Skip to content

SciPhi-AI/library-of-phi

Repository files navigation

Library of Phi

The Library of Phi is on a mission to democratize access to high-quality textbooks.

We use AI-driven methods, processing openly accessible syllabi from MIT OCW and, soon, other sources. We then apply retrieval-augmented-generation (RAG) over Wikipedia to attempt to ground the textbooks in fact. All textbooks in this repository are generated using GPT-3.5 and GPT-4.

Getting Started & Support

  • Engage with our active Discord community for discussions, troubleshooting, and collaboration.

  • For specialized support or collaboration inquiries, feel free to reach out directly.

Library of Phi Generation

  1. Scrape MIT OCW Course Webpages.
  2. Extract Syllabi.
  3. Formulate Table of Contents.
  4. Craft Textbooks.

Powered By


Screenshot 2023-10-03 at 3 14 50 PM

GPT-4 w/ RAG over WIKI

systems engineering

systems design

computational science and engineering

numerical simulation

computational modeling and simulation

systems optimization

environmental engineering

environmental management

aquatic sciences and water quality control

hydrodynamics and coastal engineering

hydrology and water resource systems

mechanical engineering

fluid mechanics

mechanical design

solid mechanics

anthropology

social anthropology

ethnography

cultural anthropology

chemistry

physical chemistry

analytical chemistry

inorganic chemistry

electrical engineering

electronics

electric power

literature

academic writing

ocean engineering

hydrodynamics

computer science

human-computer interfaces

GPT-4 Full Synthetic (Use with caution)

mechanical engineering

fluid mechanics

electrical engineering

electronics

systems engineering

computational science and engineering

systems design

numerical simulation

environmental engineering

aquatic sciences and water quality control

hydrodynamics and coastal engineering

hydrology and water resource systems

GPT-3.5-turbo w/ RAG

There are many more textbooks which were generated with GPT-3.5-turbo than GPT-4 (~240 vs 60). These textbooks are not quite of the same quality, but they are much less expensive to produce. Please use them if a GPT-4 based source is not available.

License

MIT OpenCourseWare Materials Citation:

The material used in this work used input from Massachusetts Institute of Technology's OpenCourseWare (MIT OCW) initiative, and must be used in compliance with the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) License.

Citation: Title of the specific material, MIT OpenCourseWare, [Direct Link to the Material on OCW]. Licensed under CC BY-NC-SA 4.0. To view a copy of this license, visit [https://creativecommons.org/licenses/by-nc-sa/4.0/].

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published