Table of Contents
Auto Anki generates flash-cards from your lectures, which you can study with ease! Auto Anki builds on Anki, an intelligent flash-card tools for remembering things.
| Example QA from lecture | Example QA from lecture |
|---|---|
 |
 |
If you are someone who struggles to memorise concepts taught in class, or faces difficulty during revision, or if you are just too lethargic to take notes, then Auto-Anki is for you!
Auto Anki extracts important concepts from lectures, and frames questions based on it. It searches for the answers on the web and extracts the most relevant answers. Auto Anki combines with the powerful features of Anki that let you rate the difficulty level of every question to make it easy for you to memorize tough questions.
- You want to summarize everything in a lecture to flash cards, which you can then memorize.
- You already use Anki, but have to create the flash cards for lectures manually.
- You want to break down the lecture pdf into questions and answers.
- You want to create simple flashcards for easy memorisation and revision.
Auto_Anki_Demo.1.mp4
- Clone the repository ` git clone https://github.com/SmayanaReddy/auto_anki
- Install all requirements
pip install -r requirements.txt - Install project as Python package
pip install . - Clone Anki library
git clone https://github.com/kerrickstaley/genanki; cd genanki - Install Anki library
python setup.py install
We have generated documentation of the entire codebase using Pycco. You can find the documentation here.
If you are a developer, and want to update documentation:
- Install Pycco
pip install pycco - Use Pycco to generate docs.
pycco auto_anki/**/*.py -p
We would be happy to receive contributions! If you'd like to, please go through our CONTRIBUTING.md.
For any feedback, issues, or bug reports, please create an issue here.
- Currently, we are using command line interface to get the user input such as the path of the file to be uploaded or the name of the Anki deck. This is can be improved by building a GUI for the user input.
- As of now, our appliation is capable of processing only .pdf files. Other file types such as .ppt, .doc can be added in scope.
- A browser extension which will extract contents of the current webpage which the user is on and produce a new deck of anki cards based on the material.
- Currently Spacy is being used to extract noun phrases from each slide/page of the document. Then the high frequency noun phrases are calculated and used in the final search query. However this causes an issue when every slide has the document’s author name and email address listed. The author name is considered as a noun phrase, and since it appears on every slide has a high frequency, and thus appears on the final search query.
We have built this code on top of the stack from the project here.