Generative AI (Beginner to Advanced) with Machine Learning and Deep Learning
What Will You Learn?
- Master the creation of advanced generative AI applications using the Langchain framework and Huggingface's cutting-edge models.
- Understand the architecture and design patterns for building robust and scalable generative AI systems.
- Gain practical experience in deploying generative AI models across various environments, including cloud platforms and on-premise servers.
- Explore deployment strategies that ensure scalability, reliability, and optimal performance of AI applications.
- Develop Retrieval-Augmented Generation (RAG) pipelines to boost the accuracy and efficiency of generative models by integrating retrieval mechanisms.
- Seamlessly incorporate Huggingface's pre-trained models into Langchain applications to leverage their powerful NLP capabilities.
- Customize and fine-tune Huggingface models to meet specific application needs and use cases.
- Engage in real-world projects demonstrating Generative AI applications in domains such as chatbots, content generation, and data augmentation.
Course Content
Introduction of the Course
-
Introduction-What we will learn in this course
-
Getting Started With VS Code
-
Different Ways Of creating Python Environment
-
Python Basics-Syntax And Semantics
-
Variables In Python
-
Basics DataTypes In Python
-
Operators In Python
Python Control Flow
-
Conditional Statements (if, elif, else)
-
Loops In Python
Data Structures using Python
-
Lists and List Comprehension In Python
-
Tuples In Python
-
Dictionaries In Python
-
Real World Use cases Of List
Functions in Python
-
Getting Started With Functions
-
More Coding Examples With Functions
-
Lambda Function In Python
-
Map Function In Python
-
Filter Functions In Python
Importing, Creating Modules an Packages
-
Import Modules And Packages In Python
-
Standard Libraries Overview In Python
File Handling with Python
-
File Operations With Python
-
Working with File Paths
Exception Handling
-
Exception Handling With try except else and finally blocks
OOPS Classes and Objects
-
Classes And Objects In Python
-
Single And Multiple Inheritance
-
Polymorphism In OOPS
-
Encapsulation In OOPS
-
Abstraction In OOPS
-
Magic Methods In Python
-
Operator Overloading In Python
Streamlit with Python
-
Getting Started With Streamlit
-
Example Of ML APP With Streamlit
Machine Learning for Natural Language Processing (NLP)
-
Roadmap To Learn NLP
-
Practical Usecases Of NLP
-
Tokenization and Basic Terminologies
-
Tokenization Practicals
-
Text Preprocessing Stemming Using NLTK
-
Text Preprocessing Lemmatization
-
Text Preprocessing Stopwords
-
Parts Of Speech Tagging Using NLTK
-
Named Entity Recognition
-
Whats Next
-
One Hot Encoding
-
Advantages and Disadvantages of OHE
-
Bag Of Words Intuition
-
Advantages and Disadvantages Of BOW
-
BOW Implementation Using NLTK
-
N Grams
-
N gram Implementation Using NLTK
-
TF-IDF Intuition
-
Advantages and Disadvantages OF TFIDF
-
TFIDF Practical Implementation
-
Word Embeddings
-
Word2vec Intuition
-
Word2vec CBOW Detailed Explanation
-
Skip Gram Indepth Intuition
-
Advantages OF Word2vec
-
Word2vec Practical Implementation
Deep Learning for Natural Processing Language (NLP)
-
Introduction To NLP In Deep Learning
-
ANN VS RNN
Simple Recurrent Neural Network (RNN) In-depth Intuition
-
RNN Forward Propagation With Time
-
Simple RNN Backward Propagation
-
Problems With RNN
Artificial Neural Networks (ANN) Project Implementation
-
Discussing Classification Problem Statement And Setting Up Vs Code
-
Feature Transformation Using Sklearn With ANN
-
Step By Step Training With ANN With Optimizer and Loss Functions
-
Prediction With Trained ANN Model
-
Integrating ANN Model With Streamlit Web APP
-
Deploying Streamlit web app with ANN Model
-
ANN Regression Practical Implementation
-
Finding Optimal Hidden Layers And Hidden Neurons In ANN
Project: IMDB Dataset And Feature Engineering
-
Problem Statement
-
Getting Started With Embedding Layers
-
Implementing Word Embedding With Keras TensorFlow
-
Loading And Understanding IMDB Dataset And Feature Engineering
-
Training Simple RNN With Embedding Layers
-
Prediction From Trained Simple RNN
-
End To End Streamlit Web App Integrated With RNN And Deployment
LSTM RNN In-depth Intuition
-
Why LSTM RNN
-
LSTM RNN Architecture
-
Forget Gate In LSTM RNN
-
Input Gate And Candidate Memory In LSTM RNN
-
Output Gate In LSTM RNN
-
Training Process In LSTM RNN
-
Variants Of LSTM RNN
-
GRU RNN Indepth Intuition
Project: LSTM and GRU
-
Discussing Problem Statement
-
Data Collection And Preprocessing
-
LSTM Neural Network Model Training
-
Prediction From LSTM Model
-
Streamlit Webapp Integration With LSTM Trained Model
-
GRU RNN Variant Implementation
Bidirectional RNN In-depth Intuition
-
Bidirectional RNN- Why To Use It?
Encoder and Decoder
-
Indepth Intuition OF Encoder And Decoder-Sequence to Sequence Architecture
-
Problems With Encoder and Decoder
Attention Mechanism – Seq2Seq Architecture
-
Attention Mechanism Indepth Architecture Explanation
Transformers
-
Plan Of Action
-
What and Why To Use Transformers
-
Understanding The basic Architecture Of Encoder
-
Self Attention Layer Working
-
Multi Head Attention
-
Feed Forward Neural Network With Multi Head Attention
-
Positional Encoding Indepth Intuition
-
Layer Normalization
-
Layer Normalization Examples
-
Complete Encoder Transformer Architecture
-
Decoder-Plan Of Action
-
Decoder-Masked Multi Head Attention
-
Encoder and Decoder Multi Head Attention
-
Decoder Final Linear And Softmax Layer
Introduction to Generative AI and LLM Model
-
What is Generative AI- AI Vs ML Vs DL Vs Generative AI
-
How Open AI ChatGPT or LLama3 LLM Models are Trained
-
Evolution OF LLM Models
-
All LLM Models Analysis
Introduction to LangChain for Generative AI
-
Complete Langchain Ecosystem
-
Creating Virtual Environment
Getting Started with LangChain and Open AI
-
Getting Started With Langchain And OpenAI
Important Components and Modules in LangChain
-
Introduction To Basic Components And Modules In Langchain
-
Data Ingestion With Documents Loaders
-
Text Splitting Techniques-Recursive Character Text Splitter
-
Text Splitting Technique-Character Text splitter
-
Text Splitting Technique-HTML Header Text Splitter
-
Text Splitting Technique-Recursive Json Splitter
-
Introduction To OpenAI Embedding
-
Ollama Embeddings
-
Huggingface Embeddings
-
VectorStores-FAISS
-
VectorStore And Retriever- ChromaDB
-
Going Forward
Getting Started with Open AI and Ollama
-
Building Important Components Of Langchain
-
Building GENAI Apps
-
Understanding Retrievers and Chains
-
Introduction To Ollama And Set Up
-
Simple Gen AI App Using Ollama
-
Tracking Gen AI App Using Langsmith
Building Basic LLM application Using LCEL (LangChain Expression Language)
-
Getting Started With Open source Models Using Groq API
-
Building LLM, Prompt And Stroutput Chains With LCEL
-
Deploy Langserve Runnable And Chain As API
Building Chatbots With Conversation History Using LangChain
-
Building Chatbot With Message History Using Langchain
-
Working With Prompt Template And Message Chat History Using Langchain
-
Managing the Chat Conversation History Using Langchain
-
Working With VectorStore And Retriever
Conversational Q&A Chatbot With Message History
-
Building Conversational Q&A Chatbot With Message History
Project: Q&A Chatbot Generative AI App with Open AI
-
Introduction To The Q&A Chatbot
-
Creating Virtual Environment
-
Creating Prompt Template And Integrating Open AI API
-
Creating Streamlit Web App and Integrating Response With OpenAI API
-
Q&A Chatbot With Ollama And Open Source Models
RAG Document Q&A with GROQ API and Llama3
-
Introduction To Groq Cloud And LPU Inference Engine
-
RAG Document Q&A With GROQ API And LLama3
Project: Conversational Q&A Chatbot – Chat with PDF with Chat history
-
Demo of the Conversational Q&A Chatbot
-
End To End Conversational Q&A Chatbot Implementation
Search Engine with LangChain Tools and Agents
-
Introduction To Tools And Agents
-
Creating Tools Using Langchain
-
Executing Tools And LLM with Agent Executors
-
End To End Search Engine GEN AI App using Tools And Agent With Open Source LLM
Gen AI Project-Chat With SQL DB With LangChain SQL Toolkit and Agentype
-
Demo of the Project
-
Preparing the Data For SQlite3 Database
-
Preparing The Data For My SQL Database
-
Creating the Streamlit Web app and Configuring the Databases
-
Integrating Web App With Langchain SQL Toolkit And Agent type
Text Summarization with LangChain
-
Introduction To text summarization With Langchain
-
Stuff Chain And Map Reduce Text Summarization Indepth Intuition
-
Stuff And Map Reduce Summarization Implementation
-
Refine Chain Summarization Intuition And Implementation
Project: YouTube Video And Website URL Content Summarization
-
End To End Project Demo
-
Implementing Youtube Video And Website Url Content Summarization GEN AI App
Project: Text To Math Problem Solver Using Google Gemma 2
-
Demo of the End to End Project
-
End To End Text to Math Problem Solver Using Google Gemma2 Model Implementation
HuggingFace and LangChain Integration
-
Introduction To Huggingface And Langchain Integration
-
Langchain And Huggingface Integration Practical Implementation
-
End to End Gen AI Project With Langchain And Huggingface
Project: PDF Query RAG With LangChain And AstraDB
-
End To End Project With PDf Query RAG With Langchain And AstraDB
Multilanguage Code Assistant using CodeLama
-
End To End MultiLanguage Code Assistant Implementation
Deployment OF Gen AI APP In Streamlit and Huggingspaces
-
Deployment OF Gen AI APP In Streamlit Cloud
-
Deployment Of Gen AI App In Huggingface spaces
Generative AI in AWS Cloud
-
Life Cycle Of Gen AI Project In AWS Cloud
-
Introduction To AWS Bedrock With Implementation
-
Document Q&A RAG With Langchain And Bedrock
-
End To End Blog Generation Gen AI Using AWS Lambda And Bedrock
-
Deployment Of Huggingface OpenSource LLM Models In AWS Sagemakers With Endpoints
Getting Started with Nvidia NIM and LangChain
-
Building RAG Document Q&A With Nvidia NIM And Langchain
Creating Multi AI Agents Using CrewAI For Real World Usecases
-
Youtube Videos To Blog Page Using CrewAI Agents
Hybrid Search RAG with vector Database and LangChain
-
Introduction To Hybrid Search
-
Reciprocal Rank Fusion In Hybrid Search
-
End To End Hybrid Search RAG With Pinecone db And Langchain
Introduction to Graph Database and Cypher Query Language with LangChain
-
Introduction to Graph DB with Langchain
-
What is Knowledge Graph
-
Creating Your Neo4j AuraDB Database Instance
-
RDBMS VS Graph Database
-
Neo4j Property Graph Data Model
-
Getting Started With Cypher Query Language
-
Intermediate To Advance Cypher Query Language
Implementing Graph Database with Python and LangChain
-
Getting Started-Creating Environment
-
Inserting Data In Graph DB With Python And Langchain
-
Creating GraphQuery Chain With Langchain
-
Prompting Strategies GraphDB With LLM
Detailed Intuition and Implementation Of Finetuning LLM Models
-
What Is Quantization Indepth Intuition
-
LORA And QLORA Indepth Mathematical Intuition
-
Practical Implementation fine Tuning Custom Data With Google Gemma Model
Project: Finetuning LLM Models with Lamini Platform
-
End To End Finetuning LLM Models With Lamini AI Cloud
Building Stateful, Multi-Actor Applications Using LangGraph
-
Introduction To Langgraph
-
Creating Chatbots Using Langgraph
-
Creating Chatbots With External Tools Workflow With Langgraph
-
End to End Multi AI RAG Chatbots Using Langgraph And AstraDB
Student Ratings & Reviews
No Review Yet