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: https://discord.com/invite/t4eYQRUcXB ▶️️ Subscribe: https://www.youtube.com/@engineerprompt?sub_confirmation=1 📧 Business Contact: engineerprompt@gmail.com 💼Consulting: https://calendly.com/engineerprompt/consulting-call LINKS: Google Colab: https://tinyurl.com/mr2mf65n llama-Index RAG: https://youtu.be/WL7V9JUy2sE How to chunk Documents: https://youtu.be/n0uPzvGTFI0 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