Blog
-
Announcing the OpenSearch Project Leadership Committee
We are taking another step on our journey toward a community-driven model of governance. We are thrilled to announce a sustaining OpenSearch Project Leadership Committee (LC) to help the OpenSearch community advance toward these goals.
Read More -
Semantic Search with OpenSearch: Architecture options and Benchmarks
Unlike traditional lexical search algorithms such as BM25, which only take keywords into account, semantic search improves search relevance by understanding the context and semantic meaning of search terms and context. In general, semantic search has two key elements: 1. Embedding generation: A machine learning (ML) model, usually a deep neural network model (for example, TAS-B) is used to generate...
Read More -
Improving document retrieval with sparse semantic encoders
OpenSearch 2.11 introduced neural sparse search—a new efficient method of semantic retrieval. In this blog post, you’ll learn about using sparse encoders for semantic search. You’ll find that neural sparse search reduces costs, performs faster, and improves search relevance. We’re excited to share benchmarking results and show how neural sparse search outperforms other search methods. You can even try it...
Read More -
OpenSearch adds a new generative AI assistant toolkit
OpenSearch is widely used by developers to build search and analytics solutions. One of the areas top of mind for our community has been how to use transformative technologies like artificial intelligence (AI) and machine learning (ML) to improve their search and analytics applications. OpenSearch has supported vector database capabilities, like k-NN, since its inception. Over the last year we...
Read More -
Announcing Data Prepper 2.6.0
Data Prepper 2.6.0 is now available for download. Now you can now ingest data from DynamoDB, improve data durability by using the new Kafka buffer, and automatically connect to Amazon OpenSearch Serverless collections.
Read More