Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion docs/reference/query-dsl/sparse-vector-query.asciidoc
Original file line number Diff line number Diff line change
Expand Up @@ -62,11 +62,14 @@ GET _search
(Required, string) The name of the field that contains the token-weight pairs to be searched against.

`inference_id`::
(Optional, string) The <<inference-apis,inference ID>> to use to convert the query text into token-weight pairs.
(Optional, string)
The <<inference-apis,inference ID>> to use to convert the query text into token-weight pairs.
It must be the same inference ID that was used to create the tokens from the input text.
Only one of `inference_id` and `query_vector` is allowed.
If `inference_id` is specified, `query` must also be specified.
If all queried fields are of type <<semantic-text, semantic_text>>, the inference ID associated with the `semantic_text` field will be inferred.
You can reference a `deployment_id` of a {ml} trained model deployment as an `inference_id`.
For example, if you download and deploy the ELSER model in the {ml-cap} trained models UI in {kib}, you can use the `deployment_id` of that deployment as the `inference_id`.

`query`::
(Optional, string) The query text you want to use for search.
Expand Down