OpenSearch Project Blog

OpenSearch provides a wide range of capabilities to support modern search needs, including traditional keyword-based techniques like lexical search using BM25 and more advanced methods like semantic and hybrid search....

Vector search plays a crucial role in many machine learning (ML) and data science pipelines. In the context of large language models (LLMs), vector search powers retrieval-augmented generation (RAG), a technique...

Introduced in OpenSearch 2.18, Intel Advanced Vector Extensions 512 (Intel AVX-512) is a set of new instructions that can accelerate vector workload performance. Vector search benchmarks using OpenSearch Benchmark showed...

The rise of generative AI has transformed search technology, evolving it from simple keyword-based retrieval to intelligent, multimodal search experiences powered by deep learning. In this keynote address at the Linux Foundation Member...

OpenSearch is a scalable open-source search and analytics platform that can serve as the core of a Security Information and Event Management (SIEM) system. OpenSearch can centralize logs from diverse...

OpenSearch’s adoption as a vector database has grown significantly with the rise of generative AI applications. Vector search workloads are scaling from millions to billions of vectors, making traditional CPU-based indexing both...

As organizations increasingly rely on cloud services, monitoring and detecting anomalies in system behavior has become crucial for maintaining reliable operations. In this post, we’ll explore recent improvements to the...

Trail of Bits, an independent research and consulting company, recently completed a detailed analysis of OpenSearch performance. Read the blog post and detailed analysis to learn about key performance metrics for the Big5 workload! OpenSearch is...

OpenSearch is a powerful open-source search and analytics engine that enables you to efficiently search and filter large datasets. A common search pattern involves filtering documents based on whether a...

Vector search has gained significant attention in the area of information retrieval thanks to advances in natural language embedding models. These models map domain-specific data into a vector space, where...

In February 2024, we decided to revamp the OpenSearch API Specification repository by adopting the OpenAPI Specification. While this change offered significant benefits, we encountered some challenges during implementation. Most...

OpenSearch 2.19 introduces reciprocal rank fusion (RRF), a new feature in the Neural Search plugin that enhances hybrid search. RRF merges ranked results from multiple query sources, such as neural...

The latest version of OpenSearch expands capabilities for search and observability use cases, boosts performance and ease of use, and introduces an array of advancements for machine learning (ML) and...

The OpenSearch Anomaly Detection plugin is powered by the Random Cut Forest (RCF) algorithm. Although RCF is a powerful algorithm, false alarms reduce its practical value because users must spend time verifying...

In an earlier blog post, we introduced OpenSearch’s support for the DeepSeek large language model (LLM). This post focuses on simplifying DeepSeek LLM integration using the OpenSearch Flow Framework plugin. With...

OpenSearch now integrates with DeepSeek, offering powerful and cost-effective AI capabilities. In this blog post, we’ll guide you through setting up a retrieval-augmented generation (RAG) system using OpenSearch and the DeepSeek...

We’re excited to announce that OpenSearch now supports DeepSeek integration, providing powerful and cost-effective AI capabilities. DeepSeek-R1 is a recently released open-source large language model (LLM) that delivers similar benchmarking performance to...

We’re excited to announce the release of OpenSearch JavaScript client 3.0.0. This version introduces significant improvements, including enhanced readability and consistency and a more accurate interface for interacting with OpenSearch...

As the OpenSearch Project continues to evolve, it forges its own path by prioritizing features driven by the needs and feedback of its community and users. In this spirit of...