Talpa Search

What is Talpa Search?

Talpa Search is an AI-powered library search tool developed by LibraryThing. It uses AI technology from Claude AI and ChatGPT to understand plain-English queries, then verifies results against a database of over 30 million titles and 100 million editions. This cross-referencing is designed to prevent the AI from inventing books that don’t exist — a common problem with AI-generated search results.

A distinctive feature is cover-based search, powered by data users have contributed through LibraryThing’s CoverGuess game, letting you find books by cover color, design, genre, or subject.

Who created Talpa Search?

Talpa Search was developed by LibraryThing, the company behind LibraryThing.com and TinyCat, working together with ProQuest. It combines AI from Claude AI and ChatGPT with a large body of bibliographic data to deliver accurate, reliable search results.

What is Talpa Search used for?

• Natural language search: Find books, movies, and music by describing them — plot details, genres, or general descriptions — instead of exact titles.
• Cover search: Locate items based on cover color, description, genre, or subject, using community-contributed data from the CoverGuess game.
• Verified results: Answers are cross-referenced against real bibliographic data from libraries, publishers, and the LibraryThing community, so results are authoritative and the tool avoids hallucinating non-existent books.
• Library integration: Search results can be prioritized based on what’s actually in your library’s collection, and the tool can connect with library catalogs and holdings.
• Feedback loop: Users can report problems with search results, and features are updated based on user suggestions.

Pricing and availability

Libraries can subscribe to Talpa Search with no limits on usage. An open version is available for people not using it through a library, and booksellers or book-related companies can access it through an API.