AITOPAI热报
How-to

AI Dev NYC 工作坊：用图连接区分检索证据的相关与适用

DeepLearning.AI@DeepLearningAI
Post
View the post
Why we picked it

Neo4j 两位讲师在 AI Dev NYC 开实操课，讲 RAG 最大的坑：检索到的证据不一定适用当前场景。他们会用图数据库的实体连接缩小证据范围，还教怎么让智能体判断证据够不够。做 RAG 或 Agent 评估的工程师值得去听。

DeepLearning.AI 宣布一场 AI Dev NYC 实操工作坊，主题是 RAG 检索中一个常被忽视的缺口：检索器返回的是与问题匹配的证据，但不会判断这些证据是否适用于当前上下文。

Body

工作坊由 Neo4j 的 Nyah Macklin 与 Jennifer Reif 主讲。内容分三部分：区分相关证据与适用证据；

利用数据间的连接关系（客户、产品、日期）缩小有效证据范围；为智能体加入何时证据足够、何时应停止的检查机制。

工作坊定于 2026 年 11 月 30 日至 12 月 1 日在纽约 Chelsea Piers 举办。

Original · DeepLearning.AI

Retrieval finds evidence that matches the question. It doesn't check whether that evidence applies to the context. Nyah Macklin ( @neo4j ) & Jennifer Reif lead a hands-on AI Dev NYC workshop on closing this gap: Telling relevant evidence apart from applicable evidence Using connections across data (customer, product, date) to narrow what counts Adding checks for when an agent has enough evidence or should stop 📅Nov 30–Dec 1, 2026 · Chelsea Piers, NYC 🎟Get your tickets ai-dev.deeplearning.ai/speakers/nyah-… uE #AIDev e #DeepLearningAI A #AIEvaluation on📊 2 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include RAG, Neo4j, 智能体, AI Dev NYC.

Source attribution: curated from DeepLearning.AI (@DeepLearningAI).

#RAG#Neo4j#智能体#AI Dev NYC#提示词工程

Keep reading

Recent stories with the same tag or section
ProductsBuilders02:54
Chinese contentCoreWeave Database 正式发布：托管 PostgreSQL 直接跑在 CKS 集群内

CoreWeave 把托管 PostgreSQL 塞进了自己的 CKS 集群里，基于 CloudNativePG，还带 pgvector，做 Agent 和 RAG 不用再跨云连数据库了。在 CoreWeave 上跑 GPU 工作负载的团队可以省掉一跳网络延迟，跟自己搭数据库或用 AWS RDS 的方案比，数据离计算更近。

#CoreWeave#PostgreSQL#pgvector#RAG
Event
CoreWeave@CoreWeaveSource
ProductsBuildersSelected02:43
Databricks makes Genie Ontology generally available

The 1.6× accuracy gain at under half the tokens suggests ontology grounding may matter more to agent reliability than model choice itself. Enterprise teams already running Unity Catalog can layer this on without new governance plumbing, making it a practical test case for agent accuracy work. Power BI and Google Drive connectors put it in direct competition with Microsoft's Fabric knowledge tooling.

#Databricks#Genie Ontology#Unity Catalog#agents
Event
Official accountDatabricks@databricksSource
PapersBuildersOfficialSelected02:40
Apple Details Weighted State Souping for Long-Context SSM Retrieval

The non-obvious point is that cached SSM states can be reused like precomputed retrieval index entries, so combining them with learned weights changes how memory-heavy applications manage context cost. Builders of agents, RAG pipelines and personalized assistants can evaluate this as a cheaper alternative to re-encoding long contexts on every query. Compared with transformer-based long-context methods, it trades architectural familiarity for fixed memory and faster inference.

#SSM#state space models#RAG#Apple
Primary sourceApple ML ResearchSource