Fine Tuning LLMs - A quick deep dive

Fine-tuning large language models (LLMs) has become a crucial skill in the field of artificial intelligence, especially with the rise of applications in generative AI. In this guide, we will explore the intricacies of fine-tuning LLM models, focusing on techniques such as QLoRA and LoRA, as well as quantization methods using models like LLama2 and Google Gemma. This extensive tutorial will take you through both theoretical concepts and practical implement... Read more

Advanced prompting techniques

Welcome to an exciting journey into the world of advanced ChatGPT prompting techniques! In this blog, we'll explore how to craft effective prompts that unleash the full potential of large language models, from freeform prompts to structured ones, and discover the science behind prompt engineering. Get ready to elevate your prompting skills to new heights!

Understanding Probability in Prompting

When engaging with large language models, it's essential to grasp t... Read more

Best practices for effective prompting

In this comprehensive guide, we will delve into the fascinating world of prompt engineering, a crucial skill for optimising interactions with AI models like ChatGPT. 

Introduction to Prompt Engineering

Prompt engineering is a rapidly evolving field that sits at the intersection of technology and linguistics. As artificial intelligence (AI) becomes more integrated into our daily lives, the art of crafting precise prompts has emerged as a vital ski... Read more

Amazon SageMaker vs Amazon BedRock

In the ever-evolving world of machine learning, choosing the right service can significantly impact your project's success. In this blog, we’ll delve into the key differences between Amazon SageMaker and Amazon Bedrock, helping you understand their purposes, costs, and ideal use cases to make an informed decision for your AI and ML projects.

Introduction to SageMaker and Bedrock

Amazon SageMaker and Amazon Bedrock are two powerful services provided by AWS... Read more

Building Gen AI applications on AWS Bedrock

Let's start building generative AI applications on AWS platform Bedrock. In this guide, we'll explore the features, pricing, and practical implementation of various foundation models, allowing you to harness the power of generative AI in your projects.

What is AWS Bedrock?

AWS Bedrock is a fully managed service that simplifies the process of building and scaling generative AI applications. It provides access to a wide range of foundation models (... Read more

What the hell is DeepSeek-R1?

In just 30 minutes, you'll discover everything you need to know about DeepSeek-R1, the revolutionary AI model that's shaking up the tech world. From its unique reinforcement learning approach to its remarkable capabilities compared to ChatGPT, this guide will equip you with the knowledge to leverage DeepSeek-R1 for your own projects.

Introduction

DeepSeek-R1 is transforming the landscape of artificial intelligence with its innovative approach to reasoning. Lau... Read more

Let's build an AI Agent with LangGraph

In this blog, we delve into the exciting world of multi-agent workflows using LangGraph, a powerful library designed for constructing dynamic agent-like workflows as graphs. We will explore three distinct examples of these workflows, demonstrating how agents can collaborate, operate independently, or function within hierarchical teams.

Introduction to LangGraph

LangGraph is a transformative library that facilitates the creation of dynamic workflows re... Read more

Will AI Agents eat SaaS?

The rise of AI agents has sparked an intense debate in the tech world about the future of traditional SaaS (Software-as-a-Service) businesses. While some tech leaders, like Microsoft's Satya Nadella, suggest that AI agents could potentially collapse SaaS values by taking over business logic, others remain skeptical of this dramatic shift.

The truth likely lies somewhere in between. Rather than completely "eating" SaaS, AI agents are more likely to transform how SaaS... Read more

Choosing the Right Agentic AI Framework

Are you overwhelmed by the plethora of agentic AI frameworks available today? Fear not! In this blog, I’ll break down the three most popular frameworks—LangGraph, CrewAI, and AutoGen—highlighting their unique features, strengths, and ideal use cases to help you make an informed choice.

Introduction to Agentic AI Frameworks

Agentic AI frameworks have gained significant traction in recent times, providing developers with powerful tools to create intell... Read more

GraphRAG -> Knowledge Graph + RAG (a match made in heaven)

In this blog, we explore the groundbreaking Graph Retrieval-Augmented Generation (GraphRAG) from Microsoft. This advanced system not only enhances the responses of AI but also provides vital context, making it a game-changer in the world of AI applications. Join me as we delve into its features, setup, and implementation steps to elevate your AI projects.

Introduction to Graph RAG

Graph Retrieval-Augmented Generation (Graph RAG) re... Read more

Mastering Advanced Chunking Strategies in RAG

Welcome to an exciting exploration of chunking strategies within RAG applications, where we will delve into techniques that optimise data processing for AI. From the basics to advanced methods, this guide will equip you with the knowledge to enhance AI responses through effective chunking.

Table of Contents

Introduction to Chunking Strategies in RAG Exploring Document Text Splitting Techniques Introduction to Semantic Chunking with Embeddings A... Read more

RAG But Better: Reranking with Cohere AI

Retrieval-Augmented Generation (RAG) has become a buzzword in the world of AI, promising a lot but often leaving users puzzled when the results don't match expectations. While it's straightforward to kickstart a RAG pipeline, the complexity lies in fine-tuning it for optimal performance. In this blog, we’ll explore the role of rerankers in enhancing RAG pipelines and how they can significantly improve retrieval accuracy.

Understanding RAG and Reranke... Read more