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 Generative AI | AI Future Prospects | Career Opportunities | Training Modules | Instructor Introduction | QnA Session
Demo Session
01:58:25
Class 01 – Basics of Python (Punctuations, Mathematical Operators, Brackets and Craces, Logical and Comparison) | Syntax and Semantics | Conditional Statement | Python Variables (Variables, Declaring and Assigning Variables, Naming Conventions, Types) | Practical Examples and Common Errors
Generative AI (Batch-02) – Session 01
02:06:21
Class 02 – Data Types (Integers, Floating, Point Numbers, Strings, Booleans) | Advanced Data Types (Lists, Tuples, Sets, Dictionaries) | Operators (Arithmetic, Comparison, Logical) | Conditional Statements (IF, ELIF, ELSE) | Practical Example – Employees Bonus Calculator
Generative AI (Batch-02) – Session 02
01:59:22
Class 03 – Python Basics (Syntax, Variables, and Basic Operations) | Understanding Data Types (Integers, Floats, Strings, Booleans, Lists, Tuples, Sets, and Dictionaries) | Conditional Statements (If, Else, Elif, Nested Conditions, Logical Operators)
Generative AI (Batch-02) – Session 03
01:56:18
Class 04 – Conditional Statements (If, Else, Elif, Nested Conditions, Logical Operators) | Remaining If, Elif, Else Statements | Loops in Python (For Loop, While Loop, Nested Loops, and Loop Control Statements (Break, Continue, Pass)) | Introduction to Lists
Generative AI (Batch-02) – Session 04
02:04:24
Class 05 – Functions in Python (Definition, Calling, and Arguments) | Lambda Functions (Writing Anonymous Functions) | Map Function (Applying Functions to Iterables | Filter Function (Filtering Data Based on Conditions)
Generative AI (Batch-02) – Session 05
02:01:22
Class 06 – Dictionaries in Python Including Key-Value Pairs, Accessing and Modifying Data, and Common Methods | Functions in Python Including Definition, Calling, Parameters, Return Statements, and Scope
Class 08 – Multiple Inheritance | Polymorphism (Method Overriding & Abstract base method) | Encapsulation and Abstraction | Encapsulation with Getter and Setter | Abstraction | Magic Method
Generative AI (Batch-02) – Session 08
02:15:32
Class 09 – Setting Up VS Code Environment | Streamlit (Basic Frontend with Title & Text) | Streamlit Frontend (Creating & Displaying Dataframes, Select Box, Text Slider, Upload/ Download Dataframes) | Machine Learning Classification Prediction Project using Streamlit (Using Random Forest Classifier and Iris Dataset for Predictions)
Generative AI (Batch-02) – Session 09
01:54:59
Class 10 – Introduction to NLP in Deep Learning | Artificial Neural Networks (ANNs) and Recurrent Neural Networks (RNNs) | RNN Forward Propagation | Simple RNN Backward Propagation | Problems with RNN | Project Discussion
Generative AI (Batch-02) – Session 10
01:56:57
Class 11 – Artificial Neural Networks (ANN) Project: Understanding Dataset | Feature Engineering (Label Encoding, One Hot Encoder, Creating Pickle Files, Train Test Split Method, Scaling Dataset) | ANN Implementation (Model Training)
Generative AI (Batch-02) – Session 11
02:23:25
Class 12 – Artificial Neural Networks (ANN) Project: Model Training Coding + Understanding Neural Network + Dense + Optimizer + Learning Rate + Early Stopping, Tensorboard + Saving in Scaler Format | Tensorboard Visualization Complete (Val Loss + Val Accuracy) | Predicting Custom Input Data on Trained Model + Analysis | Deploying Streamlit WebApp for ANN Project on Local Host using Streamlit
Class 14 – Recurrent Neural Network (RNN) – Training Process in LSTM RNN | Complete GRU RNN Understanding | End to End Project (Data Collection, Data Preparation and Pre-Processing, Model Building, Model Training, Evaluation and Deployment)
Generative AI (Batch-02) – Session 14
02:10:23
Class 15 – Bidirectional RNN (Including Flow and Architecture) | Encoder and Decoder Model (Seq2Seq Learning) | Problem with Encoder Decoder | Attention Mechanism (Beginning)
Generative AI (Batch-02) – Session 15
01:32:13
Class 16 – Attention Mechanism Complete Topics | Transformers Complete Topics | Introduction to Generative AI and LLMs | Understanding of Generative AI Research Papers
Generative AI (Batch-02) – Session 16
01:44:32
Class 17 – Introduction to Generative AI | Understanding Differences Between AI, ML, DL, and Generative AI | LLM Models Understanding | Training of OpenAI’s ChatGPT and LLaMA 3 LLM Models with Supervised Fine-Tuning | Evolution of AI Models | Complete LangChain Ecosystem Deep Dive
Generative AI (Batch-02) – Session 17
01:49:37
Class 18 – Using Language Model | Using PromptTemplates and OutputParsers | Using LangChain Expression Language (LCEL) to Chain Components Together | Using Human and System Messages to Structure Model Inputs | Extracting Content Using an Output Parser Instead of Raw AI Messages | Using LCEL to Chain Multiple Components Together | Using Prompt Templates to Simplify and Structure Input Messages | Setting Up Environment | Defining a Model | Creating Prompt Templates | Setting Up an Output Parser | Using LCEL | Invoking | Initiated Chatbot with Conversational History Project | Environment Connection | Calling Model
Generative AI (Batch-02) – Session 18 (Part A)
01:26:30
Generative AI (Batch 02) – Session 19 (Part B)
22:27
Class 19 – Project (Part 01): Conversational Q&A Chatbot App with Message History and Session IDs | Managing Conversation State | Handling Multiple User Sessions | Storing and Retrieving User Queries | Maintaining Context Across Sessions | Implementing Session ID Management
Generative AI (Batch-02) – Session 20
01:59:04
Class 20 – Project (Part 02): Conversational Q&A Chatbot App with Message History and Session IDs | Managing Conversation State | Handling Multiple User Sessions | Storing and Retrieving User Queries | Maintaining Context Across Sessions | Implementing Session ID Management
Generative AI (Batch-02) – Session 21 (Part A)
02:09:14
Generative AI (Batch-02) – Session 22 (Part B)
06:54
Class 21 – Project (Part 01): RAG Document Q&A with GROQ API and Hugging Face Application | Understanding Retrieval-Augmented Generation (RAG) Concept | Connecting to GROQ API for Fast LLM Responses | Using Hugging Face for Embeddings and Model Access | Document Uploading and Preprocessing | Building the Retriever and Reader Pipeline | Querying Documents and Getting Contextual Answers
Generative AI (Batch-02) – Session 23
01:42:52
Class 22 – Project (Part 02): RAG Document Q&A with GROQ API and Hugging Face Application | Understanding Retrieval-Augmented Generation (RAG) Concept | Connecting to GROQ API for Fast LLM Responses | Using Hugging Face for Embeddings and Model Access | Document Uploading and Preprocessing | Building the Retriever and Reader Pipeline | Querying Documents and Getting Contextual Answers
Generative AI (Batch-02) – Session 24
01:42:23
Class 23 – Introduction to Concepts of Tools and Agents in LangChain, Defining Tools as External Resources for LLMs, Introducing Agents to Decide Tool Usage and Timing, Discussing Strategies to Enhance Search Engine Capabilities by Fetching and Integrating Real-Time Data, Outlining Deeper Future Implementations
Generative AI (Batch-02) – Session 25
01:59:15
Class 24 – Tool Creation, Custom Tools, Preparing for Agents, Combining LLM with Tool List, Creating Dynamic Agents, Wrapping Agents in AgentExecutor, Building Streamlit UI for User Queries and Groq API Key, Defining Multiple Tools with Dynamic Selection, Executing Queries with Real-Time Chain of thought Reasoning, Handling Errors, Unexpected Results, and Infinite Loops
Generative AI (Batch-02) – Sesssion 26
01:41:02
Class 25 – Generative AI Project – Chat with SQL DB Using LangChain SQL Toolkit and AgentType | Showcased Project Demo | Explained Automatic SQL Query Generation by Agents | Discussed LangChain SQL Toolkit Functionality | Created Local SQLite Database | Defined Student Table with Relevant Columns | Connected DB to LangChain SQL Agent | Installed MySQL Workbench | Created Sample Table with 50 Rows | Verified Data Creation | Laid Foundation for Streamlit Integration to Enable Natural Language Querying of MySQL via LLM
Generative AI (Batch-02) – Session 25
01:58:29
Class 26 – Generative AI Project: Chat with SQL DB Using LangChain SQL Toolkit and AgentType | Built Streamlit Web App for SQLite or MySQL | Defined Configure DB Function Returning SQLDatabase Object | Collected User’s Groq API Key and DB Credentials | Created Agents to Query Selected Datasets via LLM | Integrated User’s DB Choice with LangChain SQL Agent | Displayed Queries and Results in Streamlit Chat Interface
Generative AI (Batch-02) – Session 26
02:02:25
Class 27 – Chat with SQL Database Application (Developed End-to-End Streamlit App Supporting SQLite and MySQL, Implemented Database Configuration Function, Integrated User’s Database Choice with LangChain SQL Agents, Displayed Queries and Results in Streamlit Chat Interface, Tested Both SQLite and MySQL Scenarios to Verify Auto-Generated SQL by Agents) | URL Summarization Project Initiated (Overview of Project Objectives and User Interface Design, Explained Functionality for YouTube and Dynamic Webpage Summarization, Discussed Text Chunking and Data Transmission Approach)
Generative AI (Batch-02) – Session 27
01:50:48
Class 28 – End-to-End Deployment of YouTube and Website Summarization Bot | Setup and Imports: Installed and Explained Streamlit, Validators, LangChain, YouTube-Transcript-API | UI Layout: Configured Page Title and Icon, Sidebar with Usage Steps, Secure API Key Input, Summary Length Slider | Input Validation: Collected API Key and URL, In-Body Warning for Missing Key, URL Format Validation | Content Loading: Used YoutubeLoader with Error Handling for Disabled Captions, UnstructuredURLLoader for Webpages | LLM Integration: Initialized ChatGroq with API Key, Built Dynamic PromptTemplate, Ran Load_Summarize_Chain | UX Feedback: Added Spinner During Fetch and Summarize, Displayed Success and Error Messages | Clean Code Practices: Added Inline Comments, Modularized Code into Validation, Loading, LLM, and UI Sections for Readability
Generative AI (Batch-02) – Session 28
02:02:31
Class 29 – Project 11: Fine-Tuning and Quantization | Understanding Quantization | Importance of Shrinking Numbers for Faster Inference | Precision Formats Overview | Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) | Introduction to Low-Rank Adaptation (LoRA) | Understanding Quantized LoRA (QLoRA) | Calibration Techniques | Low-Rank Approximations
Generative AI (Batch-02) – Session 29
01:52:22
Class 30 –
Generative AI (Batch-02) – Session 30
01:52:09
Class 31 – Project 11 – Fine-Tuning Techniques for Efficient Model Deployment | Explained Quantization: Reducing Model Precision for Efficiency | Covered Precision Types: FP-32 | FP-16 | INT-8 | Introduced Calibration and Quantization-Aware Training (QAT) to Maintain Accuracy | Discussed Low-Rank Adaptation (LoRA) for Lightweight Fine-Tuning | Explored Quantized LoRA (QLoRA) for Ultra-Compact Fine-Tuning in Real-World Deployments