GraphRAG (beyond the hype)

Practical AI: Machine Learning, Data Science, LLM

Seems like we are hearing a lot about GraphRAG these days, but there are lots of questions: what is it, is it hype, what is practical? One of our all time favorite podcast friends, Prashanth Rao, joins us to dig into this topic beyond the hype. Prashanth gives us a bit of background and practical use cases for GraphRAG and graph data.

Join the discussion

Changelog++ members save 8 minutes on this episode because they made the ads disappear. Join today!

Sponsors:

• Fly.io – The home of Changelog.com — Deploy your apps close to your users — global Anycast load-balancing, zero-configuration private networking, hardware isolation, and instant WireGuard VPN connections. Push-button deployments that scale to thousands of instances. Check out the speedrun to get started in minutes.
• Assembly AI – Turn voice data into summaries with AssemblyAI’s leading Speech AI models. Built by AI experts, their Speech AI models include accurate speech-to-text for voice data (such as calls, virtual meetings, and podcasts), speaker detection, sentiment analysis, chapter detection, PII redaction, and more.
• Speakeasy – Production-ready, enterprise-resilient, best-in-class SDKs crafted in minutes. Speakeasy takes care of the entire SDK workflow to save you significant time, delivering SDKs to your customers in minutes with just a few clicks! Create your first SDK for free!

Featuring:

• Prashanth Rao – Twitter, GitHub, LinkedIn, Website
• Chris Benson – Twitter, GitHub, LinkedIn, Website
• Daniel Whitenack – Twitter, GitHub, Website

Show Notes:

• Kùzu: A highly scalable, extremely fast, easy-to-use embeddable, open source graph database: GitHub repo
• The goals and vision of Kùzu: Blog post
• Kùzu YouTube channel
• Graph RAG strategies with Kùzu: GitHub repo
• Prashanth Rao’s blog: thedataquarry.com

Something missing or broken? PRs welcome!

챕터

1. Welcome to Practical AI (00:00:00)

2. Sponsor: Fly.io (00:00:35)

https://fly.io/

3. Welcome back Prashanth (00:03:49)

4. What are graphs? (00:08:41)

5. DB vs graph experience (00:10:05)

6. Data examples (00:13:31)

7. Sponsor: Assembly AI (00:18:15)

https://www.assemblyai.com/?utm_source=changelog&utm_medium=podcast

8. What is a RAG workflow? (00:20:45)

9. GraphRAG/NaiveRAG (00:24:07)

10. Hallucination risks (00:28:54)

11. Building the data side (00:30:54)

12. Sponsor: Speakeasy (00:35:35)

https://speakeasy.com/

13. Practical uses (00:36:38)

14. Graph construction (00:41:44)

15. Where is this headed? (00:47:26)

16. Thanks for joining us! (00:52:27)

17. Outro (00:53:57)