开源的大规模搜索与向量检索引擎,把关键字检索、向量召回和机器学习排序放在同一个平台里完成,单集群可以承载十亿级文档。做 RAG 时常用它当检索底座,因为排序逻辑能用配置和模型一起调,不必在多个系统间搬数据。 🔗 GitHub Stars: 7.1k+
An open-source engine for large-scale search and vector retrieval that combines keyword matching, vector recall and ML ranking in one platform, scaling to billions of documents per cluster. A common retrieval base for RAG pipelines. 🔗 GitHub Stars: 7.1k+
Vespa belongs to the Developer Tools category on hedirbase. Tagged with: search,vector-database,rag,retrieval,self-hosted.
An open-source engine for large-scale search and vector retrieval that combines keyword matching, vector recall and ML ranking in one platform, scaling to billions of documents per cluster. A common r