Chatting with ArXiv Research Papers — AI Assistant #3

In this video, we take a look at the first version of the chatbot that can interact with ArXiv research papers — the beginning of our own "AI research assistant". Everything here is powered by LangChain conversational react agents, OpenAI LLMs (ChatGPT's gpt-3.5-turbo and the text-embedding-ada-002 model for embedding), and the Pinecone vector database for retrieval. By using this LangChain agent framework we're able to give our LLM more abilities, like the ability to surface relevant information from ArXiv, interact with an "ArXiv database", and more. This component is a fundamental part of our AI research assistant. 📌 GitHub Repo: https://github.com/aurelio-labs/arxiv-bot 🔗 Notebook for testing chatbot: https://gist.github.com/jamescalam/c194919290339ff04809e067a6f40de6 👋🏼 NLP + LLM Consulting: https://aurelio.ai 👾 Discord: https://discord.gg/c5QtDB9RAP 🎙️ Support me on Patreon: https://patreon.com/JamesBriggs 00:00 LangChain AI Assistant 00:40 New Arxiver bot in Python 06:00 Arxiver LangChain agent code 12:22 Adding new papers to the DB #artificialintelligence #nlp #openai #langchain