A vector database stores and searches high-dimensional numerical representations such as embeddings. Instead of matching only exact fields or keywords, it can find items whose vectors are close according to a similarity measure. This supports semantic search, recommendations, image retrieval, duplicate detection, and retrieval-augmented generation. Specialized indexes make nearest-neighbor search practical across large collections, often trading a small amount of exactness for speed. A useful deployment also needs metadata filters, access controls, update and deletion handling, backups, and monitoring. Retrieval quality depends on the embedding model, chunking strategy, distance metric, index settings, and source data, so the database is one component of the system rather than an automatic knowledge solution.
Opera today introduced Neon, an AI-powered browser that can run tasks and navigate pages autonomously — aiming to shift web browsing from passive to “agentic.”
AI search startup Perplexity has reportedly raised $200 million at a $20 billion valuation, just two months after a $100 million round – signaling its rapid rise as a major rival to Google.