The library is taking its first test drive with AI (Artificial Intelligence) by providing Talpa Book Search on our library catalog.  Talpa uses the power of new technologies, together with the know-how and authority of traditional library data, to find books and other media in the library’s collection.

Talpa is optimized for “What’s that book?” questions like:  “a book about a girl, a pig, and a spider.” 

It can even answer those “I know it had a blue cover” questions, like “a book with a little boy on the moon.”

Talpa is also great for subject, topic, author, or series searches, like “modern retellings of Greek mythology,” “nonfiction books about women in tech,” or “novels about WWII in France.”

How does it work?

Talpa uses AI technology in two ways:

First, Talpa queries large language models (from Claude AI and ChatGPT) for books and other media. Critically, every item is checked against true and authoritative bibliographic data, solving the problem of invented answers (called “hallucinations”) that such models can fall into.

Second, Talpa uses the natural-language abilities of large language models to parse and understand queries, which are then answered using traditional library data. Thus a search for “novels about World War II in France” is broken down into subjects and tags and answered with results from the library’s collection.

Talpa’s authoritative book data comes from Syndetics Unbound, Bowker and LibraryThing.

Surprisingly, Talpa’s ability to find books by their cover design isn’t powered by AI at all, but by the effort of thousands of book lovers who have played LibraryThing’s CoverGuess cover-tagging game since 2010!

What’s in a name? Talpa is named for the Latin word for “mole.”

The library is trialing this feature, so try it out today and let us know how you like it!