返回首页

对比阅读

对比阅读:StarRocks Unifies Multimodal Search and Analytics, Cutting AI Data Movement 与 StarRocks合并多模态检索与分析,AI数据链路开始减少搬运

AEN
StarRocksAlibaba CloudEMR Serverless·

StarRocks Unifies Multimodal Search and Analytics, Cutting AI Data Movement

Alibaba Cloud's open-source analytical database StarRocks is bringing multimodal retrieval and analytics into a single SQL query layer for images, video and text. Its value lies not in adding another vector-search feature, but in reducing system switching and repeated synchronization across the AI data pipeline. Even so, this remains a vendor-announced product capability: production performance and costs still need validation.

What this is

Multimodal retrieval processes text, images, video and other information together, then finds relevant content by semantic similarity. The traditional approach typically uses a vector-retrieval service to identify candidate samples first, before passing their IDs to an analytical database to join tags and calculate distributions. As sample volumes grow, data transfers and follow-up queries across systems increase.

StarRocks' new direction is to bring vector retrieval, business-condition filtering, joins and aggregation into the same query. Users of EMR Serverless StarRocks can read open lakehouse tables such as Paimon and Iceberg, and use SQL to invoke models that extract fields or generate embeddings. Officially cited use cases include training-data selection, retrieval-augmented generation (RAG, where a model retrieves information before answering) and historical-record retrieval for AI applications.

Industry view

We believe this reflects AI infrastructure's shift from a model-centric architecture toward a data-pipeline-centric one. As model capabilities converge, corporate differentiation often depends on whether companies can efficiently find, filter and govern their own business data. Combining retrieval and analytics within one engine could reduce back-and-forth movement of candidate lists and avoid duplicating business attributes.

Consolidation, however, does not automatically mean lower costs or greater simplicity. Vector indexes consume storage and computing resources, while this article discloses neither latency nor recall quality for large-scale image and video retrieval. Multimodal search must also address authorization, versioning and label consistency. The reuse of game or advertising assets, in particular, cannot be determined by similarity alone. Another risk is whether the query optimizer can reliably execute complex mixed execution plans, rather than working only in demonstrations.

Impact on regular people

For enterprise IT: Companies may gradually reduce the need to stitch together vector databases, analytical warehouses and data-synchronization tools. Before migrating, they still need to calculate indexing, computing and operations costs, and verify compatibility with existing lakehouse table formats and business systems.

For individual professionals: Data, operations and business staff should find it easier to search for images, video or historical cases using natural-language descriptions. Whether this actually improves productivity depends on whether their company has completed data organization, labeling and permission governance, rather than merely adding another query interface.

For the consumer market: Ad-creative matching, product-content search and customer-service knowledge bases may gain more consistent analytical feedback, improving recommendation and campaign-placement efficiency. Consumers will also see more personalized content based on companies' private data.

来源: juejin.cn
BZH
StarRocks阿里云EMR Serverless·

StarRocks合并多模态检索与分析,AI数据链路开始减少搬运

阿里云开源分析数据库StarRocks正在把多模态检索与分析合并到同一套SQL查询中,覆盖图片、视频和文本。其价值不在于增加一个向量搜索功能,而在于减少AI数据链路中的系统切换与重复同步;但这仍是厂商发布的产品能力,生产性能与成本仍需验证。

这是什么

多模态检索指同时处理文字、图片、视频等信息,并按语义相似度寻找相关内容。传统做法通常由向量检索服务先找候选样本,再把编号交给分析数据库关联标签、统计分布;样本量扩大后,跨系统传输和补查都会增加。

StarRocks的新方向是将向量检索、业务条件过滤、关联和聚合纳入同一条查询。用户在EMR Serverless StarRocks中可读取Paimon、Iceberg等开放湖表,并用SQL调用模型提取字段或生成向量。官方列举的场景包括训练数据圈选、检索增强生成(RAG,让模型先检索资料再回答)和AI应用的历史记录检索。

行业怎么看

我们认为,这反映出AI基础设施正在从“模型中心”向“数据链路中心”移动。模型能力趋同后,企业差异往往来自能否高效找到、筛选并治理自己的业务数据。把检索和分析放在一个引擎内,有望减少候选名单往返,也避免重复保存业务属性。

但统一并不等于更便宜或更简单。向量索引会占用存储与计算资源,大规模图片、视频检索的延迟和召回质量也未在本文中披露。多模态检索还要面对授权、版本和标签一致性等问题,尤其游戏、广告素材的复用不能只靠相似度判断。另一个风险是查询优化器能否稳定执行复杂的混合计划,而不只在演示场景中成立。

对普通人的影响

对企业IT:企业可能逐步减少向量数据库、分析库与数据同步工具之间的拼接,但迁移前仍需核算索引、计算和运维成本,并验证现有湖表格式与业务系统的兼容性。

对个人职场:数据、运营和业务人员将更容易用自然描述寻找图片、视频或历史案例;不过能否真正提效,取决于公司是否完成数据整理、标签和权限治理,而非只增加一个查询入口。

对消费市场:广告素材匹配、商品内容检索和客服知识库可能获得更稳定的分析反馈,进而影响推荐与投放效率;消费者也会看到更多基于企业私有资料的个性化内容。

来源: juejin.cn