Only Few Seats Left

Module 1

Foundations of Artificial Intelligence & Generative AI

·       Building an AI Tool: Overview of the AI application development workflow

·       Artificial Intelligence: Natural vs Artificial Intelligence, brief history and Weak vs Strong AI.

·       AI Ecosystem: AI vs Data Science vs Machine Learning vs Deep Learning

·       Data Basics: Data collection, labelled vs unlabelled, structured vs unstructured; metadata

·       Machine & Deep Learning: Quick overview of Important Aspects & Applications.

·       Natural Language Processing (NLP): Introduction to NLP and its applications

·       Generative AI: Concepts, evolution, applications and introduction to ChatGPT.

·       Large Language Models (LLMs): Evolution from N-Grams and RNNs to Transformers; training and inference concepts

·       Generative AI Development: Prompt Engineering, Fine-Tuning & RAG-conceptual overview

·       Foundation Models: Open-source vs proprietary models and model selection

·       Challenges of Generative AI: Hallucination, inconsistency, bias, data limitations, latency, cost and privacy/security.

·       AI Stack: Python, LLM APIs, Hugging Face, LangChain &Vector Databases-an Overview

Module 2

Data Processing for Generative AI

·       NumPy Library: Arrays, indexing, slicing, reshaping and vectorized operations.

·       Pandas: Series, DataFrames, data types and basic data manipulation

·       Data Manipulation: Selection, filtering, sorting, indexing (loc/iloc) and groupby operations

·       Data Cleaning & Preprocessing: Missing values, duplicates, data type conversion and basic preprocessing

·       Text Data Processing: String operations, text cleaning and Regular Expressions (Regex)

·       File & Data Handling: Reading and writing CSV, JSON and text files

·       Data Exploration: Loading, inspecting, transforming and exporting datasets

Module 3

Natural Language Processing (NLP) & Text Analytics

·       NLP Fundamentals: Introduction, applications & NLP workflow; supervised vs. unsupervised

·       Text Preprocessing: Text cleaning, normalization, stop-word removal and Regular Expressions

·       Text Representation: Tokenization, stemming, lemmatization and N-grams

·       Linguistic Analysis: POS tagging and Named Entity Recognition (NER)

·       Text Classification: Sentiment analysis and traditional ML-based text classification

·       Numerical Representation: Bag-of-Words, TF-IDF and text feature extraction

·       Modern NLP: Introduction to embeddings and pre-trained Transformer-based NLP models

·       Hands-on: Build a Text Classification & Sentiment Analysis System using Python and NLP

Module 4

Large Language Models (LLMs) & Transformer Architecture

·       Understanding LLMs: General-purpose & foundation models, applications & limitations

·       LLM Training: Pre-training, instruction tuning, fine-tuning and inference

·       Transformer Architecture: Input embeddings, positional encoding, self-attention, multi-head attention and feed-forward networks

·       Transformer Variants: Encoder, decoder and architectures; masked attention

·       GPT: GPT architecture, autoregressive generation, tokenization & text generation

·       LLM Parameters: Temperature, top-p, maximum tokens & prompt-based customization

·       OpenAI API: API setup, model interaction, text generation and structured responses

·       Hugging Face Transformers: Transformer pipeline, pretrained models & special tokens

·       Encoder-based Models: BERT, RoBERTa & DistilBERT-architecture, applications & comparison

·       LLM Applications: Text generation, summarization, question answering and conversational AI

·       Fine-Tuning: Fundamentals, workflow & practical aspects for adapting pretrained models

·       Hands-on: Build a Question-Answering and Text Generation Application using Hugging Face and an LLM API

Module 5

LangChain & Retrieval-Augmented Generation (RAG)

·       Introduction to LangChain: Framework architecture, LLMs, chat models, environment setup & API configuration

·       LLM Interaction: System, Human and AI messages; temperature, token limits and streaming

·       Prompt Engg. with LangChain: Prompt templates, message templates & few-shot prompting

·       Output Parsing: String, structured and list-based output parsers

·       LangChain Expression Language (LCEL): Chains, Runnable Sequence, Runnable Passthrough, Runnable Parallel and Runnable Lambda

·       Chain Execution: Sequential processing, batching and streaming

·       RAG Fundamentals: Architecture, workflow and applications of RAG

·       Document Processing: Document loading, text splitting and metadata handling; PDF, DOCX and text documents

·       Text Embeddings & Vector Stores: Embeddings, Chroma vector store and document indexing

·       Information Retrieval: Similarity search, Maximal Marginal Relevance (MMR) and vector-store retrievers

·       RAG Pipeline: Retrieval, context augmentation and response generation

·       RAG Optimization: Chunk size, overlap, retrieval parameters and prompt design

·       Hands-on: Build a Document Question-Answering (RAG) Chatbot using LangChain, Chroma and an LLM

Module 6

LangGraph & Agentic AI Workflows

·       Introduction to LangGraph: Architecture, use cases and relationship with LangChain

·       Graph Fundamentals: State, nodes, edges and message-based workflows

·       Building Workflows: Creating nodes, defining state & constructing the first LangGraph application

·       Conditional Workflows: Routing functions, conditional edges and dynamic execution

·       State Management: State, MessagesState, reducers, Annotated and message management

·       Memory & Persistence: Threads, Checkpointers and state persistence

·       Short-Term Memory: InMemorySaver and conversational state management

·       Long-Term Memory: Persistent storage using SQLite

·       State Inspection: StateSnapshot and monitoring workflow execution

·       Agentic Workflows: Multi-step reasoning, tool-based workflows and basic agent architecture

·       Error Handling & Workflow Control: Managing execution flow and maintaining reliable state

·       Hands-on: Build a Stateful AI Agent with LangGraph featuring conditional routing, conversation memory and persistent state

Module 7

Vector Databases & Semantic Search

·       Introduction: Need for vector databases; SQL vs NoSQL vs Vector Databases

·       Vector Fundamentals: Vector space, embeddings, similarity concepts and distance metrics -Cosine Similarity, Euclidean Distance and Dot Product

·       Vector Database Architecture: Collections/indexes, vectors, metadata, namespaces and similarity search

·       Vector Database Platforms: Overview and comparison of Pinecone, Chroma, FAISS and other popular vector databases

·       Pinecone: Account setup, API configuration, creating indexes & managing vector collections

·       Pinecone with Python: Connecting to Pinecone, generating embeddings, upserting vectors and metadata, querying and retrieving results

·       Advanced Retrieval: Metadata filtering, top-K search, similarity thresholds & hybrid search

·       Vector Database Applications: Semantic search, recommendation systems, document retrieval, question answering and AI-powered applications

·       Integration with GenAI Applications: Connecting vector databases with LLMs, RAG pipelines

·       Hands-on Project: Build a Semantic Search & Recommendation System using Python, embeddings and Pinecone

Module 8

Speech Recognition & Speech AI

·       Introduction to Speech AI: Evolution of speech recognition, applications & end-to-end speech processing pipeline

·       Speech & Audio Basics: Sound waves, frequency, harmonics, formants and phonemes

·       Digital Audio Processing: Sampling rate, bit depth, bit rate, audio formats and importing/processing audio using Python

·       Audio Signal Processing: Time-domain, frequency-domain and time-frequency representations; Fourier Transform and spectrograms

·       Audio Preprocessing & Feature Extraction: Noise reduction, normalization and extraction of relevant audio features for machine learning

·       Traditional Speech Recognition: Acoustic and language models, Hidden Markov Models (HMMs) and their evolution

·       Deep Learning for Speech Recognition: CNNs, RNNs and LSTMs for speech processing

·       Transformer-based Speech Recognition: Attention mechanisms, Transformers and modern end-to-end speech recognition systems

·       Speech-to-Text APIs & Models: Google Web Speech API and OpenAI Whisper; model-based vs API-based approaches

·       Whisper AI: Transformer-based speech recognition, audio transcription, multilingual transcription and batch processing of multiple audio files

·       Speech Recognition Evaluation: Word Error Rate (WER), Character Error Rate (CER) and practical evaluation of transcription quality

·       Text-to-Speech (TTS): Basics of speech synthesis and AI-powered text-to-speech systems

·       Hands-on Project: Build an AI-powered Speech Transcription & Text-to-Speech Application using Python, Whisper and a TTS service

Module 9

LLM Engineering & Production AI Applications

·       LLM Application Architecture: LLM APIs vs self-hosted models; open-source vs proprietary models; selecting models based on performance, cost, latency and use case

·       Tokens & LLM Economics: Tokenization, context windows, input/output tokens, API pricing and estimating application costs

·       Prompt Engineering for Applications: Prompt structure, system instructions, role-based prompting, prompt templates & prompt optimization across software development lifecycle

·       LLM Parameters & Output Control: Temperature, Top-P, maximum tokens and parameter selection for different use cases

·       LLM Application Design: Requirement analysis, application workflow, database/schema design and activity diagrams for AI-powered applications

·       OpenAI Playground & API Development: Model experimentation, API configuration, client initialization and structured interaction with LLMs

·       Building LLM Applications with Streamlit: Application structure, UI components, text and chat elements, forms and session-state management

·       Conversational AI Development: Chat functionality, conversation history, session management, feedback collection and user interaction

·       Reliability & Safety: Hallucination mitigation, prompt injection, input validation, output control and responsible application design

·       Cost Optimization & Performance: Token optimization, prompt optimization, model selection, caching, latency reduction and efficient API usage

·       Deployment & Scaling: Application deployment, configuration management, monitoring, scalability and production considerations

·       Hands-on Capstone Project: Develop and deploy a Production-Ready LLM Chat Application using an LLM API and Streamlit, incorporating conversation memory, feedback, cost optimization and basic security controls