Google, Microsoft Expand AI-Driven Search Capabilities
Recent updates range from new functionality to store customer-managed keys for extra encryption of sensitive content, to an AI application template for building a RAG solution using Azure AI Search and Python.
Application scenarios listed by Microsoft for Azure AI Search include:
- Use it for traditional full text search and next-generation vector similarity search. Back your generative AI apps with information retrieval that leverages the strengths of both keyword and similarity search. Use both modalities to retrieve the most relevant results.
- Consolidate heterogeneous content into a user-defined and populated search index composed of vectors and text. You maintain ownership and control over what's searchable.
- Integrate data chunking and vectorization for generative AI and RAG apps.
- Apply granular access control at the document level.
- Offload indexing and query workloads onto a dedicated search service.
- Easily implement search-related features: relevance tuning, faceted navigation, filters (including geo-spatial search), synonym mapping, and autocomplete.
- Transform large undifferentiated text or image files, or application files stored in Azure Blob Storage or Azure Cosmos DB, into searchable chunks. This is achieved during indexing through AI skills that add external processing from Azure AI.
- Add linguistic or custom text analysis. If you have non-English content, Azure AI Search supports both Lucene analyzers and Microsoft's natural language processors. You can also configure analyzers to achieve specialized processing of raw content, such as filtering out diacritics, or recognizing and preserving patterns in strings.
In January the company introduced "Grounding with Bing Search" in Azure AI Agent Service. "In the ever-evolving landscape of artificial intelligence, staying current is paramount," Microsoft said. "We recently launched the "Grounding with Bing Search" knowledge tool as part of Azure AI Agent Service, and we're excited to offer developers a powerful new capability that bridges the gap between the temporal limitations of large language models (LLMs) and the dynamic, real-time data available on the web."
Reflecting the ever-changing AI/search landscape, Microsoft Search in Bing will no longer be available as of March 31, with Microsoft365.com, Office.com, and SharePoint Online becoming the new homes for Microsoft Search.
Microsoft Search is an enterprise search solution embedded across Microsoft 365 applications, enabling users to find information seamlessly within their organization's ecosystem. Unlike traditional internet search engines like Google Search or Bing, Microsoft Search focuses on workplace productivity by helping users locate e-mails, files, documents, people, conversations, and even knowledge from third-party applications connected through Microsoft Graph.
Different Approaches to AI-Driven Search
These moves reinforce the differing AI/search directions of Google and Microsoft, with the former looking to enhance its search-specific experiences in general, while Microsoft is focusing on infusing AI-assisted search throughout its software ecosystem.
Both companies aim to redefine search experiences with generative AI, but their strategies reflect different priorities, business models, and technological foundations. Here's a summary: