Scraping ArXiv Papers with OpenAI's GPT 3.5 — AI Assistant #2

I'm building an AI assistant that will *actually* be useful. This video covers the ArXiv paper scraping component, using a graph approach where each paper's references become "children" in the graph. We actually use LLMs (OpenAI's text-davinci-003 in this case) to transform the messy references into a clean format that we then use in a Google search and extract paper information from. We're currently focusing on the AI assistant's ArXiv "researcher" component. The idea here is to have a literal research assistant to help me research ideas and the latest in LLMs, AI, NLP, vector search, etc 🔗 Project repo: https://github.com/aurelio-labs/arxiv-bot 🎙️ Support me on Patreon: https://patreon.com/JamesBriggs 🎨 AI Art: https://www.etsy.com/uk/shop/IntelligentArtEU 🤖 70% Discount on the NLP With Transformers in Python course: https://bit.ly/3DFvvY5 🎉 Subscribe for Article and Video Updates! https://jamescalam.medium.com/subscribe https://medium.com/@jamescalam/membership 👾 Discord: https://discord.gg/c5QtDB9RAP