In this video we’ll learn how to use OpenAI’s new GPT-4 api to ‘chat’ with and analyze multiple PDF files. In this case, I use three 10-k annual reports for Tesla (~1000 PDF pages)

OpenAI recently announced GPT-4 (it’s most powerful AI) that can process up to 25,000 words – about eight times as many as GPT-3 – process images and handle much more nuanced instructions than GPT-3.5.

You’ll learn how to use LangChain (a framework that makes it easier to assemble the components to build a chatbot) and Pinecone – a ‘vectorstore’ to store your documents in number ‘vectors’. You’ll also learn how to create a frontend chat interface to display the results alongside source documents.

A similar process can be applied to other usecases you want to build a chatbot for: PDF’s, websites, excel, or other file formats.

(Side note: Since the time of recording a newer, up to date version of the video has been recorded here: https://youtu.be/OF6SolDiEwU)

Visuals & Code:
🖼 Visual guide download + github repo (this is the base template used for this demo):
https://github.com/mayooear/gpt4-pdf-chatbot-langchain/tree/feat/vectordbqa

(NOTE: The latest code example is here https://github.com/mayooear/ai-pdf-chatbot-langchain)

Books:

Learning LangChain (O’Reilly): https://www.oreilly.com/library/view/learning-langchain/9781098167271/

Twitter: https://twitter.com/mayowaoshin

Send a tip to support the channel: https://ko-fi.com/mayochatdata

Timestamps:

01:02 PDF demo (analysis of 1000-pages of annual reports)
06:01 Visual overview of the multiple pdf chatbot architecture
17:40 Code walkthrough pt.1
25:15 Pinecone dashboard
28:30 Code walkthrough pt.2

#gpt4 #investing #finance #stockmarket #stocks #trading #openai #langchain #chatgpt #langchainjavascript #langchaintypescript #langchaintutorial

source