Build a ChatGPT With Your Own Data | LLM, Embeddings, Vector Store Explained

Are you tired of wasting precious time searching for crucial information scattered across various platforms like Slack, WhatsApp, and documents in different formats? Well, I've got the solution for you!

In this video, I'll take you on a deep dive into the fascinating world of building your very own personal assistant app like ChatGPT with your personal documents.

I'll walk you through each steps and concepts necessary to bring your personal assistant to life. We will cover Large Language Models (LLMs), embeddings, embedding models, and vector stores, demystifying these complex ideas along the way.

⏰ Timestamps:
00:00​ Introduction
01:07 What is an LLM and how does it work?
01:45 Why Not Create My Own LLM?
02:14 Why Not Paste all my documents inside ChatGPT?
02:46 So what's the solution?
03:01 Chunking
03:34 Embedding
04:32 Embedding Model
05:27 Vector Store
06:11 How to query the vector store?
06:57 Conclusion

👋🏻 About Me
I am Dona, a software engineer based in Sydney passionated about the wonderful world of AI.

[evelynshi]

Very helpful. Thanks! Would love to see more videos like this!

[LuoLi-sc]

Very useful content and lovely French accent 👌

[benjoun]

Thanks great educational content, you are gifted to make it so simple & accessible!

[nachoridesbikes]

Great! Could you do a tutorial on how to do it?

[KeithWhittingham]

My documents definitely don't contain sensible data!

(I think you mean 'sensitive')