Official Technical Resources: Microsoft (page 7)
Official Technical Resources · Microsoft: 312 entries in total; this page lists entries 91–105.
Add language analyzers to string fields in an Azure AI Search index
Configure multi-lingual lexical analysis for non-English text queries and indexes in Azure AI Search.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Retrieval-Augmented Generation (RAG) · Embedding · Vector Databases
Link last checked: 2026-09-24
Add scoring profiles to boost search scores
Boost search relevance scores for Azure AI Search results by adding scoring profiles to a search index.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Retrieval-Augmented Generation (RAG) · Embedding · Vector Databases
Link last checked: 2026-09-24
Relevance in keyword search (BM25 scoring)
Explains the concepts of BM25 relevance and scoring in Azure AI Search, and what a developer can do to customize the scoring result.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Retrieval-Augmented Generation (RAG) · Embedding · Vector Databases
Link last checked: 2026-09-24
Knowledge store in Azure AI Search
A knowledge store is enriched content created by an Azure AI Search skillset and saved to Azure Storage for use in other apps and non-search scenarios.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: AI Agent · Agent Frameworks
Link last checked: 2026-09-24
Knowledge store "projections" in Azure AI Search
Introduces projection concepts and best practices. If you're creating a knowledge store in Azure AI Search, projections determine the type, quantity, and composition of objects in Azure Storage.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Retrieval and Semantic Search · Retrieval-Augmented Generation (RAG) · Vector Databases
Link last checked: 2026-09-24
Shaping data for projection into a knowledge store
Define the data structures in a knowledge store by creating data shapes and passing them to a projection.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Retrieval and Semantic Search · Retrieval-Augmented Generation (RAG) · Vector Databases
Link last checked: 2026-09-24
OData language overview for $filter , $orderby , and $select in Azure AI Search
OData language overview for filters, select, and order-by for Azure AI Search keyword search.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Retrieval and Semantic Search · Retrieval-Augmented Generation (RAG) · Vector Databases
Link last checked: 2026-09-24
Retrieval-augmented generation (RAG) in Azure AI Search
Learn how Azure AI Search supports RAG patterns with agentic retrieval and classic hybrid search to ground LLM responses in your content. Get started today.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Retrieval-Augmented Generation (RAG) · Embedding · Vector Databases
Link last checked: 2026-09-24
Analyzers for text processing in Azure AI Search
Assign analyzers to searchable string fields in an index to replace default standard Lucene with custom, predefined or language-specific alternatives.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Retrieval-Augmented Generation (RAG) · Embedding · Vector Databases
Link last checked: 2026-09-24
Filters for keyword search in Azure AI Search
Filter by user security identity, language, geo-location, or numeric values to reduce search results on queries in a search index in Azure AI Search.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Retrieval and Semantic Search · Retrieval-Augmented Generation (RAG) · Vector Databases
Link last checked: 2026-09-24
Set up integrated vectorization in Azure AI Search using REST
Learn how to use the REST APIs to define an indexer pipeline that includes chunking and vectorization.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Retrieval and Semantic Search · Retrieval-Augmented Generation (RAG) · Vector Databases
Link last checked: 2026-09-24
Chunk and vectorize with the Document Layout skill
Chunk textual content by headings and semantically coherent fragments using the Document Layout skill, generate embeddings, and send the results to a searchable index.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Retrieval and Semantic Search · Retrieval-Augmented Generation (RAG) · Vector Databases
Link last checked: 2026-09-24
Chunk and vectorize content with the Azure Content Understanding skill
Use preview semantic chunking and AI-based image descriptions with the Azure Content Understanding skill to build an Azure AI Search index.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Retrieval and Semantic Search · Retrieval-Augmented Generation (RAG) · Vector Databases
Link last checked: 2026-09-24
OData $filter syntax in Azure AI Search
OData language reference and full syntax used for creating filter expressions in Azure AI Search queries.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Retrieval and Semantic Search · Retrieval-Augmented Generation (RAG) · Vector Databases
Link last checked: 2026-09-24
Understand how OData collection filters work in Azure AI Search
Learn the mechanics of how OData collection filters work in Azure AI Search queries, including limitations and behaviors unique to collections.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Retrieval and Semantic Search · Retrieval-Augmented Generation (RAG) · Vector Databases
Link last checked: 2026-09-24