Module 1: Python Basics

1. Introduction to Python

2.Variables

3.Operators

4. Conditional Statements

Module 2: Data Types in Python

1. Integers

2. Floats

3. Complex Numbers

4. Strings

5. Lists

6. Tuples

7. Sets and FrozenSets

8. Dictionaries

9. Booleans

Module 3: Loops in Python

1. For Loop

2. While Loop

Module 4: Functions

1. Python Functions

2. Types of Arguments

3. Recursive Functions

4. Lambda Functions

5. Built-in Functions

Module 5: Modules and Packages

1. OS Module (Operating System)

2. Glob Module

3. Shutil Module

4. Time Module

5. DateTime Module

6. Regular Expressions

7. Pytesseract

8. File Handling

9. Exception Handling

Module 6: Object-Oriented Programming (OOP) in Python

1. Inheritance

2. Encapsulation

3. Polymorphism

4. Abstraction

5. Iterator and Generator

6. Decorator

Module 7: Python Web Framework

1. Flask

Module 1: Preprocessing and Model Building

1. Numpy

2. Pandas

3. Scipy

4. Statsmodels

5. Sklearn

6. Nltk

7. Imblearn

8. Mlxtend

Module 2: Visualization

1. Matplotlib

2. Seaborn

3. Plotly (3D Plotting)

Module 3: NumPy (Numerical Python)

1. Introduction to Numpy

2. Datatypes of ndarrays

3. Dealing with ndarrays, copies, and views

4. Arithmetic operations

5. Indexing, slicing, splitting arrays

6. Shape manipulation

7. Stacking together different data

8. Statistics using Numpy

9. Linear algebraic operations

10. Logarithmic functions

Module 4: Pandas (Data Analysis)

1. DataFrame and Series

2. DataFrame operations

3. Data slicing, indexing

4. DataFrame functions

5. Reading files: csv, excel

6. Storing files in various formats

7. Useful DataFrame functions

8. Statistics using Pandas

9. Dealing with missing data

10. Operations over the data

11. Sorting DataFrame using values and index

12. GroupBy and Apply

13. Joins in Pandas

Module 5: Machine Learning Algorithms

1. Linear Regression

2. Logistic Regression

3. K-Nearest Neighbour

4. Decision Tree

5. Random Forest

6. AdaBoost

7. Support Vector Machine

8. Naive Bayes Classifier

9. Gradient Boost

10. Extreme Gradient Boost

11. K-Means Clustering

12. Principal Component Analysis

Module 6: Data Preprocessing

1. Handling of missing values

2. Handling of outliers

3. Encoding

4. Feature scaling

5. Binning

Module 7: Feature Selection

1. Filter Method

2. Wrapper Method

3. Embedded Method

Module 8: Hypothesis Testing

1. P-value

2. Z Test

3. T-Test

4. ANOVA

5. Chi-Square Test

Module 1: Deep Learning Fundamentals

1. What is Deep Learning? Why Deep Learning?

2. Deep Learning vs. Machine Learning

3. Types of Neural Networks and Their Applications

4. History of Perceptron

5. Why Perceptron Failed

Module 2: Basics of Neural Networks

1. Neural Network Basics

2. Building a Neural Network

3. Forward and Backward Propagation

4. Gradient Descent

Module 3: Advanced Optimization Techniques

1. Activation Functions

2. Sigmoid

3. Tanh

4. ReLU

5. Leaky ReLU

6. Softmax

7. P-ReLU

8. Softplus

Module 4: Activation Challenges with Activation Functions

 1.Sigmoid Vanishing Gradient Problem

 2. ReLU Dying Proble           

 3. Exploding Gradient

4. Advantages, Disadvantages, and Applications of Activation Functions

Module 5:  Loss Functions

1. MSE, MAE, Huber Loss, Log Error

2. Binary Cross-Entropy

3. Categorical Cross-Entropy

4. Sparse Categorical Cross-Entropy

Module 6: Regularization Techniques

1. Dropout Ratio

2. Overfitting Problem

Module 7: Implementing Artificial Neural Networks (ANN)

Module 8: Convolutional Neural Network (CNN)

1. CNN Fundamentals

2. CNN Architecture

3. Convolution Layer

4. Data Augmentation

5. Implementing CNNs

Module 1: Understanding Databases and SQL

1. What is a Database and SQL?

2. Properties of Databases and SQL

3. Use of Databases

4. Types of Commands in SQL

Module 2:  Data Manipulation in SQL

1. DDL Commands and Implementation

2. DML Commands and Implementation

Module 3: SQL Query Clauses

1. Where Clause

2. Order By Clause

3. Distinct Clause

4. Limit Clause

5. Group By Clause

6. Having Clause

Module 4: Advanced SQL Concepts

1. Subqueries and Types

2. NOT NULL Constraints

3. UNIQUE Constraints

4. PRIMARY KEY Constraints

5. FOREIGN KEY Constraints

Module 5: SQL Joins

1. Inner Join

2. Left Join

3. Right Join

4. Self Join

5. Cross Join

6. Full Join

Module 6: Introduction to MongoDB (NoSQL Database)

1. Create Database in MongoDB

2. Create Collection in MongoDB

3.Basic Database Operations in MongoDB

Module 1: NLP Basics

1. Basic Terminology of NLP

2. NLP Pipeline

Module 2: Exploratory Data Analysis (EDA) in NLP

1. N-gram Analysis

2. Wordcloud Generation

Module 3:Keyphrase Extraction Algorithms

1. YAKE

2. RAKE

3. PageRank

Module 4: Preprocessing Techniques

1. Tokenization 

2. Normalization

3. Stopwords Removal

4. Autocorrection

5. Language Detection and Translation with TextBlob,Google Translate API

Module 5: Text Cleaning

1. Stemming and Lemmatization

2. Removing Emojis

3. Handling Accented Characters

4. Contraction Mapping

Module 6: Feature Engineering

1. Count Vectorizer

2. TF-IDF (Term Frequency-Inverse Document Frequency)

3. Word2Vec

4. Doc2Vec

Module 7: Converting Unlabeled Data into Labeled Data

1. Clustering

2. Topic Modelling

Module 8: Sentiment Analysis

1. Root Cause Analysis

2. Document Classification

Module 1: Introduction to AWS and Deployment

1. Understanding Deployment

2. Need of AWS

3. Free Tier Account Creation

Module 2: Introduction to AWS Home

1. Regions and Availability Zones

2. Billing Dashboard

Module 3: Working with EC2 Instances

1. Understanding EC2

2. Creating and Launching EC2 Instances

3. Deployment of Project on EC2

4. Stopping and Terminating EC2 Instances

Module 4: Introduction to AWS Services

1. Overview of Various AWS Services (Theory)

Module 5: AWS Sagemaker

1. Creating a Notebook Instance

2. Building Models using Jupyter Sample Notebooks

3. Creating and Deleting IAM Roles

4. Deleting Sagemaker Endpoints

Module 6: AWS S3 (Simple Storage Service)

1. Introduction and Key Concepts

2. Creating Buckets and Uploading Objects

3. Integrating S3 with Sagemaker

4. Emptying and Deleting Buckets

Module 1:Introduction to Generative AI

1. What is Generative AI?

2. Why Do We Need Generative Models?

3. Understanding Generative Models and Their Importance

4. Generative AI vs. Discriminative Models

5. Recent Advancements and Research in Generative AI

6. Generative AI Project Lifecycle

7. Key Applications of Generative Models

Module 2: Guide to OpenAI and Its Ready-to-Use Models with Applications

1. Introduction to OpenAI

2. Understanding OpenAI API and Generating an API Key

3. Installing the OpenAI Package

4. Experimenting in the OpenAI Playground

5. Setting Up Your Local Development Environment

6. Exploring Different Templates for Prompting

7. Practical Implementation of OpenAI Models: GPT-3.5 Turbo, DALL-E 2, Whisper, CLIP, Davinci, and GPT-4

8. Implementing OpenAI Embeddings and Moderation

9. Using the Chat Completion API, Function Calling, and Completion API

10. Managing Tokens in OpenAI

11. Strategies for Optimizing Results

12. Image Generation with OpenAI LLM Models

13. Speech-to-Text with OpenAI

14. Using Moderation to Ensure Content Compliance with OpenAI

15. Understanding Rate Limits and Error Codes in OpenAI

16. Connecting ChatGPT to Third-Party Applications with OpenAI Plugins

17. Fine-Tuning OpenAI Models with Custom Data

Module 3: Mastering Prompt Engineering with OpenAI

1. Ask-Before-Answer Prompting

2. Perspective-Based Prompting

3. Contextual Prompting

4. Emotion-Driven Prompting

5. Laddering Technique in Prompting

6. Using ChatGPT for Effective Prompting

7. Identifying Missing Information

8. Self-Evaluative Prompting

9. ChatGPT-Powered Problem Splitting

10. Role Reversal in Prompting

11. Exploring Additional Prompts & Finding Inspiration

12. Advanced Prompts: CAN & DAN

Module 4: Vector Databases with Python for LLM Use Cases

1. Introduction to Vector Databases

2. Foundation of Vector Databases

3. Use Cases for Vector Databases

4. Text Embedding Techniques

5. Vector Similarity Search

6. Using SQLite as a Database

7. Storing and Retrieving Vector Data in SQLite

8. Chromadb Local Vector Database: Part 1 - Setup and Data Insertion

9. Querying Vector Data

10. Fetching Data by Vector ID

11. Database Operations: Create, Update, Retrieve, Delete, Insert, and Update

12. Applications in Semantic Search

13. Building an AI Chat Agent with LangChain and OpenAI

14. Weaviate Vector Database

15. Pinecone Vector Database

Module 5: Hands-On with LangChain

1. Introduction to LangChain

2. How LangChain Works

3. Installation and Setup of LangChain in Local Environment

4. Hello World of LangChain Application: Chaining a Simple Prompt

5. Components of LangChain: Schema, Model I/O, Prompts, Indexes, Memory, Chains, Agents, Callbacks

6. Understanding Prompts, Language Models, and Output Parsers

7. Concepts of Async API, Fake LLM Human Input, and LLM Caching

8. Implementing Chat Models with Human Input, Chain, Prompt, and Streaming

9. Implementing Output Parsers: JSON Parser, XML Parser, and List Parser

10. Retrieval Implementation: Document Loader, Document Transformer, Text Embedding, and Vector Store

11. Implementing Memory with Chat Messages, Conversational Knowledge Base, and Vector Store

12. Text Summarization with LangChain

13. Question Answering with LangChain

14. Building a Chatbot with LangChain

15. LangChain Streaming

16. Embeddings and Vector Data Stores in LangChain

17. Understanding PromptTemplate, LLM, and OutputParser

18. LangChain Expression Language

19. Binding Runtime Arguments

20. Configurable Alternatives

21. Adding Fallbacks

22. Running Arbitrary Functions

23. Using RunnableParallel and RunnableMap

24. Routing Between Multiple Runnables

25. Document Loaders

26. Analyzing CSV, PDF, and JSON Files Using LangChain

27. Prompt Templating and Prompt Management

28. Retrieval-Augmented Generation Chain

29. Working with Multiple Chains

30. Querying a SQL Database

31. Adding Moderation to Your LLM Application

32. Using Hugging Face Models with LangChain

33. Fine-Tuning Falcon 7B on a Custom Dataset

34. Mistral 7B: Fine-Tuning and Inference for Custom Use Cases

35. LangChain with Google PaLM2 Model

36. LangChain with Facebook LLaMA2 Model37. Building a LangChain Webapp with Streamlit and Flask
 

Module 6: Practical Guide to LlamaIndex with LLMs

1. Introduction to LlamaIndex

2. Differences Between LangChain and LlamaIndex

3. Differences Between LLaMA and LlamaIndex

4. Setting Up LlamaIndex in a Local Environment

5. Using LLMs with LlamaIndex

6. Exploring Llamahub

7. Connecting with External Data Sources

8. Understanding In-Context Learning and Fine-Tuning

9. The Importance of Indexing in LLM Applications

10. Persisting Indexes

11. Indexing Your Data

12. Creating Document Objects

13. Various Document Loaders

14. Verifying the Sources of Responses

15. Connecting with Different Document Types (CSV, TXT, PDF, etc.)

16. Document Management

17. Recursive File Processing from Directory and Subdirectory

18. Building Applications with LlamaIndex

19. Customizing LLM Models in Applications

20. Integration with Flask and Streamlit Endpoints

21. Enabling Streaming Responses

22. Chat Engine: Condense Mode

23. Chat Engine: React Mode

24. Customizing Prompts

25. Using Vector Databases like ChromaDB and Weaviate with LlamaIndex

26. Token Prediction and Cost Analysis

27. Integrations with OpenAI and Hugging Face

1. Hands-on projects applying Data Science and NLP techniques.

2. Real-world case studies and problem-solving tasks.

Project#1: Medical Chatbot Project with Llama 2, Pinecone, LangChain & Deployment AWS

Project#2: Research Paper Summarizer with LangChain, OpenAI, Streamlit and Weviate & Deployment AWS

Project#3: Developing a High-Quality Text-to-Speech System with Advanced NLP Techniques