Query a Vector Search Index

Query a Vector Search Index activity in the Databricks connector.

Project compatibility

Windows | Cross-platform

Overview

Description	API Method	API Path
Run a similarity search against a Databricks Vector Search index and return the matching rows.	POST	/vector-search/indexes/{index_name}/query

Input

Parameter	Description	Data Type
Index Name *	Full three-level name of the Vector Search index, for example catalog.schema.index.	string
Columns *	Columns to return for each match. For example, ["id", "title", "url"].	array
Query Text	Text query; for indexes with a Databricks-computed embedding. For example, How do I reset my password?.	string
Query Vector	Raw embedding vector; for self-managed embeddings. For example, [0.12, 0.84, -0.33].	array
Number of Results	Number of matches to return. For example, 10. Default: 10.	integer
Filters JSON	JSON filter expression applied before the search. For example, {"category": "support"}.	string
Query Type	Type of search to run against the index, for example ANN or HYBRID. Allowed values: ANN, HYBRID.	string
Score Threshold	Minimum similarity score a match must reach to be returned. For example, 0.7.	number

* Required parameter.

Output

Parameter	Description	Data Type
Result	Matches under result.data_array, ordered by score.	object
Manifest	Column schema of the result set.	object

Note:

You might see variations in the output depending on where you run the activity. In API workflows and Maestro Flow, a single response object containing all the fields is returned. In RPA workflows, not all fields are exposed, but you can still retrieve them from the exposed response object.