Vectoring in on Pinecone

Practical AI: Machine Learning, Data Science, LLM

Daniel & Chris explore the advantages of vector databases with Roie Schwaber-Cohen of Pinecone. Roie starts with a very lucid explanation of why you need a vector database in your machine learning pipeline, and then goes on to discuss Pinecone’s vector database, designed to facilitate efficient storage, retrieval, and management of vector data.

Join the discussion

Changelog++ members save 3 minutes on this episode because they made the ads disappear. Join today!

Sponsors:

• Plumb – Low-code AI pipeline builder that helps you build complex AI pipelines fast. Easily create AI pipelines using their node-based editor. Iterate and deploy faster and more reliably than coding by hand, without sacrificing control.

Featuring:

• Roie Schwaber-Cohen – Twitter, GitHub, LinkedIn
• Chris Benson – Twitter, GitHub, LinkedIn, Website
• Daniel Whitenack – Twitter, GitHub, Website

Show Notes:

• Pinecone
• Pinecone | Blog

Something missing or broken? PRs welcome!

Chương

1. Welcome to Practical AI (00:00:00)

2. AI Engineer World's Fair (00:00:43)

3. Origins of Pinecone (00:02:18)

4. Vector storing methods (00:04:53)

5. Advantages of vector search (00:07:49)

6. Compressing representation (00:11:25)

7. Sponsor: Plumb (00:13:39)

https://useplumb.com/

8. What is a vector db? (00:15:16)

9. Key functionality (00:18:00)

10. Onboarding enterprises (00:22:32)

11. Internal vs external RAG (00:27:11)

12. Serverless experience (00:28:22)

13. User experience (00:32:15)

14. What is Pinecone enabling? (00:35:44)

15. It shouldn't be complicated (00:38:11)

16. A look into the future (00:40:03)

17. Thanks for joining us! (00:42:52)

18. Outro (00:43:24)