Tag

#embedding

74 posts2 followers

Explore Hashnode

Alternatives

I cut EmbeddingGemma 2's vectors to a sixth of their size. It got more answers right, and that was the worrying part.

What EmbeddingGemma 2 is, what Google says it can do, and a MacBook Air test of search by meaning, pictures, shorter vectors and speed.

17 min readsystemdesignacademy.hashnode.dev

Aman JainJul 20

Does a Wider Embedding Space Help More on Diverse Data?

Exploring model width, topic diversity, and next-token prediction with a small GPT model

7 min readcurious-pm.hashnode.dev

Nguyễn Hữu ĐứcJul 11

Building an LLM System from Scratch in Pure Python & NumPy: Architecture, Invariants, and Clean Code, Open-Source 100% Inference Engine and Thinking engine!

Exploring the design invariants, ternary quantization, and self-healing cognitive pipeline of Draco AI, a hardware-agnostic LLM built from scratch.

3 min readdraco-ai.hashnode.dev

Ashaaf KhanJul 10

Behind the Illusion of Perfection: Why Your RAG Pipeline Fails in Production

An Architectural Deep Dive into Retrieval-Augmented Generation Limitations, Breakdowns, and Real-World Failure Modes

10 min readashaaf.hashnode.dev

Tanisha SoniJul 3

Your LLM Doesn't Need to Know About All 47 Tools

From 40 tools to 6, without touching a single LLM call

7 min readtanisha-soni.hashnode.dev

Raghavan T MJun 16

You're Not Writing Prompts. You're Giving the AI Coordinates.

Models encode text and images as high‑dim vectors; cosine similarity finds nearest neighbours; RAG retrieves relevant context for precise LLM answers.

5 min readchangeofbasis.hashnode.dev

Devathi Sai LokeshJun 4

RAG is Not Just Chunking + Embedding + Retrieval — Here's What Production Actually Looks Like

A complete breakdown of enterprise-grade RAG pipeline with packages, architecture, and real engineering decisions

6 min readsailokeshdevathi.hashnode.dev

eyanpenMay 4

Why Does Semantic Chunking Need an Embedding API?

Fixed-length chunking requires no external services, yet semantic chunking absolutely needs an Embedding API — why? The Short Answer The core idea of semantic chunking is to split text at semantic boundaries. Determining whether "two pieces of text ...

11 min readai-is-coming.hashnode.dev

James GainesApr 28

Why Vector Search Alone Fails on Regulatory Documents

(and How Hybrid Search Fixes It)

10 min readblog.gainesai.com

Aashish ChapainApr 22

Embeddings in RAG: The Core of Semantic Search

Retrieval-Augmented Generation (RAG) systems rely on the core idea of converting text into vectors so we can search by meaning instead of keywords. These vectors are called embeddings, and they are th

6 min readblog.chapainaashish.com.np

Search Hashnode