What it does
Written by AI from the READMEChat with your library in a sidebar panel, answered from the paper passages most relevant to your question. Embeddings can run locally in Ollama or LM Studio while chat uses OpenAI-compatible cloud models or local ones.
Plain AI chat tends to invent answers about your papers. Retrieval sends only matching passages and shows what was sent. A cloud chat model needs an API key. Its licence is proprietary freeware, not open source.
What you'll need
Detected automatically- An API key for some featuresWorks without one: Ollama or LM Studio running locally (Ollama is the default provider). Needs a key (OpenAI): OpenAI provider (openaiApiKey).
- Or: a model on your own computerIt can use a local model such as Ollama
- Zotero 7, 8Not working with Zotero 10
Where your data goes
We found: only contacts services we could identify. 2 addresses in 2 groups.
defaultBaseUrl: "https://api.openai.com/v1",
Other plugins that do this
Matched on what they doFor the same job, work with Zotero 10 and graded B or better. Closest match first.
- AZotero RAGWorks with Zotero 10Actively maintained
Lets you ask questions about the papers in your library and get answers with links to sources, including page numbers and text anchors.
- ARetrieval IndexWorks with Zotero 10Actively maintained
Builds a page-aware passage index of your library and serves it over Zotero's local HTTP server.
How we pick these
By how closely what they do matches this plugin, using descriptions and the phrases people search with. Copies and forks of this plugin are listed under Forks and copies instead. No plugin pays to appear here.
Forks and copies
No forks listed.
The developer's response
Ratings and reviews
What people who use it say. This is separate from the grade, which is what the code does, and never changes it.
No ratings yet.