Skip to main content

Print Edition Cover Revealed: Generative AI with Local LLM

 Disclaimer: this post is not a usual technical article. If you are not interested, you can skip it. I just want to share a few recent moments with my readers.


After several months of work, the print edition of my book Generative AI with Local LLM has reached a new milestone — the cover design for the print version is now complete.

This edition is a translated version of the original book and is planned for publication through BomBora Publisher in Eastern Europe. The publisher has adapted the content specifically for non-technical readers, making the material more accessible while keeping its practical focus. The translation and adaptation process took about eight months and included multiple rounds of review, proofreading, and refinement to ensure clarity and quality.

The book is designed to help readers understand and apply generative AI through practical and accessible methods. It emphasizes clarity, simplicity, and real-world application.

Key Features of the Book:

  • Clear and Concise Explanations: Complex AI concepts are broken down into simple, step-by-step guidance, making them accessible to readers of all backgrounds.

  • Hands-On Projects: Each chapter includes guided projects, from environment setup to model deployment.

  • Real-World Applications: The examples focus on solving real problems, providing practical experience in applying AI methods.

  • Essential Tools and Libraries: The book introduces and uses tools such as Langchain, Vanna, TensorFlow, and PyTorch.

  • Project-Based Learning: Readers work through projects that range from image recognition to advanced large language model fine-tuning.

The book aims to serve as a concise and practical starting point for anyone interested in generative AI and local LLM development.

More details about the original edition are available at https://leanpub.com/quickstartwithai

Labels:

Comments

Post a Comment

Popular posts from this blog

Apache Ignite deep dive, SQL engine

Apache Ignite  is an open source memory-centric distributed database, caching and comput- ing platform. From the beginning, it was designed as an in-memory data grid for developing a high-performance software system. So, it’s core architecture design is slightly different from the traditional NoSQL databases, which can simplify building modern applications with a flexible data model and simpler high availability, high scalability.     Moreover, to understand how to design application with any databases or framework properly, you must understand the architecture of the database or framework itself. By getting a better idea of the system, you can solve different problems in your enterprise architecture landscape, can select a comprehensive database or framework that is appropriate for your application and get the maximum benefits from the system. In this article we are going to explore the Apache Ignite SQL engine.      Under the hood...
Post a Comment
Read more

Book review: High Performance in-memory computing with Apache Ignite by Sadruddin Md

A new title  The Apache Ignite book  has been released including Ignite 2.6 and above. Read the full book review by Sadruddin Md .
Post a Comment
Read more

Quick start with In memory Data Grid, Apache Ignite

UP1: For complete quick start guide, see also the sample chapter of the book "High performance in-memory computing with Apache Ignite" here . Even you can find the sample examples from the GitHub repository . IMDG or In memory data grid is not an in-memory relational database, an NoSQL database or a relational database. It is a different breed of software datastore. The data model is distributed across many servers in a single location or across multiple locations. This distribution is known as a data fabric. This distributed model is known as a ‘shared nothing’ architecture. IMDG has following characteristics: All servers can be active in each site. All data is stored in the RAM of the servers. Servers can be added or removed non-disruptively, to increase the amount of RAM available. The data model is non-relational and is object-based.  Distributed applications written on the platform independent language. The data fabric is resilient, allowing non-disruptive au...
Post a Comment
Read more