# SEMANTICSEARCH The **SEMANTICSEARCH** workflow application performs a hybrid full-text and semantic search on requests, with customizable filters and scoring. It returns structured JSON results for use in process logic. ## Required parameters

Parameter	Type	Direction	Description
`QUERY`	TEXT	IN	The main search query (full-text and similarity)
`QUERY_DATA_<NAME>`	TEXT	IN	Query for a specific data field (e.g. `QUERY_DATA_TITLE`)
`RESULT`	TEXT	OUT	JSON string containing the search results

{% hint style="info" %} At least one of `QUERY` or `QUERY_DATA_` must be provided. {% endhint %} ## Optional parameters

Parameter	Type	Direction	Description
`REQUEST_ID`	NUMERIC	IN	The request number to filter on
`REQUEST_STATE`	TEXT	IN	Request state: `OPEN` or `CLOSED`
`REQUEST_SUBSTATE`	TEXT	IN	Substate: For `OPEN`, use `NOT_RUNNING_NOT_STARTED` or `RUNNING` For `CLOSED`, use `COMPLETED` or `ABORTED`
`REQUEST_CREATED_AT_FROM`	DATETIME	IN	Filter: request created at (from)
`REQUEST_CREATED_AT_TO`	DATETIME	IN	Filter: request created at (to)
`REQUEST_CLOSED_AT_FROM`	DATETIME	IN	Filter: request closed at (from)
`REQUEST_CLOSED_AT_TO`	DATETIME	IN	Filter: request closed at (to)
`REQUESTER_USERNAME`	TEXT	IN	Requester's username
`PROCESS_NAME`	TEXT	IN	Process name
`PROCESS_VERSION`	NUMERIC	IN	Process version
`QUERY_SCORE`	NUMERIC	IN	Score threshold for the main query (default: `0.5`); see Query scores below for more information
`QUERY_SCORE_DATA_<NAME>`	NUMERIC	IN	Score threshold for the specific data field query (e.g. `QUERY_SCORE_DATA_SUBJECT`); see Query scores below for more information
`SELECT_DATA_LIST`	TEXT	IN	Comma- or semicolon-separated list of data fields to include in the search result

{% hint style="info" %} `QUERY_SCORE_DATA_` is required if you have a `QUERY_DATA_` parameter. {% endhint %} #### Query scores * Query scores are applicable to semantic search only, not full-text search. * The default score of `0.5` is equivalent to a 50% similarity threshold. * For stricter matching, use a score closer to `1.0` (e.g. `0.75` for a 75% similarity threshold). * For looser matching, use a score closer to `0.0` (e.g. `0.25` for a 25% similarity threshold). This applies to both the `QUERY_SCORE` and the `QUERY_SCORE_` parameters. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.workflowgen.com/admin/10.0/workflow-applications/semanticsearch.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.