with LCEL

Deployment with Langserve

Introduction to LangGraph

State and Memory

State Schema

State Reducer

Multiple Schemas

Trim and Filter Messages

Memory and External Memory

UX and Human-in-the-Loop (HITL)

Building Agent with LangGraph

Long Term Memory

Short vs. Long Term Memory

Memory Schema

Deployment

What is Agentic RAG

Agentic RAG vs. Traditional RAG

Agentic RAG Architecture and Components

Understanding Adaptive RAG

Variants of Agentic RAG

Applications of Agentic RAG

Agentic RAG with Llamaindex

Agentic RAG with Cohere

Agents

Models

Tools

Knowledge

Chunking

Vector DB

Storage

Embeddings

Workflows

Developing Agents with Phidata

Multi Agent Systems

Multi Agent Workflows

Collaborative Multi Agents

Multi Agent Designs

Multi Agent Workflow with LangGraph

CrewAI Introduction

CrewAI Components

Setting up CrewAI environment

Building Agents with CrewAI

Autogen Introduction

Salient Features

Roles and Conversations

Chat Terminations

Human-in-the-Loop

Code Executor

Tool Use

Conversation Patterns

Developing Autogen-powered Agents

Deployment and Monitoring

Langfuse Overview

Langfuse Dashboard

Tracing

Evaluation

Managing Prompts

Experimentation

AI Observability with Langsmith

Setting up Langsmith

Managing Workflows with Langsmith

AgentOps Practical Implementation

Introduction to No-Code/Low-Code AI

Benefits and Challenges of No-Code AI Development

Key Components of No-Code AI Platforms

Building AI Workflows Without Coding

Designing AI Agents with Drag-and-Drop Interfaces

Integrating No-Code AI with Existing Systems

Customizing and Fine-Tuning AI Solutions

Optimizing Performance and Efficiency in No-Code AI

Security and Compliance Considerations in No-Code AI

Best Practices for Deploying No-Code AI Solutions

Real-World Use Cases and Applications of No-Code AI

Scaling and Future Trends in No-Code AI