diff --git a/docs/reference/ml/ml-shared.asciidoc b/docs/reference/ml/ml-shared.asciidoc
index 4948db48664ed..af384c2c90011 100644
--- a/docs/reference/ml/ml-shared.asciidoc
+++ b/docs/reference/ml/ml-shared.asciidoc
@@ -1167,6 +1167,12 @@ tag::inference-config-text-embedding-size[]
 The number of dimensions in the embedding vector produced by the model.
 end::inference-config-text-embedding-size[]
 
+tag::inference-config-text-expansion[]
+The text expansion task works with sparse embedding models to transform an input sequence
+into a vector of weighted tokens. These embeddings capture semantic meanings and
+context and can be used in a <<sparse-vector,sparse vector>> field for powerful insights.
+end::inference-config-text-expansion[]
+
 tag::inference-config-text-similarity[]
 Text similarity takes an input sequence and compares it with another input sequence. This is commonly referred to
 as cross-encoding. This task is useful for ranking document text when comparing it to another provided text input.
diff --git a/docs/reference/ml/trained-models/apis/put-trained-models.asciidoc b/docs/reference/ml/trained-models/apis/put-trained-models.asciidoc
index 256c0d29f8d2f..ccd76b7095762 100644
--- a/docs/reference/ml/trained-models/apis/put-trained-models.asciidoc
+++ b/docs/reference/ml/trained-models/apis/put-trained-models.asciidoc
@@ -395,10 +395,10 @@ the model definition is not supplied.
 (Required, object)
 The default configuration for inference. This can be: `regression`,
 `classification`, `fill_mask`, `ner`, `question_answering`,
-`text_classification`, `text_embedding` or `zero_shot_classification`.
+`text_classification`, `text_embedding`, `text_expansion` or `zero_shot_classification`.
 If `regression` or `classification`, it must match the `target_type` of the
 underlying `definition.trained_model`. If `fill_mask`, `ner`,
-`question_answering`, `text_classification`, or `text_embedding`; the
+`question_answering`, `text_classification`, `text_embedding` or `text_expansion`; the
 `model_type` must be `pytorch`.
 +
 .Properties of `inference_config`
@@ -592,6 +592,25 @@ Refer to <<tokenization-properties>> to review the properties of the
 `tokenization` object.
 =====
 
+`text_expansion`:::
+(Object, optional)
+include::{es-ref-dir}/ml/ml-shared.asciidoc[tag=inference-config-text-expansion]
++
+.Properties of text_expansion inference
+[%collapsible%open]
+=====
+`results_field`::::
+(Optional, string)
+include::{es-ref-dir}/ml/ml-shared.asciidoc[tag=inference-config-results-field]
+
+`tokenization`::::
+(Optional, object)
+include::{es-ref-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization]
++
+Refer to <<tokenization-properties>> to review the properties of the
+`tokenization` object.
+=====
+
 `text_similarity`:::
 (Object, optional)
 include::{es-ref-dir}/ml/ml-shared.asciidoc[tag=inference-config-text-similarity]