LangChain101: Question A 300 Page Book (w/ OpenAI + Pinecone)

Twitter: https://twitter.com/GregKamradt
Or get updates to your inbox: https://mail.gregkamradt.com/signup

In this tutorial we will load a PDF book, split it up into documents, get vectors for those documents as embeddings, then ask a question.

—AI Generated Description—
In this tutorial, I am is discussing how to query a book using OpenAI, LangChain, and Pinecone, an external vector store, for semantic search.

I’m demonstrating how to split up the book into documents, use OpenAI embeddings to change them into vectors, and then use Pinecone to store them externally.

I’m then showing how to ask a question and get an answer back in natural language. This technique can be used to query books as well as internal documents or external data sets.
—AI Generated Description—



0:00 – Intro
1:31 – Diagram Overview
3:33 – Code Start
5:46 – Embeddings
6:33 – Pinecone Index Create
7:45 – First Question
9:33 – Ask Questions w/ OpenAI

Code: https://github.com/gkamradt/langchain-tutorials/blob/main/data_generation/Ask%20A%20Book%20Questions.ipynb