[Backport 3.1] Fix typo in neural-sparse-with-pipelines.md

_vector-search/ai-search/neural-sparse-with-pipelines.md

@@ -518,7 +518,7 @@ GET /my-nlp-index/_mapping
 ```
 {% include copy-curl.html %}
 
-An object field named `passage_text_semantic_info` is automatically created. It includes a `ran_features` subfield for storing the embedding, along with additional text fields for capturing model metadata.
+An object field named `passage_text_semantic_info` is automatically created. It includes a `rank_features` subfield for storing the embedding, along with additional text fields for capturing model metadata.
 
 ### Step 3: Ingest documents into the index
 
@@ -698,4 +698,4 @@ To mitigate throttling exceptions, decrease the maximum number of connections sp
 
 - To learn how to use custom neural sparse search configurations, see [Using custom configurations for neural sparse search]({{site.url}}{{site.baseurl}}/vector-search/ai-search/neural-sparse-custom/). 
 - To learn more about improving retrieval time for neural sparse search, see [Accelerating neural sparse search]({{site.url}}{{site.baseurl}}/search-plugins/neural-sparse-search/#accelerating-neural-sparse-search).
-- To learn how to build AI search applications, explore our [tutorials]({{site.url}}{{site.baseurl}}/vector-search/tutorials/). 
+- To learn how to build AI search applications, explore our [tutorials]({{site.url}}{{site.baseurl}}/vector-search/tutorials/).