Only Few Seats Left

Module 1

Introduction to AI & Gen AI

·       Building an AI tool

·       Natural vs Artificial Intelligence, Brief history of AI, Weak vs Strong AI

·       AI vs Data Science vs Machine Learning vs Deep Learning

·       Data: Collection, Labelled vs Unlabeled, Structured vs Unstructured, Metadata

·       Overview of Machine Learning (Supervised, Unsupervised and Reinforcement Learning)

·       Overview of Deep Learning, Robotics, Computer Vision, Traditional ML, Generative AI

·       Generative AI: Introducing ChatGPT, Natural Language, Processing (NLP)

·       Large Language Models (LLMs): Training, N-Grams, RNNs, Transformers

·       Building LLMs: Prompt Engineering, Fine Tuning, RAG

·       Foundation Models vs Private Models

·       Inconsistency and Hallucination in Gen AI, Budgeting, Latency, Running out of Data

·       AI stack: Python, Working with APIs, Vector Databases, Hugging Face, LangChain

Module 2

Fundamentals of Python Programming

• Basics of Python Language
• Python objects with details of Numbers/Variables/Strings/Lists/Dictionaries/Tuples etc. 
• Variable Assignment, Indexing & Slicing
• Comparison & Logical operators
• Range, List Comprehension, Functions, Lambda expressions.
• Scope, with statement, Working with various Files types, Error Handling
• Regex: Anchors and Groupings, Range Expressions, Non-Greedy Matching, Substitutions.
• Object Oriented Programming, -class, Attributes, Inheritance, Polymorphism

Module 3

Working with Python Libraries: OS, Requests, and Pandas

·       Understanding Python Module: OS module, Import Techniques and Best Practices

·       Requests and HTTPZ Libraries: Getting Started, Handling Errors and Managing Authentication and Headers (Open AI API)

·       Introduction and working with Pandas

·       Series, DataFrames, working with various data types, Group-By operation

·       Selecting a single column, important series methods

·       Indexing & Sorting; loc & iloc with series; Inspecting DataFrames, filtering with conditional operators

Module 4

Natural Language Processing (NLP)

·       Introduction, Supervised vs Unsupervised NLP

·       Data preparation, Handling Stop words, Regular Expressions

·       Tokenization, Stemming, Lemmatization, N-grams

·       Text tagging, Parts of Speech (POS) tagging, Name Entity Recognition (NER)

·       Sentiment Analysis, Rule-based Sentiment Analysis, Pre-trained Transformers

·       Numerical Representation of text, Bag of Words, TF-IDF

·       Topic Modelling, Latent Dirichlet Allocation (LDA), Latent Semantic Analysis (LSA)

·       Custom text classifier using various ML models     

Module 5

Large Language Models (LLMs)

·       Understanding LLMs, General Purpose Models, Pre-training and Fine Tuning

·       Deep- Learning recap, Transformer Architecture, Input Embeddings

·       Multi-headed Attention, Feed-Forward Layer, Masked multihaed Attention

·       Understanding GPT, Open AI API, Generating Text, Customizing GPT output

·       Key word text summarization, Coding a simple chatbot using LangChain in Python

·       Hugging Face, Transformer Pipeline, Pre-trained tokenizers, Special tokens

·       Q&A models : BERT architecture, Tokenizer, Embeddings, Calculating response

·       Creating QA bot, BERT, RoBERTa, DistilBERT, GPT vs BERT vs XLNET, XLNET Embeddings and Fine Tuning

Module 6

LangChain

·       LangChain Introduction, Tokens and Models, Setting up Environment, Open API key

·       System, User and Assistant roles, Creating chatbot, Temperature, Max Tokens, Streaming

·       LangChain Framework, ChatOpenAI, System, AI and Human messages

·       Prompt Templates and Prompt Values, Few-shot chat message prompt templates

·       String output parser, Comma-separated list output parser, Datetime output parser

·       Piping a prompt, model and parser, Batching, Streaming, Runnable Sequence class

·       Piping chains and Runnable Passthrough, Runnable Parallel, Runnable Lambda

·       Retrieval Augmented Generation (RAG): Document Loading, Splitting and Embedding

·       Document storing, retrieval and generation, loading with PyPDFLoader, Docx2txtLoader

·       Splitting with character text splitter, markdown header text splitter

·       Text embedding with OpenAI, Chroma vectorstore (Inspecting and Managing docs)

·       Retrieval: Similarity search, Maximal Marginal Relevance (MMR) search, Vectorstore-backed retriever

·       Generation: Stuffing documents and Generating a response 

Module 7

LangGraph

·       States, nodes and Edges, First graph: Importing relevant classes, Building graph

·       Conditional edges: Defining nodes, routing function, Building the graph

·       Annotated construct and reducer functions, MessagesState, RemoveMessages

·       Checkpointers and threads, Short-term memory with the InMemorySaver class

·       The StateSnapshot class, Long-term memory with SQLite    

Module 8

Vector Databases

·       Database comparison: SQL, NoSQL and Vector, Understanding Vector databases,

·       Vector space: Introduction, Distance Metrics, Vector Embeddings

·       Vector database, comparison, Pinecone registration, walkthrough and creating index

·       Pinecone with Python: Connection, Pinecone Index, Upsetting data and using embedding

·       Vector database for Recommendation Engines, Biomedical research, Semantic search

Module 9

Speech Recognition Module

·       Development and Evolution, Formants, Harmonics and Phonemes

·       Sound and Sound waves: Fundamentals and properties

·       Sample Rate, bit depth, bit rate, Audio signal processing for Machine Learning and AI

·       Audio Features: Time-domain, Frequency-domain, time-frequency-domain, Fourier transform

·       Acoustic and language modeling, Hidden Markov Models (HMMs)

·       Traditional Neural Networks: CNNs, RNNs and LSTMs

·       Advanced speech recognition systems: Transformers

·       Building a Speech Recognition Model

·       Audio file formats for speech recognition, Importing audio files in python

·       Google Web Speech API, Evaluation metrics: WER and CER

·       Dealing with background, Noise Creating spectrogram

·       Whisper AI: Transformer-based speech-to-text, Transcribing multiple audio files 

• Reversing the process: AI-powered text-to-speech

Module 10

LLM Engineering

·       Hosting an LLM vs Using an API, Open-Source vs Closed-source, Tokens

·       Pricing: Hosting an LLM vs Pay-by-Token, Initial Prompt Development

·       Database Design and Schema Development, Activity Diagram

·       OpenAI Playground, Optimizing Temperature, Top P for Different Use Cases

·       Prompt Engineering for Software Lifecycle

·       Streamlit: Introduction, Pros and Cons, Text Methods, Chat Elements, Session State

·       Initializing an OpenAI Client, Implementing the Chat Functionality, Building the Setup Page

·       Enhancing Chatbot Interaction with Session State, Feedback Functionality, Deployment

·       Application Structure, Prompt Structure, Hallucinations, Prompt Injection

• Counting Tokens, Cost reduction and Scaling