AITOPAI热报
How-to

AI Dev NYC 工作坊：解决 RAG 检索证据不适用问题

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

Neo4j 的人在 AI Dev NYC 带的实操课，专门讲智能体引用证据但证据不适用怎么办。用知识图谱补上向量检索的短板，做 RAG 系统的开发者能直接抄工作流。

DeepLearning.AI 宣布在 AI Dev NYC 大会开设一场实操工作坊，由 Neo4j 的 Jennifer Reif 与 Nyah Macklin 主讲，主题是修复智能体引用不相关证据的问题。

Body

工作坊定于 2026 年 11 月 30 日至 12 月 1 日在纽约 Chelsea Piers 举行。核心切入点是：基础相似度搜索只能找到看起来相关的文本，但不会验证这些证据是否真正适用于当前上下文。

课程安排从诊断引用失当的具体案例入手，先用最简单可行的方法修复，再进入更复杂的场景——建模实体之间的连接关系，也就是引入知识图谱来补充向量检索的不足。对做 RAG 系统的开发者来说，这是一个从纯向量检索转向向量加知识图谱混合方案的教学案例。

Original · DeepLearning.AI

Basic similarity search finds text that looks relevant. It doesn't check whether that evidence applies to the context. @JMHReif Jennifer Reif ( @neo4j ) & Nyah Macklin lead a hands-on AI Dev NYC workshop on closing this gap: Diagnosing an agent citing evidence that doesn't apply Fixing it with the simplest approach that works Modeling connections a harder case needs 📅Nov 30–Dec 1, 2026 · Chelsea Piers, NYC 🎟Get your tickets ai-dev.deeplearning.ai/speakers/jenni… j9 #AIDev e #DeepLearningAI A #KnowledgeGraphs hs📊 1 ⚡

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, 知识图谱, Neo4j, 智能体.

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

#RAG#知识图谱#Neo4j#智能体#DeepLearning.AI

Keep reading

Recent stories with the same tag or section
ProductsBuildersMulti-sourceSelected03:41
LlamaIndex launches ParseBench-2 benchmark and OCRia-1.5 parsing models

Benchmark design that weights errors by severity rather than raw accuracy changes how OCR vendors will be ranked and evaluated going forward. Teams building document ingestion pipelines, RAG systems, or enterprise data extraction can use ParseBench-2 to compare the 150+ benchmarked OCR solutions, and LlamaParse users get OCRia-1.5 immediately. If you currently evaluate with OmniDocBench or LLM-judge methods, this offers a third methodology grounded in human-judgment alignment.

#LlamaIndex#ParseBench-2#OCRia-1.5#OCR
Event
Jerry Liu@jerryjliu0Source
ModelsBuildersMulti-sourceSelected01:35
LlamaIndex launches ParseBench-2 benchmark and OCRia-1.5 parsing models

The severity-weighted metric design is the notable shift: it fixes the known weaknesses of both deterministic scores and LLM judges, making cross-vendor OCR comparisons more trustworthy. Engineering teams building RAG or document pipelines should re-run their parsing stack against ParseBench-2 before procurement decisions. OCRia-1.5 is available through LlamaParse in the cloud, giving developers a direct baseline to test against incumbent OCR providers on tables, forms and complex layouts.

#LlamaIndex#ParseBench#OCRia-1.5#LlamaParse
Event
Jerry Liu@jerryjliu0Source
ProductsBuilders01:07
Chinese contentPinecone 集成 Gemini Embedding 2，混合搜索免建第二索引

Pinecone 把 Google 的 Gemini Embedding 2 直接做进了索引，发纯文本就能自动向量化，全文搜索和向量搜索共用一个字段。做 RAG 或混合搜索的朋友可以少维护一套嵌入管线，部署成本明显下降，值得上手试试。

#Gemini Embedding 2#Pinecone#RAG#向量数据库
Pinecone@pineconeSource
ProductsBuildersOfficial00:40
Chinese content用编码智能体迁移到 Amazon Bedrock Managed Knowledge Base

AWS 把知识库迁移做成了给编码智能体用的 skill：只读盘点、生成 IaC 模板、切流前自动验证检索。正在用 Bedrock 自管知识库的团队可以少写一堆 CloudFormation，也比手动迁移多了检索质量校验这一步。

#Amazon Bedrock#AWS#RAG#编码智能体
Primary sourceAWS Machine Learning Blog@Josh DeMuthSource