search

opensearch-project / project-website

The source to opensearch.org
https://opensearch.org
BSD 3-Clause "New" or "Revised" License
40 stars 478 forks source link

OpenSearchCon - Add new session for Airbnb #3276

Closed pajuric closed 1 month ago

pajuric commented 2 months ago

Please add the following session for OpenSearchCon 2024:

Date: 9/25 Room: Main Stage (Continental 4-5) Time: 10:00-10:40am

Title: Airbnb Embedding Platform

Abstract In this session, you'll learn how Airbnb is leveraging OpenSearch as a vector database for its embedding platform. This talk is for everyone, starting with an overview of how Airbnb is using vector embeddings to solve guest, host & marketplace challenges, followed by specific use cases that led Airbnb to adopt OpenSearch as its vector database. We will share lessons learned and provide insights into strategies for optimizing OpenSearch as a vector database.This talk is must attend for those exploring vector databases to power embeddings based retrieval, generative AI or RAG use cases. Description In this talk we will

  1. Overview - Discuss how we use embeddings and LLMs to tackle many product challenges across Airbnb.
  2. Infrastructure - We will also discuss the infrastructure we built at airbnb to power vector solutions with focus on Airbnb’s embedding platform.
  3. OpenSearch - This section will discuss in detail how we leverage OpenSearch as a vector database to store and retrieve embeddings effectively.
  4. Optimizations - Finally we share our learnings and strategies to optimize OpenSearch vector indices with “image search” as case study.

Presenters: Moutupsi Paul (she/her) Moutupsi is a Staff engineer at Airbnb and has been working in search infrastructure and solutions for the past ten years. Her interests range from building efficient data processing and indexing platforms to high performance retrieval and ranking infrastructure. Before Airbnb she worked at Microsoft’s knowledge graph and ads team. Besides work she enjoys spending time with her family, hiking across pacific north-west and pursuing south-asian dance forms.

Xiaotang Wang (she/her) Xiaotang is a Senior Engineer at Airbnb, where she has been working on scalable indexing and search systems, along with the necessary toolings, for the past seven years. Her expertise covers a wide spectrum of search systems, from supporting product features to optimizing backend infrastructure for performance and scalability. Currently, she is focused on developing an embedding search platform based on OpenSearch. Xiaotang is eager to share her insights and experiences at the OpenSearch conference.

Tomas Fernandez Lobbe (he/him) Tomás is a senior engineer, currently working with Airbnb to build and support search infrastructure. He is a committer and PMC member for Apache Lucene and Solr projects, and has ample experience in search, having helped building scalable and reliable search infrastructure at Apple and Amazon for the past 10+ years.

Amulya Sharma (he/him) Amulya is a Principal Technologist at AWS. In his role Amulya partners with AWS strategic customers, such as Airbnb, to help them in building and operating exceptional products on AWS. In addition Amulya is one of the founders of AWS Resiliency Focus Area and Open Source Observability Ambassadors group.

pajuric commented 2 months ago

@kaimmej - FYI

pajuric commented 2 months ago

@nateynateynate - Can we push this to the schedule tomorrow?

pajuric commented 1 month ago

@nateynateynate @peterzhuamazon - Can we get this one pushed live.