Category Archives: Generative AI

Retrieval Augmented Generation (RAG) & LLM: Examples

Retrieval augmented Generation RAG pattern for LLMs

Last updated: 26th Jan, 2024 Have you ever wondered how to seamlessly integrate the vast knowledge of Large Language Models (LLMs) with the specificity of domain-specific knowledge stored in file storage, image storage, vector databases, etc? As the world of machine learning continues to evolve, the need for more sophisticated and contextually relevant responses from LLMs becomes paramount. Lack of contextual knowledge can result in LLM hallucination thereby producing inaccurate, unsafe, and factually incorrect responses. This is where context augmentation with prompts, and, hence retrieval augmentated generation method, comes into the picture. For data scientists and product managers keen on deploying LLMs in production, the Retrieval Augmented Generation pattern offers …

Continue reading

Posted in Generative AI, Machine Learning, NLP. Tagged with , , .

Large Language Models (LLMs): Types, Examples

Large language models - LLM - building blocks

Last updated: 31st Jan, 2024 Large language models (LLMs), being the key pillar of generative AI, have been gaining traction in the world of natural language processing (NLP) due to their ability to process massive amounts of text and generate accurate results related to predicting the next word in a sentence, given all the previous words. These different LLM models are trained on a large or broad corpus of text datasets, which contain hundreds of millions to billions of words. LLMs, as they are known, rely on complex algorithms including transformer architectures that shift through large datasets and recognize patterns at the word level. This data helps the LLMs better understand …

Continue reading

Posted in Data Science, Deep Learning, Generative AI, Large Language Models, Machine Learning, NLP. Tagged with , .

LLM Optimization for Inference – Techniques, Examples

LLM Inference Optimization Techniques Examples

One of the common challenges faced with the deployment of large language models (LLMs) while achieving low-latency completions (inferences) is the size of the LLMs. The size of LLM throws challenges in terms of compute, storage, and memory requirements. And, the solution to this is to optimize the LLM deployment by taking advantage of model compression techniques that aim to reduce the size of the model. In this blog, we will look into three different optimization techniques namely pruning, quantization, and distillation along with their examples. These techniques help model load quickly while enabling reduced latency during LLM inference. They reduce the resource requirements for the compute, storage, and memory. …

Continue reading

Posted in Generative AI, Large Language Models, Machine Learning, NLP, Python. Tagged with , , , .

Transfer Learning vs Fine Tuning LLMs: Differences

differences between transfer learning and fine tuning

Last updated: 23rd Jan, 2024 Two NLP concepts that are fundamental to large language models (LLMs) are transfer learning and fine-tuning pre-trained LLMs. Rather, true fine-tuning can also be termed as full fine-tuning because transfer learning is also a form of fine-tuning. Despite their interconnected nature, they are distinct methodologies that serve unique purposes when training foundation LLMs to achieve different objectives. In this blog, we will explore the differences between transfer Learning and full fine-tuning, learning about their characteristics and how they come into play in real-world scenarios related to natural language understanding (NLU) and natural language generation (NLG) tasks with the help of examples. We will also learn …

Continue reading

Posted in Deep Learning, Generative AI, Machine Learning, NLP. Tagged with , , , .

AI-assisted Software Development: Tools & Processes

AI assisted software development

In the rapidly evolving landscape of software development, the integration of artificial intelligence (AI) and generative AI (Gen AI) is not just a luxury but a cornerstone for enhancing software development velocity. This blog delves into the key aspects of Gen AI and AI-assisted software development, presenting actionable takeaways for software leaders, including engineering managers, project managers, product managers, and software engineers. We will look into different tools and related processes that can be enhanced across the entire software development lifecycle. Design & Architect: Crafting the Blueprint Integrate the following tools to speed up the design process while ensuring adherence to best practices, significantly reducing design iteration times. Code & …

Continue reading

Posted in AI, Generative AI, Software Engg, Software Quality. Tagged with , .

Transformer Architecture in Deep Learning: Examples

Transformer Architecture

The Transformer model architecture, introduced by Vaswani et al. in 2017, is a deep learning model that has revolutionized the field of natural language processing (NLP) giving rise to large language models (LLMs) such as BERT, GPT, T5, etc.  In this blog, we will learn about the details of transformer model architecture with the help of examples and references from the mother paper – Attention is All You Need.  Transformer Block – Core Building Block of Transformer Model Architecture Before getting to understand the details of transformer model architecture, let’s understand the key building block termed transformer block. The core building block of the Transformer architecture consists of multi-head attention …

Continue reading

Posted in Deep Learning, Generative AI, NLP. Tagged with , , .

LLM Training & GPU Memory Requirements: Examples

LLM GPU Memory Requirements

As data scientists and MLOps Engineers, you must have come across the challenges related to managing GPU requirements for training and deploying large language models (LLMs). In this blog, we will delve deep into the intricacies of GPU memory demands when dealing with LLMs. We’ll learn with the help of various examples to better understand how GPU memory impacts the performance and feasibility of training these LLMs. Whether you’re planning to train a foundation (pre-trained) model or fine-tuning an existing model, the insights are aimed to guide you through the crucial considerations of GPU memory allocation. Greater details can be found in this book: Generative AI on AWS. Understanding GPU …

Continue reading

Posted in Generative AI, Large Language Models, NLP. Tagged with , .

Transformer Architecture Types: Explained with Examples

encoder decoder architecture

Are you fascinated by the power of deep learning large language models that can generate creative writing, answer complex questions, etc? Ever wondered how these LLMs understand and process human language with such finesse? At the heart of these remarkable achievements lies a machine learning model architecture that has revolutionized the field of Natural Language Processing (NLP) – the Transformer architecture and its types. But what makes Transformer models so special? From encoding sentences into numerical embeddings to employing attention mechanisms that capture the relationships between words, we will dissect different types of Transformer architectures, provide real-world examples, and even dive into the mathematics that governs its operation. Let’s explore …

Continue reading

Posted in Deep Learning, Generative AI, Machine Learning. Tagged with , , .

Blueprint: Deploying Generative AI Applications

Generative AI Applications Architecture

In this blog, we will learn about a comprehensive framework for the deployment of generative AI applications, breaking down the essential components that architects must consider. Learn more about this topic from this book: Generative AI on AWS. The following is a solution / technology architecture that represents a blueprint for deploying generative AI applications. The following is an explanation of the different components of this architectural viewpoint:

Posted in Generative AI, Machine Learning. Tagged with , .

BERT vs GPT Models: Differences, Examples

BERT base BERT Large neural network architectures

Have you been wondering what sets apart two of the most prominent transformer-based machine learning models in the field of NLP, Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformers (GPT)? While BERT leverages encoder-only transformer architecture, GPT models are based on decoder-only transformer architecture. In this blog, we will delve into the core architecture, training objectives, real-world applications, examples, and more. By exploring these aspects, we’ll learn about the unique strengths and use cases of both BERT and GPT models, providing you with insights that can guide your next LLM-based NLP project or research endeavor. Differences between BERT vs GPT Models BERT, introduced in 2018, marked a significant …

Continue reading

Posted in Deep Learning, Generative AI, Machine Learning. Tagged with , , .

Demystifying Encoder Decoder Architecture & Neural Network

encoder decoder architecture

In the field of AI / machine learning, the encoder-decoder architecture is a widely-used framework for developing neural networks that can perform natural language processing (NLP) tasks such as language translation, text summarization, and question-answering systems, etc which require sequence-to-sequence modeling. This architecture involves a two-stage process where the input data is first encoded (using what is called an encoder) into a fixed-length numerical representation, which is then decoded (using a decoder) to produce an output that matches the desired format. In this blog, we will explore the inner workings of the encoder-decoder architecture, how it can be used to solve real-world problems, and some of the latest developments in …

Continue reading

Posted in Deep Learning, Generative AI, Machine Learning, NLP. Tagged with , , , .

Large Language Models (LLMs) & Semantic Search: Examples

Large Language Models and Semantic Search

Have you ever marveled at how typing a few words into a search engine yields exactly the information you’re looking for from the vast expanse of the web? This is largely thanks to the advancements in semantic search, bolstered by technologies like Large Language Models (LLMs). Semantic search, which focuses on understanding the intent and contextual meaning behind queries, benefits from LLMs to provide more accurate and relevant results. However, it’s important to note that traditional search engines also rely on a sophisticated mix of algorithms, indexing, and ranking systems. LLMs complement these systems by enhancing their ability to interpret complex queries, making your search experience more intuitive and effective. …

Continue reading

Posted in Deep Learning, Generative AI, Large Language Models, Machine Learning. Tagged with , , , .

Procurement Analytics Use Cases Examples

procurement analytics use cases

Last updated: 26th Nov, 2023 The procurement analytics applications is seeing tremendous growth in last few years. With so much data available, advancement in data analytics and related technology field, and the need for digital transformation across procurement organizations, it’s important to know how procurement analytics can help you make better business decisions. This blog will cover procurement analytics and key use cases examples from advanced analytics field such as machine learning, AI, generative AI that will be useful for business stakeholders such as category managers, sourcing managers, supplier relationship managers, business analysts/product managers, and data scientists to implement different use cases using machine learning. The use cases around data-driven decision …

Continue reading

Posted in Data Science, Generative AI, Machine Learning, Procurement. Tagged with , , , .

First Principles Thinking using ChatGPT

ChatGPT Prompt for First Principles Thinking

Have you ever wondered why an object such as a chair is shaped the way it is, or why it’s even needed in the first place? What mystery unravels when we dig into the very essence of everyday objects and concepts around us? Navigating through a universe having well-established beliefs and customary wisdom, the hunt for innovative answers and deciphering the secrets hidden behind the everyday becomes not just a curiosity, but a necessity. This is where first principles thinking comes to the rescue. I have posted a detailed blog on First principles thinking – First principles thinking: Concepts & Examples. In this blog, let’s explore how we can utilize …

Continue reading

Posted in Analytics, ChatGPT, Generative AI, OpenAI. Tagged with , , .

Generative AI Framework for Product Managers: Examples

Ever wondered how you as a product manager can stay ahead in the competitive era fuelled by technological advancements such as generative AI? Are you constantly grappling with the pressure to deliver groundbreaking solutions in line with your business goals? As a product manager, wouldn’t it be revolutionary to have some kind of a playbook that simplifies these challenges? What exactly can generative AI do for modern product managers? Which areas of your daily struggles can it alleviate, and what AI frameworks are best suited for your unique challenges? In this blog, we will dive into the potential of Generative AI vis-a-vis real-life use cases for product managers. Use Cases: …

Continue reading

Posted in Generative AI, Product Management. Tagged with , .

OpenAI Python API Example for NLP Tasks

OpenAI Python API Example

Ever wondered how you can leverage the power of OpenAI’s GPT-3 and GPT-3.5 (from Jan 2024 onwards) directly in your Python application? Are you curious about generating human-like text with just a few lines of code? This blog post will walk you through an example Python code snippet that utilizes OpenAI’s Python API for different NLP tasks such as text generation. Check out my other post on how to use Langchain framework for text generation using OpenAI GPT models. OpenAI Python APIs The OpenAI Python API is an interface that allows you to interact with OpenAI’s language models, including their GPT-3 model. The following are different popular models that you …

Continue reading

Posted in Generative AI, Machine Learning, NLP, OpenAI, Python. Tagged with , , , .