---
title: "karthik hubli (@karthikhubli) | Hashnode"
description: "Everything bits and bytes. Read the latest articles by karthik hubli on Hashnode."
url: "https://hashnode.com/@karthikhubli"
---

@karthikhubli

# karthik hubli

@karthikhubli · Joined November 2024

Everything bits and bytes

### [From Words to Vectors: Understanding the Magic of Text Embedding](https://customer-identity-access-management.hashnode.dev/from-words-to-vectors-understanding-the-magic-of-text-embedding?utm_source=hashnode&utm_medium=feed)

Transformers are the backbone of large language models (LLMs) and have revolutionized natural language processing by enabling models to handle vast amounts of text efficiently. Unlike traditional neural networks, transformers use a self-attention mec...

7 min read · [customer-identity-access-management.hashnode.dev](https://customer-identity-access-management.hashnode.dev/from-words-to-vectors-understanding-the-magic-of-text-embedding?utm_source=hashnode&utm_medium=feed)

[Mar 4, 2025](https://hashnode.com/posts/from-words-to-vectors-understanding-the-magic-of-text-embedding/67c66996b8a1678b9e67e6b8)

### [RAG: Putting the pieces together (Part - 3)](https://rag-101.hashnode.dev/rag-putting-the-pieces-together-part-3?utm_source=hashnode&utm_medium=feed)

RAG has significant advantage over traditional generative models that rely solely on pre-trained data. RAG systems incorporate a retrieval mechanism that dynamically fetches relevant information to improve the accuracy and reliability of responses. E...

4 min read · [rag-101.hashnode.dev](https://rag-101.hashnode.dev/rag-putting-the-pieces-together-part-3?utm_source=hashnode&utm_medium=feed)

[Mar 4, 2025](https://hashnode.com/posts/rag-putting-the-pieces-together-part-3/67c66950a494cd5641cefe90)

### [RAG: Building blocks (Part - 1)](https://rag-101.hashnode.dev/rag-building-blocks-part-2?utm_source=hashnode&utm_medium=feed)

Introduction LLM/Inference LLMs are the "brain" of RAG systems, responsible for interpreting input queries, retrieving relevant knowledge, and generating coherent, context-aware responses. Key roles of LLM in a RA system involve Natural Language Unde...

3 min read · [rag-101.hashnode.dev](https://rag-101.hashnode.dev/rag-building-blocks-part-2?utm_source=hashnode&utm_medium=feed)

[Jan 20, 2025](https://hashnode.com/posts/rag-building-blocks-part-2/678e847d7834cdabd0b1d9e7)

### [RAG: The big picture (Part - 2)](https://rag-101.hashnode.dev/rag-the-big-picture-part-2?utm_source=hashnode&utm_medium=feed)

To understand RAG, we must take a few steps back and start with understanding what is AI. There are many definitions for what constitutes an AI. The one broadly accepted is that any system which matches or exceeds average human capability in a comple...

3 min read · [rag-101.hashnode.dev](https://rag-101.hashnode.dev/rag-the-big-picture-part-2?utm_source=hashnode&utm_medium=feed)

[Jan 20, 2025](https://hashnode.com/posts/rag-the-big-picture-part-2/678e7608d8ae4f24dec7acb6)

### [From Words to Vectors: Understanding the Magic of Text Embedding](https://text-embedding.hashnode.dev/from-words-to-vectors-understanding-the-magic-of-text-embedding?utm_source=hashnode&utm_medium=feed)

Transformers are the backbone of large language models (LLMs) and have revolutionized natural language processing by enabling models to handle vast amounts of text efficiently. Unlike traditional neural networks, transformers use a self-attention mec...

7 min read · [text-embedding.hashnode.dev](https://text-embedding.hashnode.dev/from-words-to-vectors-understanding-the-magic-of-text-embedding?utm_source=hashnode&utm_medium=feed)

[Nov 21, 2024](https://hashnode.com/posts/from-words-to-vectors-understanding-the-magic-of-text-embedding/673e808db28d32ce43326a50)
