Release notes

更新时间:
复制 MD 格式

This document describes the feature releases and updates for OpenSearch Vector Search Edition.

2026

May

Date

Feature

Type

Description

2026-05

Product feature updates

New

  1. Introduces a vector caching feature that uses a cache table to automatically compare field content during data ingestion. The model recomputes vectors only for changed data, significantly reducing model API calls and computational costs.

  2. Introduces the object field type and nested query. You can now store multiple fields in a nested structure and use a nested query to retrieve data from it, supporting complex query models.

April

Date

Feature

Type

Description

2026-04

Product feature updates

New

Adds a vector fusion feature that lets you use a multimodal model to encode content from multiple fields, such as text and image, into a single vector. This enables cross-modal retrieval.

March

Date

Feature

Type

Description

2026-03

Product feature updates

New

  1. Adds support for vector models from Model Studio. You can now vectorize multimodal data, such as text and images, during preprocessing for index building and queries. Supported models include multimodal and text vector models.

2025

January

Date

Feature

Type

Description

2025-01-02

Product feature updates

New

  1. The CAGRA algorithm now supports GPU acceleration. You can purchase GPU-based nodes to achieve significant performance improvements in high-QPS scenarios.

  2. Supports hybrid search. You can build an inverted index on text fields and use hybrid retrieval (a combination of full-text search and vector search) to improve search quality in RAG and semantic search scenarios.

  3. Adds support for range indexes. You can use a range index to query documents within a specific range. Using a range index instead of a range filter in a filter clause significantly improves performance.

  4. You can specify whether to create an index that has the same name as a field.

  5. Supports statistical syntax.

2024

December

Date

Feature

Type

Description

2024-12-05

Product feature updates

New

  1. Introduces the QGraph algorithm, an improvement on HNSW, which automatically quantizes raw data during index building. This reduces index size to 1/8 of the original and delivers performance several times that of HNSW.

  2. Supports the JSON format for files from a full data source in Object Storage Service (OSS).

September

Date

Feature

Type

Description

2024-09-27

Product feature updates

New

  1. Integrates with AI Search Open Platform, allowing you to call platform model services, such as embedding and the OCR service, directly from the console when configuring fields.

  2. Supports automatic data cleanup based on time to live (TTL).

  3. Supports custom resource policies for table loading.

2024-09-10

Product feature updates

New

  1. Supports Data Lake Formation (DLF) as a full data source.

July

Date

Feature

Type

Description

2024-07-01

Product feature updates

New

  1. Adds a log query feature for viewing query and write logs.

  2. Supports table aliases.

  3. Supports custom default values for fields.

June

Date

Feature

Type

Description

2024-06-04

Feature optimization

Optimized

  1. Improved table creation time.

  2. Supports adjusting the number of QRS worker replicas.

  3. Improved the API.

March

Date

Feature

Type

Description

2024-03-26

Product feature updates

New

  1. The console now supports vector data management, including adding, deleting, and previewing data.

  2. Updated monitoring metrics.

  3. Improved the Change History FSM.

  4. Shard decoupling: The number of table shards is now decoupled from the number of Searcher workers, and shard counts are also decoupled between tables.

  5. Supports adding remarks to fields.

  6. Supports schema import and export.

January

Date

Feature

Type

Description

2024-01-17

Product feature updates

New

  1. The console supports primary key queries, image or text uploads for search, and hybrid queries.

  2. Supports multi-subject recognition for image search.

2024-01-08

Product feature updates

New

  1. Supports hybrid retrieval.

  2. Supports configuring multiple vectors for a single document.

  3. Adds a new text-to-vector model that supports automatic vectorization for Chinese and English text with token lengths of 128, 512, and 1024.

2023

December

Date

Feature

Type

Description

2023-12-26

Instance specification adjustment

New

Supports purchasing a single Searcher worker.

October

Date

Feature

Type

Description

2023-10-12

Instance specification adjustment

New

  1. New, smaller node specifications are available: QRS workers start at 2 vCPUs and 8 GB of memory, and Searcher workers start at 2 vCPUs and 16 GB of memory.

  2. QRS workers and Searcher workers support both cloud disk and SSD types.

  3. Each single instance now includes 100 GB of free index storage.

  4. Adjusted the instance rental fee.

2023-10-10

Product feature updates

New

  1. Adds an enhanced e-commerce image-to-vector model.

  2. Supports resource updates based on data changes from the current full version.

September

Date

Feature

Type

Description

2023-09-07

Product redesign

New

  1. Improved the query method.

  2. Upgraded SDK versions.

    1. SDK for the new engine (Developer Guide)

    2. SDK for the old engine ( Developer Guide (ha3_3.10.0))

August

Date

Feature

Type

Description

2023-08-31

Product feature updates

New

  1. Table configuration now supports Object Storage Service (OSS) data sources.

  2. Removes the TEXT field type.

July

Date

Feature

Type

Description

2023-07-21

Product redesign

New

OpenSearch Vector Search Edition is now generally available.

June

Date

Feature

Type

Description

2023-06-07

Product feature updates

New

  1. Adds the ignore_invalid_doc and enable_rt_build configurations for vector indexes.

  2. Supports configuring an instance alert at the account level.

  3. Adds the Pause Switch feature.

  4. Supports dictionary content upload from a file.

  5. Adds an incremental text vector template.

March

Date

Feature

Type

Description

2023-03-30

Product feature updates

New

  1. Introduces end-to-end image search. This includes support for image embedding to enable text-to-image search and image-to-image search.

  2. Supports data compression for fields, attributes, and indexes.

  3. Adds internet access and IP whitelist features.

  4. Adds support for data retrieval by using a RESTful API.

  5. Adds the Vector: Image Search template.

January

Date

Feature

Type

Description

2023-01-09

Product feature updates

New

  1. Adds multiple built-in analyzers, including an entertainment content analyzer, a general English e-commerce analyzer, an IT content analyzer, an e-commerce analyzer, a person name analyzer, and a geographic location analyzer. All built-in analyzers support dictionary intervention.

  2. Supports user-defined multi-value delimiters.

  3. Infrequently used advanced configuration parameters for vector indexes are collapsed by default to simplify configuration and O&M.

  4. Adds alert monitoring for when the index change rate exceeds a specified threshold or when full and incremental updates are not completed within a specified period. You can customize alert thresholds.

  5. The Change History page now displays offline full-build metrics, which allows you to monitor the build process.

2022

September

Date

Feature

Type

Description

2022-09-21

Product feature updates

New

  1. Removes the DUP requirement for vector fields, adds field order restrictions for vector indexes, expands the field types supported by vector indexes, and adds default values for advanced vector index configurations to simplify setup.

  2. Supports setting a timestamp by using natural time.

  3. On the Deployment Management page, you can switch index tables to go live. All data sources, index tables, and clusters are displayed on the Deployment Management page.

August

Date

Feature

Type

Description

2022-08-16

Product feature updates

New

1. Adds an index data recovery feature and a quick shard scaling feature.

2. Improved the alert feature and adds a default alert for the Vector Search Edition.

May

Date

Feature

Type

Description

2022-05-20

Product feature updates

New

1. Includes quick cluster scale-out, click-based configuration for index structures, addition of query configuration to online configurations, and scenario-based instance O&M.

2. Vectors can be used as plug-ins in the sorting phase. Supports multi-value indexes and range indexes.

2021

December

Date

Feature

Type

Description

2021-12-31

Official release of OpenSearch Vector Search Edition

New

OpenSearch Vector Search Edition is officially released. It provides a highly available, low-latency, and cost-effective solution with an automated O&M system for building custom search services.