At Inspire 2023, Microsoft today announced the public preview of Vector search in Azure Cognitive Search, a new capability for building applications powered by large language models. Using this new capability, developers can retrieve relevant information, analyze and understand the retrieved data, and generate responses or actions based on the LLM’s capabilities.
Unlike regular keyword matching search, Vector search results are based on the similarity of numerical representations of data, called vector embeddings. The integration of Vector search extends to other capabilities of Azure Cognitive Search. Vector search in Azure Cognitive Search offers the following capabilities:
- Build search-enabled, chat-based applications using the Azure OpenAI Service
- Convert images into vector representations using Azure AI Vision for accurate, relevant text-to-image and image-to-image search experiences
- Quickly and accurately retrieve relevant information from large datasets, to help automate processes and workflows
You can learn more about Vector Search in Azure Cognitive Search from the source link below.