Generative AI with LangChain : build production-ready LLM applications and advanced agents using Python, LangChain, and LangGraph / Ben Auffarth, Leonid Kuligin.

Format:

Book

Author/Creator:

Auffarth, Ben, author.

Kuligin, Leonid, author.

Series:

Expert insight.

Expert insights

Language:

English

Subjects (All):

Application software--Development.

Application software.

Artificial intelligence.

Computer programming.

Application program interfaces (Computer software).

Physical Description:

1 online resource (476 pages) : color illustrations.

Edition:

Second edition.

Place of Publication:

Birmingham : Packt Publishing, 2025.

Summary:

Go beyond foundational LangChain documentation with detailed coverage of LangGraph interfaces, design patterns for building AI agents, and scalable architectures used in production--ideal for Python developers building GenAI applications Key Features Bridge the gap between prototype and production with robust LangGraph agent architectures Apply enterprise-grade practices for testing, observability, and monitoring Build specialized agents for software development and data analysis Purchase of the print or Kindle book includes a free PDF eBook Book Description This second edition tackles the biggest challenge facing companies in AI today: moving from prototypes to production. Fully updated to reflect the latest developments in the LangChain ecosystem, it captures how modern AI systems are developed, deployed, and scaled in enterprise environments. This edition places a strong focus on multi-agent architectures, robust LangGraph workflows, and advanced retrieval-augmented generation (RAG) pipelines. You'll explore design patterns for building agentic systems, with practical implementations of multi-agent setups for complex tasks. The book guides you through reasoning techniques such as Tree-of -Thoughts, structured generation, and agent handoffs--complete with error handling examples. Expanded chapters on testing, evaluation, and deployment address the demands of modern LLM applications, showing you how to design secure, compliant AI systems with built-in safeguards and responsible development principles. This edition also expands RAG coverage with guidance on hybrid search, re-ranking, and fact-checking pipelines to enhance output accuracy. Whether you're extending existing workflows or architecting multi-agent systems from scratch, this book provides the technical depth and practical instruction needed to design LLM applications ready for success in production environments. What you will learn Design and implement multi-agent systems using LangGraph Implement testing strategies that identify issues before deployment Deploy observability and monitoring solutions for production environments Build agentic RAG systems with re-ranking capabilities Architect scalable, production-ready AI agents using LangGraph and MCP Work with the latest LLMs and providers like Google Gemini, Anthropic, Mistral, DeepSeek, and OpenAI's o3-mini Design secure, compliant AI systems aligned with modern ethical practices Who this book is for This book is for developers, researchers, and anyone looking to learn more about LangChain and LangGraph. With a strong emphasis on enterprise deployment patterns, it's especially valuable for teams implementing LLM solutions at scale. While the first edition focused on individual developers, this updated edition expands its reach to support engineering teams and decision-makers working on enterprise-scale LLM strategies. A basic understanding of Python is required, and familiarity with machine learning will help you get the most out of this book.

Contents:

Cover

Title Page

Copyright Page

Contributors

Table of Contents

Preface

Chapter 1: The Rise of Generative AI: From Language Models to Agents

The modern LLM landscape

Model comparison

LLM provider landscape

Licensing

From models to agentic applications

Limitations of traditional LLMs

Understanding LLM applications

Understanding AI agents

Introducing LangChain

Challenges with raw LLMs

How LangChain enables agent development

Exploring the LangChain architecture

Ecosystem

Modular design and dependency management

LangGraph, LangSmith, and companion tools

Third-party applications and visual tools

Summary

Questions

Chapter 2: First Steps with LangChain

Setting up dependencies for this book

API key setup

Exploring LangChain's building blocks

Model interfaces

LLM interaction patterns

Development testing

Working with chat models

Reasoning models

Controlling model behavior

Choosing parameters for applications

Prompts and templates

Chat prompt templates

LangChain Expression Language (LCEL)

Simple workflows with LCEL

Complex chain example

Running local models

Getting started with Ollama

Working with Hugging Face models locally

Tips for local models

Multimodal AI applications

Text-to-image

Using DALL-E through OpenAI

Using Stable Diffusion

Image understanding

Using Gemini 1.5 Pro

Using GPT-4 Vision

Review questions

Chapter 3: Building Workflows with LangGraph

LangGraph fundamentals

State management

Reducers

Making graphs configurable

Controlled output generation

Output parsing

Error handling

Prompt engineering

Prompt templates

Zero-shot vs. few-shot prompting

Chaining prompts together

Dynamic few-shot prompting

Chain of Thought

Self-consistency.

Working with short context windows

Summarizing long video

Understanding memory mechanisms

Trimming chat history

Saving history to a database

LangGraph checkpoints

Chapter 4: Building Intelligent RAG Systems

From indexes to intelligent retrieval

Components of a RAG system

When to implement RAG

From embeddings to search

Embeddings

Vector stores

Vector stores comparison

Hardware considerations for vector stores

Vector store interface in LangChain

Vector indexing strategies

Breaking down the RAG pipeline

Document processing

Chunking strategies

Retrieval

Advanced RAG techniques

Hybrid retrieval: Combining semantic and keyword search

Re-ranking

Query transformation: Improving retrieval through better queries

Context processing: maximizing retrieved information value

Response enhancement: Improving generator output

Corrective RAG

Agentic RAG

Choosing the right techniques

Developing a corporate documentation chatbot

Document loading

Language model setup

Document retrieval

Designing the state graph

Integrating with Streamlit for a user interface

Evaluation and performance considerations

Troubleshooting RAG systems

Chapter 5: Building Intelligent Agents

What is a tool?

Tools in LangChain

ReACT

Defining tools

Built-in LangChain tools

Custom tools

Wrapping a Python function as a tool

Creating a tool from a Runnable

Subclass StructuredTool or BaseTool

Advanced tool-calling capabilities

Incorporating tools into workflows

Controlled generation

Controlled generation provided by the vendor

ToolNode

Tool-calling paradigm

What are agents?

Plan-and-solve agent

Chapter 6: Advanced Applications and Multi-Agent Systems.

Agentic architectures

Multi-agent architectures

Agent roles and specialization

Consensus mechanism

Communication protocols

Semantic router

Organizing interactions

LangGraph streaming

Handoffs

Communication via a shared messages list

LangGraph platform

Building adaptive systems

Dynamic behavior adjustment

Human-in-the-loop

Exploring reasoning paths

Tree of Thoughts

Trimming ToT with MCTS

Agent memory

Cache

Store

Chapter 7: Software Development and Data Analysis Agents

LLMs in software development

The future of development

Implementation considerations

Evolution of code LLMs

Benchmarks for code LLMs

LLM-based software engineering approaches

Security and risk mitigation

Validation framework for LLM-generated code

LangChain integrations

Writing code with LLMs

Google generative AI

Hugging Face

Anthropic

Agentic approach

Documentation RAG

Repository RAG

Applying LLM agents for data science

Training an ML model

Setting up a Python-capable agent

Asking the agent to build a neural network

Agent execution and results

Analyzing a dataset

Creating a pandas DataFrame agent

Asking questions about the dataset

Chapter 8: Evaluation and Testing

Why evaluation matters

Safety and alignment

Performance and efficiency

User and stakeholder value

Building consensus for LLM evaluation

What we evaluate: core agent capabilities

Task performance evaluation

Tool usage evaluation

RAG evaluation

Planning and reasoning evaluation

How we evaluate: methodologies and approaches

Automated evaluation approaches

Human-in-the-loop evaluation

System-level evaluation

Evaluating LLM agents in practice

Evaluating the correctness of results.

Evaluating tone and conciseness

Evaluating the output format

Evaluating agent trajectory

Evaluating CoT reasoning

Offline evaluation

Evaluating RAG systems

Evaluating a benchmark in LangSmith

Evaluating a benchmark with HF datasets and Evaluate

Evaluating email extraction

Chapter 9: Production-Ready LLM Deployment and Observability

Security considerations for LLM applications

Deploying LLM apps

Web framework deployment with FastAPI

Scalable deployment with Ray Serve

Building the index

Serving the index

Running the application

Deployment considerations for LangChain applications

Local development with the LangGraph CLI

Serverless deployment options

UI frameworks

Model Context Protocol

Infrastructure considerations

How to choose your deployment model

Model serving infrastructure

How to observe LLM apps

Operational metrics for LLM applications

Tracking responses

Hallucination detection

Bias detection and monitoring

LangSmith

Observability strategy

Continuous improvement for LLM applications

Cost management for LangChain applications

Model selection strategies in LangChain

Tiered model selection

Cascading model approach

Output token optimization

Other strategies

Monitoring and cost analysis

Chapter 10: The Future of Generative Models: Beyond Scaling

The current state of generative AI

The limitations of scaling and emerging alternatives

The scaling hypothesis challenged

Big tech vs. small enterprises

Emerging alternatives to pure scaling

Scaling up (traditional approach)

Scaling down (efficiency innovations)

Scaling out (distributed approaches)

Evolution of training data quality

Democratization through technical advances.

New scaling laws for post-training phases

Economic and industry transformation

Industry-specific transformations and competitive dynamics

Job evolution and skills implications

Near-term impacts (2025-2035)

Medium-term impacts (2035-2045)

Long-term shifts (2045 and beyond)

Economic distribution and equity considerations

Societal implications

Misinformation and cybersecurity

Copyright and attribution challenges

Regulations and implementation challenges

Appendix

OpenAI

Google

1. Google AI platform

2. Google Cloud Vertex AI

Other providers

Summarizing long videos

Packt Page

Other Books You May Enjoy

Index.

Notes:

Includes index.

OCLC-licensed vendor bibliographic record.

ISBN:

1-83702-200-3

OCLC:

1521194298