README.md

metadata

title: US History QA
emoji: 📖
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 3.39.0
app_file: app.py
pinned: true
license: bigscience-openrail-m

Overview

This is a basic Question-Answer style of chain using a database created from OpenStax's free US History textbook. The question is embedded as a vector, the database retrieves the nearest vectors in the database, and that is then input into GPT-3.5-turbo to generate a cohesive answer. This entire workflow is visible via the app.py file.

Citation Information

Access the US History textbook (used in the database) for free at https://openstax.org/books/us-history/pages/1-introduction I do not claim any of their content as my own.

Other Notes

This demo was created to show how easily this model can be applied to various databases, with this large textbook serving as an example of a larger knowledge-base