Premium
Title Page
1/1/2025
Copyright Page
1/1/2025
Dedication Page
1/1/2025
About the Author
1/1/2025
About the Reviewers
1/1/2025
Acknowledgement
1/1/2025
Preface
1/1/2025
Table of Contents
1/1/2025
1. Introducing New Age Generative AI
1/1/2025
Introduction
1/1/2025
Structure
1/1/2025
Objectives
1/1/2025
Overview of generative AI
1/1/2025
Retrieval system
1/1/2025
Sparse retrieval
1/1/2025
Dense retrieval
1/1/2025
Generation system
1/1/2025
Types of generation systems
1/1/2025
Autoregressive generation
1/1/2025
Prompting strategies
1/1/2025
Understanding where generation systems excel
1/1/2025
Combining retrieval and generation
1/1/2025
Retrieval-augmented generation
1/1/2025
RAG working
1/1/2025
Architecture of a basic RAG pipeline
1/1/2025
Types of RAG architectures
1/1/2025
Iterative RAG
1/1/2025
Vector databases and RAG
1/1/2025
Prompt engineering for RAG
1/1/2025
Advanced RAG techniques
1/1/2025
Applications of RAG
1/1/2025
Orchestration in AI systems
1/1/2025
Orchestration in RAG systems
1/1/2025
Orchestration in agentic systems
1/1/2025
Tokens in AI systems
1/1/2025
Vector database
1/1/2025
Understanding vector databases
1/1/2025
Indexing algorithms in vector databases
1/1/2025
Search algorithms in vector databases
1/1/2025
Embeddings and embedding models
1/1/2025
Importance of vector databases for RAG and agentic systems
1/1/2025
Reranking
1/1/2025
Bi-encoders vs. cross-encoders
1/1/2025
Cross-encoders for reranking
1/1/2025
Guardrails
1/1/2025
Types of guardrails
1/1/2025
Methods of applying guardrails
1/1/2025
Without guardrails
1/1/2025
Industry examples of guardrail solutions
1/1/2025
Agents
1/1/2025
Agentic RAG vs. non-agentic RAG
1/1/2025
Model Context Protocols
1/1/2025
Conclusion
1/1/2025
2. Deep Dive into Multimodal Systems
1/1/2025
Understanding vision-language models
1/1/2025
Categories of vision-language models
1/1/2025
Core architectural components of vision-language models
1/1/2025
Challenges in vision-language models
1/1/2025
Multimodal GenAI system
1/1/2025
Multimodal vector embedding
1/1/2025
Multimodal vector database
1/1/2025
Collections
1/1/2025
Points and point IDs
1/1/2025
Vectors
1/1/2025
Payload
1/1/2025
Storage and vector store
1/1/2025
Indexing
1/1/2025
Implementation comparisons
1/1/2025
Single collection, partitioned via payload
1/1/2025
Multiple collections with global indexing
1/1/2025
Multimodal generative AI systems vs. VLMs
1/1/2025
Vision-language models
1/1/2025
Multimodal generative AI systems
1/1/2025
Using vision-language models
1/1/2025
Using multimodal generative AI systems
1/1/2025
Real-world example comparison
1/1/2025
Output-based classification of multimodal systems
1/1/2025
Text-to-image systems
1/1/2025
Image-to-text systems
1/1/2025
Text and image systems
1/1/2025
Text-only to specifications and image systems
1/1/2025
Text-to-SQL systems
1/1/2025
Text-to-code systems
1/1/2025
3. Implementing Unimodal Local GenAI System
1/1/2025
GPU in today’s generative AI systems
1/1/2025
Using a local GPU
1/1/2025
Architectural components
1/1/2025
About Ollama
1/1/2025
Alternatives to Ollama
1/1/2025
Generate a PDF document with Ollama
1/1/2025
RAG implementation
1/1/2025
Load and chunk the PDF document
1/1/2025
Alternative chunking strategies in LangChain
1/1/2025
Creating embeddings with metadata
1/1/2025
Using them in code
1/1/2025
Hybrid search with semantic and keyword
1/1/2025
Other retrievers you can use
1/1/2025
Conversation memory buffer
1/1/2025
LLM configuration natural language generation
1/1/2025
ReAct prompt template
1/1/2025
Building the conversational QA chain
1/1/2025
User chat loop
1/1/2025
Challenges in RAG
1/1/2025
4. Implementing Unimodal API-based GenAI Systems
1/1/2025
Getting started with OpenAI APIs and models
1/1/2025
OpenAI as a company
1/1/2025
Overview of the OpenAI API
1/1/2025
Core API endpoints
1/1/2025
Major OpenAI models
1/1/2025
Accessing OpenAI models
1/1/2025
Choosing the right model
1/1/2025
Best practices for beginners
1/1/2025
From OpenAI to agentic AI
1/1/2025
OpenAI’s agentic API ecosystem
1/1/2025
Responses API
1/1/2025
Agents SDK
1/1/2025
Operator
1/1/2025
Codex
1/1/2025
Assistants API
1/1/2025
Multi-document query
1/1/2025
Implementing modular RAG with OpenAI
1/1/2025
Main controller
1/1/2025
Configuration
1/1/2025
Embedding initialization
1/1/2025
Vector store setup
1/1/2025
Metadata tagging
1/1/2025
Document loading and chunking
1/1/2025
Hybrid retriever
1/1/2025
Enforce metadata-based filtering during retrieval
1/1/2025
Language model
1/1/2025
Prompt template
1/1/2025
RAG chain assembly
1/1/2025
Conversational memory
1/1/2025
Dependencies
1/1/2025
To do
1/1/2025
5. Implementing Agentic GenAI Systems with Human-in-the-loop
1/1/2025
Architecting agentic GenAI systems
1/1/2025
Parallel pattern
1/1/2025
Sequential pattern
1/1/2025
Loop pattern
1/1/2025
Router pattern
1/1/2025
Aggregator pattern
1/1/2025
Network pattern
1/1/2025
Hierarchical pattern
1/1/2025
Human-in-the-loop pattern
1/1/2025
Shared tools pattern
1/1/2025
Database with tools pattern
1/1/2025
Memory transformation using tools
1/1/2025
Planner-executor pattern
1/1/2025
Critic or validator pattern
1/1/2025
Negotiator pattern
1/1/2025
Multimodal agent pattern
1/1/2025
Voting or consensus pattern
1/1/2025
Supervisor-subordinate pattern
1/1/2025
Watchdog or recovery pattern
1/1/2025
Temporal planner pattern
1/1/2025
Human-in-the-loop
1/1/2025
End-to-end human-in-the-loop RAG workflow
1/1/2025
From HITL to multi-agent human-in-the-loop RAG
1/1/2025
Agentic AI vs. AI agents
1/1/2025
6. Two and Multi-stage GenAI Systems
1/1/2025
Concepts of interactions in dense retrievals
1/1/2025
No interaction
1/1/2025
Full interaction
1/1/2025
Late interaction
1/1/2025
Multi-vector representations
1/1/2025
Differentiation from late interaction architectures
1/1/2025
Role of interaction models in two-stage RAG systems
1/1/2025
Interaction in the retrieval phase
1/1/2025
Reranking with various interaction models
1/1/2025
Integration into two-stage RAG architectures
1/1/2025
Two-stage RAG architecture
1/1/2025
Stage one dense retrievals
1/1/2025
Stage-two, reranking for semantic precision
1/1/2025
The strategic role of two-stage design
1/1/2025
Two-stage RAG vs. late interaction
1/1/2025
Capabilities of ColBERT and ColPali
1/1/2025
Use of two-stage RAG
1/1/2025
Multi-stage RAG
1/1/2025
Beyond two-stage systems
1/1/2025
Components of multi-stage RAG
1/1/2025
Benefits of multi-stage RAG
1/1/2025
Types of multi-stage RAG
1/1/2025
Grading mechanisms
1/1/2025
Challenges and considerations
1/1/2025
Token utilization in multi-stage RAG systems
1/1/2025
Grading types
1/1/2025
Implementation of multi-stage RAG workflow with routing
1/1/2025
7. Building a Bidirectional Multimodal Retrieval System
1/1/2025
Integration and design implications
1/1/2025
Understanding a multimodal retrieval system
1/1/2025
Technical architecture
1/1/2025
Applications and implications
1/1/2025
Code implementation and explanation
1/1/2025
Requirement
1/1/2025
Frontend
1/1/2025
Data directory
1/1/2025
The retrieval system
1/1/2025
Loaders
1/1/2025
Embedding utils
1/1/2025