AnkiWeb addon 1399280435
Grades typed answers using OpenAI and immediately shows pop-up feedback with suggested ease and mnemonics, integrating into Anki's review flow.
Open on AnkiWeb GitHub Find alternatives
stale
| Min Anki | Max Anki | Updated |
|---|---|---|
| 2.1.1 | 25.02.4+ | 2025-05-10 |
Loading…
Turns Anki reviews into chat-based AI sessions that semantically grade typed answers, suggest difficulty ratings, and support follow-up questions using OpenAI or Gemini providers.
Scores typed flashcard answers with a 0–100% AI similarity grade, optional partial credit, automatic Again/Hard/Good/Easy selection, and OpenAI or Gemini support.
Grades written Anki answers using an LLM, retrieves supporting material via semantic RAG, offers tutor explanations, analytics, batch assessment, and optional interval suggestions.
Adds an in-card AI tutor for on-the-spot explanations, mnemonics, translations, image understanding, answer grading, and saved answers during review, using free or user-supplied models.
Lets you answer flashcards by typing, speaking, or handwriting, then has a chosen LLM grade the answer as correct, partly, or totally wrong and explain mistakes.
Semantically evaluates typed Anki answers using multiple AI providers, providing a 0–10 score, improvement tips, review suggestions, configurable prompts, and multilingual feedback.
Evaluates the learner's typed answer with OpenAI and shows immediate AI feedback in a pop-up.
Go to https://platform.openai.com and log in or sign up for an account. In the dashboard, open the “API Keys” section under your profile menu. Click “Create new secret key,” copy the generated key, finally add it to the add on’s configuration.
Evaluates the learner's typed answer with OpenAI and shows immediate AI feedback in a pop-up.
.ankiaddon release or package the add-on as described below..ankiaddon file.If you are developing or modifying the add-on:
# From the project root
zip -r answer_eval.ankiaddon __init__.py manifest.json config.json
manifest.json is at the root of the archive (not inside a folder).Edit config.json to set your OpenAI API key and model:
{
"openai_api_key": "sk-...",
"model": "gpt-4o-mini",
"field_name": "Back",
"temperature": 0.0
}
MIT License. See LICENSE for details.