Generate flashcards using large language models.
Explore the docs »
View Demo
·
Report Bug
·
Request Feature
Table of Contents
Anki is great, but creating notes can be time-consuming. AutoAnki uses GPT-3 to automatically generate flashcards from local files and urls. It uses textract to extract text from PDFs, word documents, even images (through OCR), and other file types. We use the OpenAI API to generate notes from the text, and AnkiConnect to add the notes to your Anki deck.
At first glance, this is a bad idea because creating notes is an important part of learning the material. So we recommend you use the --interactive mode to manually filter/edit notes before importing them. This way, you can still benefit from the automatic generation of notes, with room for personalization.
This is an example of how you may give instructions on setting up your project locally. To get a local copy up and running follow these simple example steps.
-
Get an API Key at https://openai.com
-
Clone the repo
git clone https://github.com/jqhoogland/autoanki.git
-
Install Python packages
# Install dependencies for textract brew cask install xquartz brew install poppler antiword unrtf tesseract swig # Install other dependencies pip install -r requirements.txt
-
Open Anki on your computer and make sure you have AnkiConnect installed.
-
Use the shell script
python autoanki/shell.py path/to/file.txt python autoanki/shell.py https://example.com/file.txt
Use
--helpfor a list of arguments.
- Add
--interactiveflag to allow user to manually approve or reject suggested notes.
See the open issues for a full list of proposed features (and known issues).
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Distributed under the MIT License. See LICENSE.txt for more information.
Jesse Hoogland - @hoogland_jesse - jesse@jessehoogland.com
Project Link: https://github.com/jqhoogland/autoanki