Azure Data Source AI Search

Overview

You can use this Snap to enable search and retrieval across indexed datasets using Azure AI Search, allowing efficient query execution and intelligent information retrieval. It supports advanced configurations such as field mappings, semantic and vector-based query types, relevance strictness, and document filtering for precise and efficient search results.
Important: If you do not configure an account for the Azure Data Source AI Search Snap, it automatically uses the Azure system-assigned managed identity by default. This authentication method relies on the System Assigned Managed Identity type associated with your Azure application account.

Azure Data Source AI Search Overview

Prerequisites

  • A configured Azure AI Search service.
  • An index within the search service.

Limitations and known issues

None.

Snap views

Type Description Examples of upstream and downstream Snaps
Input This Snap supports a maximum of one document input view. Mapper
Output This Snap has at the most one document output view. The Snap provides the search results from the Azure AI Search index in the configured format. Mapper
Learn more about Error handling.

Snap settings

Legend:
  • Expression icon (): Allows using JavaScript syntax to access SnapLogic Expressions to set field values dynamically (if enabled). If disabled, you can provide a static value. Learn more.
  • SnapGPT (): Generates SnapLogic Expressions based on natural language using SnapGPT. Learn more.
  • Suggestion icon (): Populates a list of values dynamically based on your Snap configuration. You can select only one attribute at a time using the icon. Type into the field if it supports a comma-separated list of values.
  • Upload : Uploads files. Learn more.
Learn more about the icons in the Snap settings dialog.
Field/Field set Type Description
Label String

Required. Specify a unique name for the Snap. Modify this to be more appropriate, especially if more than one of the same Snaps is in the pipeline.

Default value: Azure Data Source AI Search

Example: Create customer support chatbots
Endpoint String/Expression

Required. Specify the absolute endpoint path for the Azure AI Search resource to use.

Default value: N/A

Example: https://my-search-service.search.windows.net
Index name String/Expression

Required. Specify the name of the index to use in the referenced Azure AI Search resource.

Default value: N/A

Example: hotels-sample-index
Advanced properties Configure additional settings to refine search behavior and relevance.
Field mapping Use this field set to customize field mapping behavior to use when interacting with the search index.
Field mapping options Dropdown list
Choose the option for the field mapping to use for the Azure AI Search resource. Available options include:
  • content_fields: Fields in the index that should be identified as content.
  • vector_fields: Fields that store vector data.
  • content_fields_separator: A pattern used to separate content fields. Default value is \n.
  • title_field: The field in the index to be used as a title.
  • url_field: The field in the index to be used as a URL..

Default value: content_fields

Example: title_field
Field mapping value String/Expression

Specify the field mapping value to use when interacting with the search index.

Important: Field mapping value must be a string or an array of strings.

Default value: N/A

Example: HotelName
Filter String/Expression

Specify the search filter to narrow down the search results based on conditions applied to index fields. Learn more.

Default value: N/A

Example: rating ge 4 and category eq 'luxury'
In scope Checkbox/Expression

Select this checkbox to restrict queries to use only indexed data for search results.

Default status: Selected
Query type Dropdown list

Choose the query type to use with Azure AI Search. Available options include:

  • simple: Uses the default simple query parser.
  • semantic: Uses the semantic query parser for enhanced semantic modeling.
  • vector: Performs vector-based search on computed data.
  • vector_simple_hybrid: Combines the simple query method with vector data.
  • vector_semantic_hybrid: Combines semantic search with vector data querying.
Note: If you select vector-related query type, configure embedding dependency in the Azure OpenAI Chat Completions Snap.

Default value: simple

Example: vector
Role information String/Expression

Specify the instructions for the model on how to behave, the context to reference, and the response formatting. You can also choose to specify the assistant's personality.

Default value: N/A

Example: Owner
Semantic configuration String/Expression

Specify the semantic configurations for the query. Learn more.

Important: This field is required when the Query type is either semantic or vector_semantic_hybrid.

Default value: N/A

Example: semantic01
Strictness Integer/Expression

Specify the strictness of the search relevance filtering. Higher strictness increases precision but reduces recall.

Default value: 3

Example: 5
Top-N documents Integer/Expression

Specify the maximum number of documents to retrieve for the configured query.

Default value: 5

Example: 10
Snap execution Dropdown list
Choose one of the three modes in which the Snap executes. Available options are:
  • Validate & Execute: Performs limited execution of the Snap and generates a data preview during pipeline validation. Subsequently, performs full execution of the Snap (unlimited records) during pipeline runtime.
  • Execute only: Performs full execution of the Snap during pipeline execution without generating preview data.
  • Disabled: Disables the Snap and all Snaps that are downstream from it.

Default value: Validate & Execute

Example: Execute only

Examples