27,745 views
Discover how RAGs deliver accurate, verifiable results without the prohibitive costs of training and ongoing updating. Dive into the world of AI efficiency, where less is more and knowledge is accessible to everyone. LLMs Video: • It's not all about ChatGPT - Introduction to L... Prompt engineering: • Prompt Engineering Interacting with... Embeddings: • The magic of Machine Learning: Embedd... RAG: • BETTER and CHEAP: How RAG is... Code: https://feregri.no/rag SUPPORT ME: Join the channel and enjoy benefits: https://www.youtube.com/@feregri_no/join Buy me a coffee: https://www.buymeacoffee.com/feregrino SOCIAL: / feregri_no / feregri_no https://twitch.com/feregri_no / feregri_no https://github.com/fferegrino https://kaggle.com/ioexception https://feregri.no TIMESTAMPS: 00:00:00 Start 00:01:45 Everyone wants a GPT 00:05:39 Traditional LLM query 00:08:27 RAG systems 00:11:52 What a system offers us RAG 00:13:31 How to do context recovery 00:15:58 Populating a vector DB 00:17:53 What to do with the user query 00:18:38 Complete RAG system 00:20:04 Practical project 00:20:56 Project components 00:23:02 Where to find the code 00:24:37 Introduction to the dataset 00:26:39 A motivating example 00:28:59 Working with the dataset 00:33:31 Introduction to Chunking 00:35:58 Chunking our documents 00:39:42 Processing the chunks to index them 00:41:46 Where do we get the embeddings from 00:43:03 Creating embeddings for our documents 00:45:21 Vector database 00:46:46 Inserting into the vector DB 00:50:33 Running queries in the DB 00:51:26 Getting potential responses 00:53:19 Generating RAG responses 00:53:56 Generating responses with my documents 00:58:14 Next steps 01:00:14 In conclusion