Maintained with ☕️ by
IcePanel logo

Public Preview: Vector search, a feature of Azure Cognitive Search

Share

Services

We're excited to announce that Vector search is now available in public preview on [Azure Cognitive Search](https://azure.microsoft.com/en-us/products/search/). The enterprise retrieval cloud service powers the next generation of LLM-based applications, as well as plugins for ChatGPT and Azure OpenAI service. With Vector search, Developers can store, index, and deliver search applications over vector representations of organizational data, also known as embeddings. Vector search supports a wide range of data types, such as text, images, audio, video, and graphs. Execute vector similarity queries using approximate nearest neighbor search. Find information that is semantically similar to search queries, even if the search terms are not exact matches. Azure Cognitive Search offers pure vector search and hybrid retrieval – as well as a sophisticated re-ranking system powered by Bing in a single integrated solution. Build applications to generate personalized responses in natural language, deliver product recommendations, detect fraud, identify data patterns, and more. Now Azure Cognitive Search is the go-to for Vector storage on Azure! Watch the [demo video](https://aka.ms/Vector%5FSearchSnackableVideo). * Features