Azure AI Search Platform
Jump to navigation
Jump to search
A Azure AI Search Platform is a cloud search platform that can be used to create enterprise search solutions (that support information retrieval tasks and knowledge mining tasks).
- AKA: Azure Cognitive Search, Azure Search.
- Context:
- It can typically provide Full-Text Search Capability through Azure AI search indexes.
- It can typically enable Vector Search Capability through Azure AI search vector embedding storage.
- It can typically support Semantic Ranking through Azure AI search natural language processing.
- It can typically integrate with Azure AI Service for Azure AI search cognitive skill enhancement.
- It can typically perform Document Processing through Azure AI search content extraction pipeline.
- It can typically handle Multi-Modal Content through Azure AI search image processing and Azure AI search text analysis.
- ...
- It can often facilitate Retrieval Augmented Generation through Azure AI search RAG pattern implementation.
- It can often provide Faceted Navigation through Azure AI search filtering mechanisms.
- It can often implement Knowledge Mining through Azure AI search unstructured data processing.
- It can often support Multi-Lingual Search through Azure AI search language analysis for 56 languages.
- It can often enable Geo-Search Capability through Azure AI search location-based filtering.
- It can often enhance User Experience through Azure AI search autocomplete, Azure AI search autosuggest, and Azure AI search hit highlighting.
- ...
- It can range from being a Basic Azure AI Search to being an Advanced Azure AI Search, depending on its Azure AI search pricing tier.
- It can range from being a Text-Only Azure AI Search to being a Multi-Modal Azure AI Search, depending on its Azure AI search capability configuration.
- It can range from being a Simple Search Azure AI Search to being a ChatGPT-like Experience Azure AI Search, depending on its Azure AI search integration level with Azure OpenAI Service.
- ...
- It can integrate with Azure OpenAI Service for Azure AI search RAG implementation.
- It can connect to Azure Blob Storage for Azure AI search automatic crawling.
- It can support Azure Cognitive Services for Azure AI search enrichment pipeline.
- ...
- Examples:
- Azure AI Search Versions, such as:
- Azure AI Search (April 2025), featuring RAG Time Journey for Azure AI search RAG workflow demonstration and Azure AI search agentic search.
- Azure AI Search (March 2025), with Azure AI Search Service Upgrade for Azure AI search storage limit expansion without recreation.
- Azure AI Search (February 2025), supporting Increased Vector Dimension Limits up to 3072 for Azure AI search vector capability enhancement.
- Azure AI Search (November 2023), introducing Vector Search General Availability and renaming from Azure Cognitive Search.
- Azure Cognitive Search (October 2019-November 2023), renamed from Azure Search to reflect Azure AI search cognitive skill addition.
- Azure Search (2013-October 2019), the original service launched as part of Azure IaaS offering.
- Azure AI Search API Versions, such as:
- Azure AI Search API Version 2025-03-01-preview, supporting Azure AI search facet hierarchies, Azure AI search aggregations, and Azure AI search semantic ranker pre-release models.
- Azure AI Search API Version 2024-07-01, providing Azure AI search stable feature support for Azure AI search production implementation.
- Azure AI Search API Version 2023-11-01, introducing Azure AI search semantic ranking and Azure AI search vector search as generally available features.
- Azure AI Search Implementations, such as:
- Azure AI Search RAG Implementation for Azure AI search ChatGPT-like experience over corporate data.
- Azure AI Search Knowledge Mining Implementation for Azure AI search unstructured document processing.
- Azure AI Search Enterprise Search Implementation for Azure AI search company intranet and content discovery.
- ...
- Azure AI Search Versions, such as:
- Counter-Examples:
- AWS CloudSearch and Google Cloud Search, which are competitor cloud search services not integrated with Azure ecosystem.
- GCP Document AI Warehouse, which focuses on document processing but lacks Azure AI search comprehensive search capability.
- Azure OpenAI Service, which provides AI language model capabilities but not Azure AI search indexing functionality or Azure AI search retrieval capability.
- Traditional Database Services, which store structured data but lack Azure AI search cognitive skills and Azure AI search vector capability.
- See: Cloud Search Service, Enterprise Search Solution, Knowledge Mining Platform, Retrieval Augmented Generation System, Azure AI Service, Azure OpenAI Service.
References
2023
- chat
| Service | AI-Powered Features | Scalability | Ease of Implementation | Pricing | Integration with other services |
|---|---|---|---|---|---|
| Azure Cognitive Search | Yes | High | Moderate | Pay-as-you-go, tiered pricing | Strong integration with Microsoft Azure services |
2023
- https://learn.microsoft.com/en-us/training/modules/intro-to-azure-search/1-introduction
- QUOTE: Searching for information online has never been easier. However, it's still a challenge to find information from documents that aren't in a search index. For example, every day, people deal with unstructured, typed, image-based, or hand-written documents. Often, people must manually read through these documents to extract and record their insights in order to persist the found data. Now we have solutions that can automate information extraction.
Knowledge mining is the term used to describe solutions that involve extracting information from large volumes of often unstructured data. One of these knowledge mining solutions is Azure Cognitive Search, a cloud search service that has tools for building user-managed indexes. The indexes can be used for internal only use, or to enable searchable content on public-facing internet assets.
Importantly, Azure Cognitive Search can utilize the built-in AI capabilities of Azure Cognitive Services such as image processing, content extraction, and natural language processing to perform knowledge mining of documents. The product's AI capabilities makes it possible to index previously unsearchable documents and to extract and surface insights from large amounts of data quickly.
- Azure Cognitive Search comes with the following features:
- Data from any source: Azure Cognitive Search accepts data from any source provided in JSON format, with auto crawling support for selected data sources in Azure.
- Full text search and analysis: Azure Cognitive Search offers full text search capabilities supporting both simple query and full Lucene query syntax.
- AI powered search: Azure Cognitive Search has Cognitive AI capabilities built in for image and text analysis from raw content.
- Multi-lingual: Azure Cognitive Search offers linguistic analysis for 56 languages to intelligently handle phonetic matching or language-specific linguistics. Natural language processors available in Azure Cognitive Search are also used by Bing and Office.
- Geo-enabled: Azure Cognitive Search supports geo-search filtering based on proximity to a physical location.
- Configurable user experience: Azure Cognitive Search has several features to improve the user experience including autocomplete, autosuggest, pagination, and hit highlighting.
- QUOTE: Searching for information online has never been easier. However, it's still a challenge to find information from documents that aren't in a search index. For example, every day, people deal with unstructured, typed, image-based, or hand-written documents. Often, people must manually read through these documents to extract and record their insights in order to persist the found data. Now we have solutions that can automate information extraction.
2023
- (Wikipedia, 2023) ⇒ https://en.wikipedia.org/wiki/Azure_Cognitive_Search Retrieved:2023-4-30.
- Microsoft Azure Cognitive Search, formerly known as Azure Search, is a component of the Microsoft Azure Cloud Platform providing indexing and querying capabilities for data uploaded to Microsoft servers. The Search as a service framework is intended to provide developers with complex search capabilities for mobile and web development while hiding infrastructure requirements and search algorithm complexities. Azure Search is a recent addition to Microsoft's Infrastructure as a Service (IaaS) approach.
2023
- https://github.com/Azure-Samples/azure-search-openai-demo/
- QUOTE: ... This sample demonstrates a few approaches for creating ChatGPT-like experiences over your own data using the Retrieval Augmented Generation pattern. It uses Azure OpenAI Service to access the ChatGPT model (gpt-35-turbo), and Azure Cognitive Search for data indexing and retrieval.
The repo includes sample data so it's ready to try end to end. In this sample application we use a fictitious company called Contoso Electronics, and the experience allows its employees to ask questions about the benefits, internal policies, as well as job descriptions and roles. ...
- QUOTE: ... This sample demonstrates a few approaches for creating ChatGPT-like experiences over your own data using the Retrieval Augmented Generation pattern. It uses Azure OpenAI Service to access the ChatGPT model (gpt-35-turbo), and Azure Cognitive Search for data indexing and retrieval.