Play all

Continuing discussion around the recursive crawler

GitHub CoPilot, and the tasks it excels at

What do we do with the HTML we extract? How the seeder works

The different types of document splitters you can use

embedDocument and how it works

Why do we split documents when working with a vector database?

Problems that occur if you don’t split documents

Proper chunking improves relevance

You still need to tweak and experiment with your chunk parameters

Chunked upserts

Chat endpoint - how we use the context at runtime

Injecting context in LLMs prompts

Is there a measurable difference in where you put the context in the prompt?

Reviewing the end to end RAG workflow

LLMs conditioned us to be okay with responses taking time being pretty slow!

Cool UX anecdote around what humans consider too long

You have an opportunity to associate chunks with metadata

UI cards - selecting one to show it was used as context in response

How we make it visually clear which chunks and context were used in the LLM

Auditability and why it matters

Testing the live app

Outro chatting - Thursday AI sessions on Twitter spaces

Review GitHub project - this is all open-source!

Inaugural stream conclusion

Vim / VsCode / Cursor AI IDE discussion

Setting up Devtools on Mac OSX

Upcoming stream ideas - Image search / Pokemon search

Description:

Dive into the second part of a live code review exploring the Pinecone Vercel starter template and Retrieval Augmented Generation (RAG). Explore topics such as recursive crawlers, document splitting techniques, embedding processes, and the importance of proper chunking in vector databases. Learn about injecting context into LLM prompts, the end-to-end RAG workflow, and how to associate metadata with chunks. Discover UI design considerations for displaying context usage, the significance of auditability, and test a live application. Gain insights on GitHub CoPilot, IDE preferences, and setting up developer tools on Mac OSX. The video concludes with discussions on future stream ideas and AI sessions on Twitter spaces.

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

Pinecone

Add to list

#Programming #Databases #Vector Databases #Software Development #GitHub Copilot #Computer Science #Machine Learning #Embeddings #Retrieval Augmented Generation

0:00 / 0:00