Artwork

内容由Tessl提供。所有播客内容(包括剧集、图形和播客描述)均由 Tessl 或其播客平台合作伙伴直接上传和提供。如果您认为有人在未经您许可的情况下使用您的受版权保护的作品,您可以按照此处概述的流程进行操作https://zh.player.fm/legal
Player FM -播客应用
使用Player FM应用程序离线!

The Graph Layer Behind NASA’s Breakthroughs | Michael Hunger

36:24
 
分享
 

Manage episode 493310236 series 3585084
内容由Tessl提供。所有播客内容(包括剧集、图形和播客描述)均由 Tessl 或其播客平台合作伙伴直接上传和提供。如果您认为有人在未经您许可的情况下使用您的受版权保护的作品,您可以按照此处概述的流程进行操作https://zh.player.fm/legal

Michael Hunger of Neo4j, joins Simon Maple to unpack how graph databases inject structure, intent, and traceability into modern AI systems.
On the docket:

  • why relationships in data encode intent
  • the black-box problem in vector based RAG
  • why devs should build their own MCP server

AI Native Dev, powered by Tessl and our global dev community, is your go-to podcast for solutions in software development in the age of AI. Tune in as we engage with engineers, founders, and open-source innovators to talk all things AI, security, and development.
Connect with us here:

  1. Michael Hunger- https://www.linkedin.com/in/jexpde/
  2. Simon Maple- https://www.linkedin.com/in/simonmaple/
  3. Tessl- https://www.linkedin.com/company/tesslio/
  4. AI Native Dev- https://www.linkedin.com/showcase/ai-native-dev/

(00:00) Trailer
(01:03) Introduction & Neo4j Origins
(03:02) Persisting Relationships for High-Performance Queries
(04:00) Modeling Business Intent & Key Use Cases
(05:00) Fraud Detection at Scale with Graph Algorithms
(06:11) Graph-Enhanced RAG vs. Vector-Only Retrieval
(09:02) Explainability & Drill-Down Evaluation in RAG
(13:05) Fusing Structured & Unstructured Data for Context
(15:00) MCP for Developer Productivity: Schema-to-Code & API Wrapping
(21:16) Security & Sandboxing Best Practices for MCP
(29:08) MCP Server Recommendations & Outro

Join the AI Native Dev Community on Discord: https://tessl.co/4ghikjh
Ask us questions: [email protected]

  continue reading

章节

1. Trailer (00:00:00)

2. Introduction & Neo4j Origins (00:01:03)

3. Persisting Relationships for High-Performance Queries (00:03:02)

4. Modeling Business Intent & Key Use Cases (00:04:00)

5. Fraud Detection at Scale with Graph Algorithms (00:05:00)

6. Graph-Enhanced RAG vs. Vector-Only Retrieval (00:06:11)

7. Explainability & Drill-Down Evaluation in RAG (00:09:02)

8. Fusing Structured & Unstructured Data for Context (00:13:05)

9. MCP for Developer Productivity: Schema-to-Code & API Wrapping (00:15:00)

10. Security & Sandboxing Best Practices for MCP (00:21:57)

11. MCP Server Recommendations & Outro (00:29:49)

83集单集

Artwork
icon分享
 
Manage episode 493310236 series 3585084
内容由Tessl提供。所有播客内容(包括剧集、图形和播客描述)均由 Tessl 或其播客平台合作伙伴直接上传和提供。如果您认为有人在未经您许可的情况下使用您的受版权保护的作品,您可以按照此处概述的流程进行操作https://zh.player.fm/legal

Michael Hunger of Neo4j, joins Simon Maple to unpack how graph databases inject structure, intent, and traceability into modern AI systems.
On the docket:

  • why relationships in data encode intent
  • the black-box problem in vector based RAG
  • why devs should build their own MCP server

AI Native Dev, powered by Tessl and our global dev community, is your go-to podcast for solutions in software development in the age of AI. Tune in as we engage with engineers, founders, and open-source innovators to talk all things AI, security, and development.
Connect with us here:

  1. Michael Hunger- https://www.linkedin.com/in/jexpde/
  2. Simon Maple- https://www.linkedin.com/in/simonmaple/
  3. Tessl- https://www.linkedin.com/company/tesslio/
  4. AI Native Dev- https://www.linkedin.com/showcase/ai-native-dev/

(00:00) Trailer
(01:03) Introduction & Neo4j Origins
(03:02) Persisting Relationships for High-Performance Queries
(04:00) Modeling Business Intent & Key Use Cases
(05:00) Fraud Detection at Scale with Graph Algorithms
(06:11) Graph-Enhanced RAG vs. Vector-Only Retrieval
(09:02) Explainability & Drill-Down Evaluation in RAG
(13:05) Fusing Structured & Unstructured Data for Context
(15:00) MCP for Developer Productivity: Schema-to-Code & API Wrapping
(21:16) Security & Sandboxing Best Practices for MCP
(29:08) MCP Server Recommendations & Outro

Join the AI Native Dev Community on Discord: https://tessl.co/4ghikjh
Ask us questions: [email protected]

  continue reading

章节

1. Trailer (00:00:00)

2. Introduction & Neo4j Origins (00:01:03)

3. Persisting Relationships for High-Performance Queries (00:03:02)

4. Modeling Business Intent & Key Use Cases (00:04:00)

5. Fraud Detection at Scale with Graph Algorithms (00:05:00)

6. Graph-Enhanced RAG vs. Vector-Only Retrieval (00:06:11)

7. Explainability & Drill-Down Evaluation in RAG (00:09:02)

8. Fusing Structured & Unstructured Data for Context (00:13:05)

9. MCP for Developer Productivity: Schema-to-Code & API Wrapping (00:15:00)

10. Security & Sandboxing Best Practices for MCP (00:21:57)

11. MCP Server Recommendations & Outro (00:29:49)

83集单集

Alle episoder

×
 
Loading …

欢迎使用Player FM

Player FM正在网上搜索高质量的播客,以便您现在享受。它是最好的播客应用程序,适用于安卓、iPhone和网络。注册以跨设备同步订阅。

 

快速参考指南

版权2025 | 隐私政策 | 服务条款 | | 版权
边探索边听这个节目
播放