Vector Database
![Introducing the sparse vector query: Searching sparse vectors with inference or precomputed query vectors](/search-labs/_next/image?url=%2Fsearch-labs%2Fassets%2Fimages%2Fintroducing-sparse-vector-query%2Fdot-product-scoring-example.png&w=3840&q=100)
Introducing the sparse vector query: Searching sparse vectors with inference or precomputed query vectors
Introducing the sparse vector query, powering sparse vector search in the future
![Bit vectors in Elasticsearch](/search-labs/_next/image?url=%2Fsearch-labs%2Fassets%2Fimages%2Fbit-vectors-in-elasticsearch%2Fhamming_dist.png&w=3840&q=100)
Bit vectors in Elasticsearch
What are bit vectors and how to use them in Elasticsearch
![semantic_text with Amazon Bedrock](/search-labs/_next/image?url=%2Fsearch-labs%2Fassets%2Fimages%2Fsemantic-text-with-amazon-bedrock%2Fcover.png&w=3840&q=100)
semantic_text with Amazon Bedrock
Using semantic_text new feature, and AWS Bedrock as inference endpoint service
![Elasticsearch open inference API adds Amazon Bedrock support](/search-labs/_next/image?url=%2Fsearch-labs%2Fassets%2Fimages%2Fblog-aws-inference.png&w=3840&q=100)
Elasticsearch open inference API adds Amazon Bedrock support
Elasticsearch open inference API adds support for embeddings generated from models hosted on Amazon Bedrock."
![Playground: Experiment with RAG using Bedrock Anthropic Models and Elasticsearch in minutes](/search-labs/_next/image?url=%2Fsearch-labs%2Fassets%2Fimages%2Fbedrock-playground%2Fimage.png&w=3840&q=100)
Playground: Experiment with RAG using Bedrock Anthropic Models and Elasticsearch in minutes
Playground is a low code interface for developers to explore grounding LLMs of their choice with their own private data, in minutes.
![Playground: Experiment with RAG applications with Elasticsearch in minutes](/search-labs/_next/image?url=%2Fsearch-labs%2Fassets%2Fimages%2Fplayground-introduction%2Fcover.jpeg&w=3840&q=100)
Playground: Experiment with RAG applications with Elasticsearch in minutes
Playground is a low code interface for developers to explore grounding LLMs of their choice with their own private data, in minutes.
![Elasticsearch vs. OpenSearch: Vector Search Performance Comparison](/search-labs/_next/image?url=%2Fsearch-labs%2Fassets%2Fimages%2Felasticsearch-opensearch-vector-search-performance-comparison%2Fheader.webp&w=3840&q=100)
Elasticsearch vs. OpenSearch: Vector Search Performance Comparison
Elasticsearch is out-of-the-box 2x–12x faster than OpenSearch for vector search
![Elasticsearch new semantic_text mapping: Simplifying semantic search](/search-labs/_next/image?url=%2Fsearch-labs%2Fassets%2Fimages%2Fsemantic-search-simplified-with-semantic-text%2Fcover.jpeg&w=3840&q=100)
Elasticsearch new semantic_text mapping: Simplifying semantic search
Using the new semantic_text field type and semantic query for simplifying semantic search in Elasticsearch
![Enhancing recommendations with geo-semantic search in Elasticsearch](/search-labs/_next/image?url=%2Fsearch-labs%2Fassets%2Fimages%2Fmajestic-geo-semantic-search-recommendations.png&w=3840&q=100)
Enhancing recommendations with geo-semantic search in Elasticsearch
Explore Elasticsearch's hybrid geo-semantic search capabilities and learn how to integrate geographical & semantic search to enhance recommendations.
![Designing for large scale vector search with Elasticsearch](/search-labs/_next/image?url=%2Fsearch-labs%2Fassets%2Fimages%2Felasticsearch-vector-large-scale-part1%2Faggressive-merge-results.png&w=3840&q=100)
Designing for large scale vector search with Elasticsearch
Part 1: High-fidelity dense vector search in Elasticsearch. Learn how we achieve a 75% memory reduction without impacting search quality.