Master AI in 60 Minutes with Vector Databases!

Watch the first part of this series:

Timestamps:
00:00 Intro
02:51 Vector Databases and Embeddings Full Overview
11:48 Embeddings vs Vectors
15:15 Checkin - Real-world Use Case Overview
16:41 Vector Databases and Large Language Models
20:29 Load all Documents
28:10 Generating Embeddings from Docs Chunks and Saving them to the Database
36:29 Getting the Relevant Chunks when Given a Query
42:18 Using OpenAI LLM to Generate a Response - Full Flow
49:07 Summary
50:40 Important Message for YOU

[photorealm]

Great explication, the light bulb went on for me and it started making sense. I have been trying to understand this for a bit now, this video did it. Thanks for your work and sharing it.

[rsoorajs]

Hi, your videos are very informative. It would be very useful to show how to create embeddings using Ollama, as this would help work locally. Additionally, there is a limit on OpenAI API keys, so including a demonstration of creating embeddings via Ollama would be great.

[dhruvbaghel]

Thank you
Please make more videos like these, its a request
I have watched both part and really liked and understand it...

[somynt]

The best Vector data base video-Thankyou sir.

[francescagia]

thank you very much, very well explained. Can you link a repo, where to get the data and use it when coding along, please? :)

[--------]

It is not clear, 1. how many chunks are taken for a query in openai? 2. If there is no suitable chunk, what then? 3. Are there smarter ways to split documents into chunks?
Tnx!