How to Improve LLMs with RAG (Overview + Python Code)

Get exclusive access to AI resources and project ideas: https://the-data-entrepreneurs.kit.com/shaw

In this video, I give a beginner-friendly introduction to retrieval augmented generation (RAG) and show how to use it to improve a fine-tuned model from a previous video in this LLM series.

▶️ Series Playlist: https://www.youtube.com/playlist?list=PLz-ep5RbHosU2hnz5ejezwaYpdMutMVB0
🎥 Fine-tuning with QLoRA: https://youtu.be/XpoKB3usmKc

📰 Read more: https://medium.com/towards-data-science/how-to-improve-llms-with-rag-abdc132f76ac?sk=d8d8ecfb1f6223539a54604c8f93d573
💻 Colab: https://colab.research.google.com/drive/1peJukr-9E1zCo1iAalbgDPJmNMydvQms?usp=sharing
💻 GitHub: https://github.com/ShawhinT/YouTube-Blog/tree/main/LLMs/rag
🤗 Model: https://huggingface.co/shawhin/shawgpt-ft

References
[1] https://github.com/openai/openai-cookbook/blob/main/examples/Question_answering_using_embeddings.ipynb
[2] https://www.youtube.com/watch?v=efbn-3tPI_M
[3] https://docs.llamaindex.ai/en/stable/understanding/loading/loading.html
[4] https://www.youtube.com/watch?v=Zj5RCweUHIk&list=WL&index=4

--
Homepage: https://www.shawhintalebi.com/
Book a call: https://calendly.com/shawhintalebi

Intro - 0:00
Background - 0:53
2 Limitations - 1:45
What is RAG? - 2:51
How RAG works - 5:03
Text Embeddings + Retrieval - 5:35
Creating Knowledge Base - 7:37
Example Code: Improving YouTube Comment Responder with RAG - 9:34
What's next? - 20:58