Fast retrieval is table stakes. Retrieval that respects who's asking, what they're allowed to see, a...
TL;DR · AI 摘要
Qdrant 提出了一种结合 Neo4j 图治理层的架构，实现符合企业政策的向量检索。
核心要点
- 企业级 AI 需要结合向量检索与图治理层以确保合规性。
- Adobe 的架构演示了同一查询对不同用户返回不同结果的能力。
- Vector Space Day 将展示该架构的实时演示。
结构提纲
按章节快速跳转。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- 企业级向量检索架构
- 挑战
- 用户身份与权限
- 政策合规性
- 解决方案
- Neo4j 图治理层
- Qdrant 向量检索
- 应用场景
- 企业 AI 系统
金句 / Highlights
值得收藏与分享的关键句。
Fast retrieval is table stakes. Retrieval that respects who's asking, what they're allowed to see, and what policies apply is a much harder problem.
combined with a neo4j graph governance layer, so agents retrieve fast and stay policy-compliant.
They'll demo it live, showing how the same query returns different results for different users based on governance, not just relevance.
Qdrant on X: "Fast retrieval is table stakes. Retrieval that respects who's asking, what they're allowed to see, and what policies apply is a much harder problem. Murthy Chandrapaty and Ankush Gumber from @Adobe are coming to Vector Space Day to show a concrete architecture that solves it: https://t.co/NU00nFNlv8" / X
Qdrant
@qdrant_engine
Fast retrieval is table stakes. Retrieval that respects who's asking, what they're allowed to see, and what policies apply is a much harder problem. Murthy Chandrapaty and Ankush Gumber from
@
Adobe
are coming to Vector Space Day to show a concrete architecture that solves it:
combined with a
neo4j
graph governance layer, so agents retrieve fast and stay policy-compliant. They'll demo it live, showing how the same query returns different results for different users based on governance, not just relevance. If you're building enterprise AI, this is the architecture talk you've been waiting for. Get your ticket at
luma.com/vsd-sf
3:00 PM · Jun 5, 2026
292
Views
4
1
7
Read 4 replies