Skip to main content

AI Documents (Azure AI Search)

Feature NameAI Documents indexing using Azure AI Search
Feature IDCrestApps.OrchardCore.AI.Documents.AzureAI

Provides services to index AI Documents in Azure AI Search indexes.

Overview​

This module integrates Azure AI Search as an embedding and search provider for the AI Documents feature.

  • Embedding Support: Uses Azure AI Search for storing vector embeddings of document chunks
  • Search Integration: Retrieves relevant document chunks using Azure AI Search vector search

Getting Started​

  1. Enable the AI Documents indexing using Azure AI Search feature in Orchard Core admin.
  2. Configure an Azure AI Search connection and create an index via Search > Indexing.
  3. Select the index in Settings > Chat Interaction.

Operational notes​

  • Reopening and saving an AI Documents (Azure AI Search) index now keeps the built-in ChunkId, DocumentId, Content, FileName, ReferenceId, ReferenceType, ChunkIndex, and Embedding mappings stable instead of appending duplicate managed fields on each edit.
  • Existing duplicate managed mappings are normalized when Orchard loads the index profile, while any custom Azure AI Search fields you added remain intact.