{"id":3320,"date":"2024-03-07T09:31:04","date_gmt":"2024-03-07T17:31:04","guid":{"rendered":"https:\/\/www.couchbase.com\/blog\/vector-search-on-mobile-beta\/"},"modified":"2024-03-07T09:31:04","modified_gmt":"2024-03-07T17:31:04","slug":"vector-search-on-mobile-beta","status":"publish","type":"post","link":"https:\/\/www.couchbase.com\/blog\/ko\/vector-search-on-mobile-beta\/","title":{"rendered":"Vector search is coming to Couchbase Lite, sign up for beta!"},"content":{"rendered":"

Mobile app developers know that a key to adoption is engaging users with an experience that is unique and tailored just for them. This means the app must display items and data in context with the user’s tastes, history, location, habits and other information to make a personal connection, the more it can provide this sort of experience the more engaged users become.<\/span><\/p>\n\n\n\n

Search is a ubiquitous means of user interaction in apps, and as such should always return personalized responses in order to make an impact. But searching only for specific words and phrases is not enough to produce accurate results in context. To make a personal connection you need semantic search for matches that are meaningful to the user. This is where vector search comes in.<\/span><\/p>\n\n\n\n

Vector search goes beyond simply finding matching words, it finds related information based on the meaning of a search query, making it the best option for providing relevant information that connects with users.<\/span><\/p>\n\n\n\n

Vector search also makes output from generative AI more personal by enabling Retrieval Augmented Generation, or \u201cRAG\u201d, where local vectorized data is passed along with prompts to provide better precision and context for LLM responses.<\/span><\/p>\n\n\n\n

In fact, vector search features are being added to nearly every cloud database, so how is Couchbase doing it differently? By offering vector search from cloud to edge.
\n<\/span><\/p>\n\n\n\n