Understanding Embeddings in RAG and How to use them - Llama-Index

In this video, we will take a deep dive into the World of Embeddings and understand how to use them in RAG pipeline in Llama-index. First, we will understand the concept and then will look at home to use different embeddings including OpenAI Embedding, Open source embedding (BGE, and instructor embeddings) in llama-index. We will also benchmark their speed.


CONNECT:
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Support my work on Patreon: Patreon.com/PromptEngineering
🦾 Discord:   / discord  
▶️️ Subscribe: https://www.youtube.com/@engineerprom...
📧 Business Contact: [email protected]
💼Consulting: https://calendly.com/engineerprompt/c...


LINKS:
Google Colab: https://tinyurl.com/mr2mf65n
llama-Index RAG:    • Talk to Your Documents, Powered by Ll...  
How to chunk Documents:    • LangChain: How to Properly Split your...  
llama-Index Github: https://github.com/jerryjliu/llama_index

TIMESTAMPS:
[00:00] Intro
[01:21] What are Embeddings
[03:58] How they Work!
[05:54] Custom Embeddings
[08:30] OpenAI Embeddings
[09:33] Open-Source Embeddings
[10:45] BGE Embeddings
[11:42] Instructor Embeddings
[11:57] Speed Benchmarking