Skip to content
Hot storiesContinuously updated

Zilliz在开源项目提出两阶段Jev检索方案

1 reports1 reporting sourcesUpdated 4 hours ago

Start here

AI overview

2026年11月5日,Zilliz团队在开源项目Vector Graph RAG中提出两阶段Jev决策模型检索方案。针对多跳问答场景中大模型重排耗时过长的问题,该方案通过先筛选图谱关系、再对候选原文进行重排的机制,有效优化了Vector Graph RAG的多跳召回率与检索延迟。目前该检索方案已在其开源项目中正式提出。

AI-generated from reports · Updated 3 hours ago

Report timeline

Follow the reports to see different sides of the story.

Nov 5
  1. AITNT · AI头条
    Zilliz 提出两阶段 Jev 检索优化 Vector Graph RAG 多跳召回与延迟

    Zilliz 团队在开源项目 Vector Graph RAG 中提出两阶段 Jev 决策模型检索方案,先筛选图谱关系再对候选原文重排,解决了多跳问答中大模型重排耗时过长的问题。

Story heat trend

Current heat 9·Comparable peak 10(Nov 5 18:00)·Comparable change, last 24 hours–

02.557.510Nov5Nov5Nov5Nov5

Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.