Building a GPT-3 Enabled Document Assistant with LangChain: Academy

In this video tutorial, we'll discuss how to use LangChain and the OpenAI Embeddings in order to upload unstructured documents and be able to ask questions about the document using GPT-3

Specifically, we can use LangChain and the Unstructured library to transform PDFs, PowerPoints, images, and HTML into text. We can then use OpenAI's embeddings & completions API to be able to ask questions about our document.

The steps we need to take to do this include:

1. Install and import the necessary packages
2. Upload unstructured documents with LangChain
3. Split the documents into smaller chunks of text
4. Retrieve document embeddings with OpenAI
5. Ask questions about the document with GPT-3
6. Including document sources in our responses