Menu

#Embeddings

35 posts

Feed·
20 of 35 posts
Learn Vector Databases for Beginners – Embeddings, Similarity Search & ChromaDB
📰
0Read More

Learn Vector Databases for Beginners – Embeddings, Similarity Search & ChromaDB

freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More ·Beau Carnes·15 days ago
#sV0fUW7O
#freecodecamp#news#vector#embeddings#search

A vector database stores data as lists of numbers called embeddings, which lets it search by meaning instead of matching exact keywords. It's the piece behind a lot of recommendation systems, RAG apps

15s
Embeddings Explained: A Quick Walkthrough with Java
📰
0Read More

Embeddings Explained: A Quick Walkthrough with Java

DEV Community: java·Vishnu B·23 days ago
#NVLSPJCG
#devtojava#devto#dev#vectors#king

If you have used semantic search, a recommendation engine, or any "chat with your documents" feature,...

15s
Building a RAG Pipeline with LLM Embeddings and Scikit-learn - MachineLearningMastery.com
🖼️
0Read More

Building a RAG Pipeline with LLM Embeddings and Scikit-learn - MachineLearningMastery.com

In this article, you will learn how to build a lightweight, end-to-end RAG pipeline using scikit-learn for vector retrieval and open-source models for embeddings and text generation, without the use of paid APIs or heavyweight frameworks.

15s
How to win a beer with high-dimensional statistics
🖼️
81Read More

How to win a beer with high-dimensional statistics

Hacker News·about 2 months ago
#CXU6baEh

My longtime labmate-turned-student/friend1 Dhruva Karkada recently wrote a sick paper on data statistics which deservedly went viral on Twitter, in part beca...

15s
14× faster embeddings: how we rebuilt the ONNX path in Manticore
🖼️
80Read More

14× faster embeddings: how we rebuilt the ONNX path in Manticore

Hacker News·5 months ago
#vtitFQGS

When we shipped Auto Embeddings — the feature that turns any text column into a vector automatically, with no separate model service to run — the most common piece of feedback was about speed.

15s
Pinterest cut AI costs 90% by gutting a frontier model's vision layer
📰
0Read More

Pinterest cut AI costs 90% by gutting a frontier model's vision layer

At 620 million monthly users, calling a frontier model for every image recommendation isn't a strategy — it's a bill. Pinterest CTO Matt Madrigal solved it by gutting Qwen3-VL's vision layer and rebuilding it with proprietary embeddings, cutting costs 90%…

15s
Vector Embeddings Basics: A Technical Introduction for AI
🖼️
0Read More

Vector Embeddings Basics: A Technical Introduction for AI

DEV Community: nlp·FreeDevKit·6 months ago
#A9sJHfud
#dev#embeddings#freedevkit#vector#points

Explore vector embeddings, their function in AI, types like Word2Vec and BERT, applications in semantic search and NLP, and implementation considerations for de

15s
RAG Pipeline Optimization: Production Best Practices
🖼️
0Read More

RAG Pipeline Optimization: Production Best Practices

DEV Community·丁久·6 months ago
#7FelycpA
#rag#ai#machinelearning#llm#retrieval

Optimize Retrieval-Augmented Generation pipelines: chunking strategies, embedding selection, retrieval tuning, and evaluation.

15s
Embedding Dimension Reduction: When 1536 256 Doesn't Hurt Recall
🖼️
0Read More

Embedding Dimension Reduction: When 1536 256 Doesn't Hurt Recall

DEV Community·Gabriel Anhaia·7 months ago
#nwMcu9dz
#when#rag#ai#embeddings#embedding

Cut embeddings 1536 → 256 without breaking recall. Matryoshka native truncation, PCA on legacy models, recall curves, decision rule.

15s