Basic GenAI

Introduction of AI
Introduction of GenAI
History of GenAI
ML in GenAI
     Introduction of ML
     Supervised Learning
     Unsupervised Learning
     Reinforcement Learning
     Overfitting & Underfitting
     Model Evaluation Basics

DL in GenAI
     Introduction of DL
     Neural Networks
     Activation Functions
    Loss Functions
   CNN, RNN, LSTM

GenAI Models
    Autoencoders
    Variational Autoencoders (VAE)
    GANs
    Diffusion Models
    Model Comparison

Core GenAI
   Parameters & Model Size 
  Training vs Inference
  Fine-Tuning Basics
GPU & Compute Fundamentals

GenAI Tools & Ecosystem
   PyTorch
   TensorFlow
   Hugging Face
   Model Hubs & Datasets

 TransFormar

Limitations of RNN/LSTM
Transformer Architecture
Attention Is All You Need
Tokens & Embeddings
Positional Encoding
Encoder & Decoder

Transformer Block
       Feed Forward Network (FFN)
      Residual Connections
       Layer Normalization

Transformer Variants
        BERT (Encoder)
       GPT (Decoder)
       T5 (Encoder-Decoder)

Attention Mechanism
    Self-Attention
    Query, Key, Value (QKV)
     Multi-Head Attention
    Cross-Attention

Next Token Prediction

Large Language Models (LLMs)
Introduction of LLM
Model Parameters
Scaling Laws
Context Window
Tokens
Tokenizers
split into tokens
Output Controls
      Temperature
       Top-P
        Top-K
        Max Tokens
LLM Behavior
   Hallucinations
   Emergent Abilities
   Reasoning Limitations

Popular Models
        GPT
         Claude
          Llama
          DeepSeek
         Open-source

Prompt Engineering
Introduction of Prompt
System Prompt
User Prompt
Assistant Prompt
Prompt Templates
Best Practices(Context,Constraints,Guardrails)
Core Techniques
     Zero-Shot
    One-Shot
    Few-Shot
    Role Prompting
   Chain of Thought
    Self-Consistency
   ReAct

Structured Outputs
   JSON Output
   Function Calling
   Tool Calling

Embeddings

Introduction of Embeddings
Text to Vectors
Semantic Similarity
Cosine Similarity
Euclidean Distance
Embedding Models
   OpenAI Embeddings
   Sentence Transformers
  BGE Models
   E5 Models

Vector Databases

Introduction of Vector Database
Storing Embeddings
Metadata Storage
Collections & Namespaces
Similarity Search
K-Nearest Neighbors
Top-K Retrieval
ANN Search
Vector Databases
    Chroma
   FAISS
  Pinecone
  Weaviate

Retrieval Optimization
       Metadata Filtering
       Hybrid Search
       Reranking
      Caching
 Retrieval-Augmented Generation (RAG)
Introduction RAG
RAG Architecture
RAG pipeline
     Document Loading
     Chunking
     embedding
      storing

Vector Search
Hybrid Search
Reranking
Parent-Child Retrieval
Multi-Query Retrieval
Graph RAG

Evaluation
     Recall
     Precision
    Faithfulness

AI Agents

Introduction of AI Agent
Planning
Memory
Reasoning
Tools

Agent Patterns

       ReAct
      Plan & Execute
      Reflection
Tool Usage
      Function Calling
        APIs
       Code Execution

Multi-Agent Systems
     Agent Communication
     Agent Collaboration
    Task Delegation
     Agent Orchestration

 Agent Frameworks

LangChain

IntroDuctions of Langchain
Tools
Memory
Retrievers
Agents

LlamaIndex

introduction 
Indexing
Query Engines
RAG Pipelines
22. LangGraph
Introduction
State Management
Workflow Design
Human-in-the-Loop

Fine-Tuning
Introduction of Tuning

Tuning Types
    Full Fine-Tuning
    Instruction Tuning

PEFT
    LoRA
    QLoRA
    Adapters

Data Collection
Data Formatting
Benchmarks
Model Comparison

Multimodal AI
Intro of Multimodal AI
MultiModel LLM

 Modalities
    Text
   Image
  Audio
  Video