Pinterest engineering blog

  • Back to all posts
  • Dec 9, 2016
  • Share

Search serving and ranking at Pinterest

Pinterest Search team

Pinterest Search handles billions of queries every month. Every day, we help millions of Pinners discover useful ideas by delivering results among billions of Pins saved by people with overlapping tastes. In the early days, we built our first search system on top of Solr and Lucene. Over past few years, we’ve evolved our search stack by adding new layers, designing services and experimenting with ranking functions.

Tags: 

Pinterest engineering blog

  • Back to all posts
  • Sep 1, 2016
  • Share

Handling large data sets at scale

Timothy Koh

Timothy Koh is an infrastructure engineer on the Search team

Millions of people search for ideas on Pinterest every day. Since launching search guides two years ago, we’re now handling two billion search queries every month. A core component of our search stack is our query rewrite service which we use to understand the query and rewrite it as needed. We do many key-value pair lookups in this service, so it’s essential that we pick the right data structures. 

Tags: 

Pinterest engineering blog

  • Back to all posts
  • Jun 28, 2016
  • Share

Introducing automatic object detection to visual search

Dmitry Kislyuk

Dmitry Kislyuk, software engineer, Visual Search team

When we launched visual search last year, we gave a first look at what’s possible when you use images as search queries. Now, more than 130 million visual searches are done every month, as people search for the objects, styles and colors they see in Pins and get related recommendations. It’s a whole new kind of search, and a technological challenge. 

Pinterest engineering blog

  • Back to all posts
  • Mar 25, 2016
  • Share

Improving search relevance and engagement with text attributes

Matthew Fong

Matthew Fong is a software engineer on the Discovery team

Nearly two years ago, we launched Guided Search, a way to search for questions with more than one right answer, and have been making improvements ever since. Pinterest Search was built on top of Lucene, utilizing basic functionalities, such as normal text fields and payload fields, without many major customizations.

Tags: 

Pinterest engineering blog

  • Back to all posts
  • Feb 25, 2016
  • Share

Automating human evaluation at Pinterest

Maesen Churchill

Maesen Churchill is a software engineer on the Search team

Computers are so smart these days. Machine learning accomplishes some pretty amazing feats at Pinterest, from making sophisticated recommendations to building higher-quality home feeds. There are some things humans tend to do better, such as evaluating content, but having Pinployees (Pinterest employees) regulate content on Pinterest is simply not scalable.

Tags: 

Pinterest engineering blog

  • Back to all posts
  • Nov 8, 2015
  • Share

Introducing a new way to visually search on Pinterest

Andrew Zhai

Andrew Zhai is a software engineer on the Visual Discovery team

Discovery products at Pinterest are built on top of Pins. Last year, we introduced Guided Search, a feature built on top of understanding Pins’ descriptions. Before that, we launched Related Pins, a service built on top of understanding Pin to board connections.

Pinterest engineering blog

  • Back to all posts
  • Oct 8, 2015
  • Share

Building a new localized search experience

Yuliang Yin

Yuliang Yin is a software engineer on the Search team

As the number of Pinners outside the U.S. grows to nearly half of all 100 million monthly active users, we’re able to show more local content to people around the world. If a Japanese and French Pinner both search for “poster design,” for example, the results should be relevant to their interests and localized in their language. To help Pinners from all over the globe discover the best Pins being saved in their country, today we’re rolling out improvements to search, including more localized results, international autocomplete and international spellcheck.

Tags: 

Pinterest engineering blog

  • Back to all posts
  • May 28, 2015
  • Share

Building a scalable machine vision pipeline

Kevin Jing

Kevin is an engineering manager on the Visual Discovery team. He previously founded Visual Graph, a company acquired by Pinterest in January 2014.

Discovery on Pinterest is all about finding things you love, even if you don’t know at first what you’re looking for. The Visual Discovery engineering team at Pinterest is tasked with building technology that will help people to continue to do just that, by building technology that understands the objects in a Pin’s image to get an idea of what a Pinner is looking for.

Pinterest engineering blog

  • Back to all posts
  • Feb 6, 2015
  • Share

Discover Pinterest: Search and Discovery

Kevin Jing

As we continue to focus on making search improvements and building a discovery engine, we recently invited members of the local search communities to Pinterest for a Discover Pinterest event. Hugh Williams joined a few Pinterest engineers to keynote the event and share insights he’s learned from over two decades in the field.

Pinterest engineering blog

  • Back to all posts
  • Jan 30, 2015
  • Share

A look behind search guides

Kevin Ma

Kevin is a software engineer at Pinterest on the Discovery team

We launched Guided Search last year to give Pinners an exploratory search where they can discover the best ideas by clicking different guides to filter results.

Pages

Subscribe to RSS - Search