Pinecone Vercel Starter Template and RAG - Live Code Review Part 2

Pinecone Vercel Starter Template and RAG - Live Code Review Part 2

Pinecone via YouTube Direct link

Injecting context in LLMs prompts

12 of 27

12 of 27

Injecting context in LLMs prompts

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Pinecone Vercel Starter Template and RAG - Live Code Review Part 2

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Continuing discussion around the recursive crawler
  2. 2 GitHub CoPilot, and the tasks it excels at
  3. 3 What do we do with the HTML we extract? How the seeder works
  4. 4 The different types of document splitters you can use
  5. 5 embedDocument and how it works
  6. 6 Why do we split documents when working with a vector database?
  7. 7 Problems that occur if you don’t split documents
  8. 8 Proper chunking improves relevance
  9. 9 You still need to tweak and experiment with your chunk parameters
  10. 10 Chunked upserts
  11. 11 Chat endpoint - how we use the context at runtime
  12. 12 Injecting context in LLMs prompts
  13. 13 Is there a measurable difference in where you put the context in the prompt?
  14. 14 Reviewing the end to end RAG workflow
  15. 15 LLMs conditioned us to be okay with responses taking time being pretty slow!
  16. 16 Cool UX anecdote around what humans consider too long
  17. 17 You have an opportunity to associate chunks with metadata
  18. 18 UI cards - selecting one to show it was used as context in response
  19. 19 How we make it visually clear which chunks and context were used in the LLM
  20. 20 Auditability and why it matters
  21. 21 Testing the live app
  22. 22 Outro chatting - Thursday AI sessions on Twitter spaces
  23. 23 Review GitHub project - this is all open-source!
  24. 24 Inaugural stream conclusion
  25. 25 Vim / VsCode / Cursor AI IDE discussion
  26. 26 Setting up Devtools on Mac OSX
  27. 27 Upcoming stream ideas - Image search / Pokemon search

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.