AnkiWeb addon 2028823832
Generates local Ollama vector embeddings for Anki cards, stored in ChromaDB, enabling semantic natural-language searches via "vec:" queries that can combine with keyword filters.
Open on AnkiWeb GitHub Find alternatives
stale
| Min Anki | Max Anki | Updated |
|---|---|---|
| 2.1.1 | 23.09+ | 2025-11-20 |
Loading…
Enables semantic and keyword search across selected Anki notes, generating cited AI answers through local or cloud providers.
Enables natural-language semantic card search via Voyage AI embeddings, optional Claude reranking and smart search, plus duplicate finding, card actions, and clinical vignette/guideline review modes.
Adds a local AI panel in Anki's Browser that turns plain-English requests into Anki searches, expands synonyms, and finds matching cards privately.
Enables offline AI semantic and keyword hybrid card search on local CPU, with a browser semantic: prefix, a search dialog for previewing and suspending cards, and automatic model download.
Searches PDF or PPTX lecture slides against your Anki collection using local semantic embeddings, moves matched cards into decks, and uses Gemini to generate cloze cards for uncovered concepts.
Provides inline AI autocomplete and Cmd-K prompting via a local Ollama server, including natural-language browse queries and PDF-grounded card suggestions.
This anki addon creates vector embeddings for your cards, allowing you to search using natural language queries rather than keywords.
When you restart Anki after installing the add-on, a vector-database will be initialized for your deck. This process may take a few minute- you should see a loading dialog with a progress bar. From this point on, any changes to your deck will be automatically indexed.
To search the vector database, use the form "vec: [your query here]" in Anki's usual search bar. You can combine keyword searches with vector searches by putting the "vec" section at the end of the query: e.g. "keyword1 keyword2 vec: [natural language description]".
Download from ollama.ai and install.
Pull the embedding model:
ollama pull nomic-embed-text
There are three parameters that govern how AnkiVec operates, available in the add-on's configuration dialog:
This anki addon creates vector embeddings for your cards, allowing you to search using natural language queries rather than keywords.
When you restart Anki after installing the add-on, a vector-database will be initialized for your deck. This process may take a few minute- you should see a loading dialog with a progress bar. From this point on, any changes to your deck will be automatically indexed.
To search the vector database, use the form "vec: [your query here]" in Anki's usual search bar. You can combine keyword searches with vector searches by putting the "vec" section at the end of the query: e.g. "keyword1 keyword2 vec: [natural language description]".
Download from ollama.ai and install.
Pull the embedding model:
ollama pull nomic-embed-text
There are three parameters that govern how AnkiVec operates, available in the add-on's configuration dialog:
Other Platforms: Currently, only Mac OS is supported. Windows support should be straightforward if I can get my hands on a Windows machine. Linux support is more tricky, as the uv binary bundled with Anki will be installed in different places depending on your distribution. I need to investigate how Anki is distributed in different package managers.
Ordering by Relevance: Currently, Anki's search feature allows you to filter the cards you seen in the Browser, but not to order them by a specific relevance score. Implementing this as an add on might require obscene amounts of monkey patching, but I think it will be worth the effort.
Debugging Ollama: Ollama can be buggy. A small fraction of Anki notes cause Ollama to throw an error when generating embeddings. This is a known issue, and I'm working on figuring out what's going on.