The search startup Exa just launched Websets, a new search engine that aims to transform the chaotic web into a structured database, using large language model embedding technology to create the âperfect web search.â
ADVERTISING
The details
- Unlike traditional keyword-based search engines, Exa encodes the content of web pages into embeddings that capture meaning, rather than just matching terms.
- The company has processed about 1 billion web pages, prioritizing depth of understanding over breadth of trillions of pages of Google.
- Searches can take several minutes to process, but return highly specific lists of results spanning hundreds or thousands of entries.
- The platform excels at complex searches, such as finding specific types of companies, people or data sets, that traditional search engines struggle to find.
- Websets is Exaâs first consumer-facing product, with the company also providing back-end search services for enterprises.
Why does it matter
While others are racing to integrate AI models into classic search engines, Exa is rethinking search from the ground up. While currently slower than traditional search, this database-style approach could revolutionize how we find and organize information on the web, especially for uncovering deeper, more specific patterns on the web.
Read also
