How to Improve LLMs with RAG (Overview + Python Code)
30,150
Published 2024-03-18
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: • Large Language Models (LLMs)
🎥 Fine-tuning with QLoRA: • QLoRA—How to Fine-tune an LLM on a Si...
📰 Read more: medium.com/towards-data-science/how-to-improve-llm…
💻 Colab: colab.research.google.com/drive/1peJukr-9E1zCo1iAa…
💻 GitHub: github.com/ShawhinT/YouTube-Blog/tree/main/LLMs/ra…
🤗 Model: huggingface.co/shawhin/shawgpt-ft
Resources
[1] github.com/openai/openai-cookbook/blob/main/exampl…
[2] • LlamaIndex Webinar: Building LLM Apps...
[3] docs.llamaindex.ai/en/stable/understanding/loading…
[4] • LlamaIndex Webinar: Make RAG Producti...
--
Book a call: calendly.com/shawhintalebi
Homepage: shawhintalebi.com/
Socials
medium.com/@shawhin
www.linkedin.com/in/shawhintalebi/
twitter.com/ShawhinT
www.instagram.com/shawhintalebi/
The Data Entrepreneurs
🎥 YouTube: / @thedataentrepreneurs
👉 Discord: discord.gg/RSqZbF9ygh
📰 Medium: medium.com/the-data-entrepreneurs
📅 Events: lu.ma/tde
🗞️ Newsletter: the-data-entrepreneurs.ck.page/profile
Support ❤️
www.buymeacoffee.com/shawhint
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
All Comments (21)
-
Check out more videos in this series 👇 👉 Series Playlist: youtube.com/playlist?list=PLz-ep5RbHosU2hnz5ejezwa… 🎥 Fine-tuning with QLoRA: https://youtu.be/XpoKB3usmKc -- 📰 Read more: medium.com/towards-data-science/how-to-improve-llm… 💻 Colab: colab.research.google.com/drive/1peJukr-9E1zCo1iAa… 💻 GitHub: github.com/ShawhinT/YouTube-Blog/tree/main/LLMs/ra… 🤗 Model: huggingface.co/shawhin/shawgpt-ft Resources [1] github.com/openai/openai-cookbook/blob/main/exampl… [2] https://www.youtube.com/watch?v=efbn-3tPI_M [3] docs.llamaindex.ai/en/stable/understanding/loading… [4] https://www.youtube.com/watch?v=Zj5RCweUHIk&list=WL&index=4
-
Thank you Talebi. No one explains the subject like you
-
This is so helpful! Thanks Shaw, you never miss!
-
Incredible breakdown Shaw!
-
superb explanation Shaw !😍
-
very nice. thank you for explaining in details.
-
Very good explanation 👏 👌
-
Very useful indeed
-
Really great
-
Thank you very much!
-
good work!
-
Thanks Shaw!
-
Solid video
-
Very useful.
-
Great 🙏
-
Awesome video, thanks! I'm wondering if instead of using top_k documents/batches one could define a threshold/distance for the used batches?
-
Thank you so much sir :)
-
Thankyou so much. Becoming a fan of yours! Please do a video on Rag with llamaIndex + llama3 if it's free and not paid.
-
Thanks!
-
super helpfull