Tag: search
Yahoo Scout is... actually good?
Yahoo launched an AI search tool that does something different: inline links that flow with the text like actual hyperlinks. It feels like what search would look like if it was built around AI from the start, but still cared about sending you places.
Plex Collection Creator - Local Semantic Search with Transformers.js
Organizing a large media library into meaningful collections is harder than it sounds. With 1000+ movies, you need something smarter than keyword matching. "Star Wars: A New Hope" and "Star Wars: The Empire Strikes Back" share a franchise, but a text search for "Star Wars" won't catch "Rogue One: A Star Wars Story" if the title varies. Movies about heists aren't all titled "heist." Thematic grouping requires understanding what movies are about, not just what they're called. The solution is sem
fzf ftw
fzf-tools is a zsh plugin that enhances command line efficiency with interactive selection for files, history, scripts, and git commits.
Refactoring Blog Search from Pinecone to Claude
How we replaced vector search with AI-powered semantic search using Claude via AWS Bedrock
Using LLMs as a search engine
A quick perspective on using LLMs as search engines
Could &udm=14 Break?
That popular single-serving site I built to work around Google’s AI snippets could, unfortunately, see an infusion of AI soon. Sorry to be the bearer of bad news.
Implementing Pinecone Vector Search for Blog Content
A detailed guide on how we implemented semantic search using Pinecone vector database and OpenAI embeddings
Let’s Bring Back Small Tools
Thoughts on the misadventure of udm14, or what I hope to gain from successfully reviving the single-serving site for a couple of weeks.
CDK Deployment of Amazon Bedrock Knowledge Base with OpenSearch Serverless
In this demo we will see how to deploy an Amazon Bedrock Knowledge Base with an OpenSearch Vector Index using CDK
Herrington Darkholme - AST Grep, Searching Code with Code
Herrington Darkholme demonstrates AST Grep's powerful code search capabilities using abstract syntax trees instead of traditional regex patterns.
Cache Clearing
Google appears to hide away an important feature from its search engine—an easily accessible cache of search results. (It’s still there, if you know where to look.)
Mastodon’s Next Major Release Enables Full-Text Search
One of the biggest criticisms of Mastodon's technical capabilities involves how limited its search system is. With a new update, everything has changed.
The Technorati Generation
The search engine that kept up at the speed of blogging created a “search war” with Google. But eventually, the speed of blogging just wasn’t fast enough.
Jumping-Off Point
What the heck is a jumpstation, and why did it fade from internet nomenclature? It’s complicated, but the web’s first search engine is in there somewhere.
Extreme Googling
It’s easy to forget given its size, but Google fundamentally changed our relationship with information. Two decades later, we’re still feeling the effects.
Find web references to the page you're looking at
I thought I'd share two small bookmarklets I've been using to find references for a page I'm looking at: * Web references: page * Web references: site To use them, drag each link to your browser toolbar. This will create a couple of buttons that you can click when you want to find more information about whatever page you're looking at; the first checks the full page URL, while the second just searches for the domain name of the site. At the moment both open Google Blog Search and Twitter se
Ubiquity für WordPress (ein Plugin)
Die beste Methode sich mit einer Sache zu beschäftigen ist, einen sinnvollen Anwendungsfall zu schaffen... Bei dem "näher beschäftigen" mit Ubiquity ist ein WordPress-Plugin rausgekommen :) Das WordPress-Plugin erstellt eine Ubiquity-Suche für das eigene Weblog (Quellcode) mit dem Command "search-" Das kann teilweise (wie im Falle meines Blogs: search-notizblog-a-private-weblog-written-by-matthias-pfefferle) ziemlich lang werden, was aber nicht...