Indexer

In the Ultra Transcenders books

AI-103

Each book explains Indexer in context, with comparison tables and the common traps.

Terms in this definition

• Azure AI Search

  Managed Azure service that builds indexes over your content and answers keyword, vector, hybrid and semantically ranked queries, optionally with AI enrichment. Retrieval-augmented generation, Foundry agents and knowledge mining all use it to fetch relevant content.

• Search data source

  Connection object in Azure AI Search pointing an indexer at its content, which must be a supported source: Blob, ADLS Gen2, Table Storage, Cosmos DB, Azure SQL, SQL Managed Instance or SQL Server on Azure VMs. One indexer, one data source.

• APPLY

  Evaluates a table-valued expression for every row on its left, inside FROM. Think of OUTER APPLY as a left outer join and CROSS APPLY as an inner join.

• AI enrichment

  Indexing-time process in Azure AI Search where skills such as OCR, key phrase extraction, entity recognition and image analysis turn raw content into fields that can be searched.

• Index

  Speeds up queries that filter on certain columns by keeping those columns sorted, with pointers back to each row; the price is more storage and slower writes.

• Agents (classic) API

  First-generation Foundry Agent Service API, based on threads, messages and runs. It is deprecated, replaced by conversations and responses, and retires on 31 March 2027.

Related terms

• Billable Foundry resource (skillset)

  Key or identity of a Foundry resource linked to a skillset, letting built-in Vision, Language and Translator skills process more than the free allowance of 20 documents per indexer per day; a single multi-service resource is enough for all of them.

• Document cracking

  The opening step of an indexer: source files or records are opened, and their text, metadata and, if requested, images are pulled out.

• Field mappings

  Indexer configuration passing a source field unchanged into an index field with another name or type. It is applied once documents are cracked and before any skillset runs.

• imageAction

  A parameter in indexer configuration. Setting it to generateNormalizedImages, with dataToExtract set to contentAndMetadata, pulls images out and normalises them into /document/normalized_images ready for OCR and image analysis.

• Indexer schedule

  A repeating interval for running an indexer, five minutes at the shortest, which allows a lengthy indexing job to continue from where it left off when change detection is turned on. It does not make indexing run in parallel.

• Integrated vectorization

  Azure AI Search capability that lets an indexer split documents into chunks using the Text Split skill and produce embeddings via a skill like Azure OpenAI Embedding; a corresponding vectorizer on the index turns search queries into vectors.

• OCR skill

  Azure AI Search built-in skill that relies on Azure Vision Read to pull printed and handwritten text out of /document/normalized_images/*. The indexer must have imageAction configured.

• Output field mappings

  Skills create nodes in the enriched document; this indexer setting routes them into index fields. It runs after the skillset, and enriched content is only indexed when mapped here.