Merge pull request #5863 from HeidiSteen/heidist-semantic

small edits to semantic docs

Author: prmerger-automator[bot]

articles/search/includes/quickstarts/semantic-ranker-csharp.md

@@ -357,7 +357,7 @@ Press Enter to continue to the next query...
 
 ### Output for a semantic query with captions
 
-This query adds captions with hit highlighting.
+Here are the results for the query that adds captions with hit highlighting.
 
 ```
 Caption: Chic hotel near the city. High-rise hotel in downtown, within walking distance to<em> theaters, </em>art galleries, restaurants and shops. Visit<em> Seattle Art Museum </em>by day, and then head over to<em> Benaroya Hall </em>to catch the evening's concert performance.
@@ -400,13 +400,13 @@ Press Enter to continue to the next query...
 
 ### Output for semantic answers
 
-In this final query, return semantic answers. Notice that we changed the query string for this example: 'what's a good hotel for people who like to read'.
+The final query returns a semantic answer. Notice that we changed the query string for this example: 'what's a good hotel for people who like to read'.
 
 Semantic ranker can produce an answer to a query string that has the characteristics of a question. The generated answer is extracted verbatim from your content so it won't include composed content like what you might expect from a chat completion model. If the semantic answer isn't useful for your scenario, you can omit `semantic_answers` from your code.
 
-To get a semantic answer, the question and answer must be closely aligned, and the model must find content that clearly answers the question. If potential answers fail to meet a confidence threshold, the model doesn't return an answer. For demonstration purposes, the question in this example is designed to get a response so that you can see the syntax.
+To produce a semantic answer, the question and answer must be closely aligned, and the model must find content that clearly answers the question. If potential answers fail to meet a confidence threshold, the model doesn't return an answer. For demonstration purposes, the question in this example is designed to get a response so that you can see the syntax.
 
-Recall that answers are verbatim content pulled from your index and might be missing phrases that a user would expect to see. To get composed answers as generated by a chat completion model, considering using a [RAG pattern](../../retrieval-augmented-generation-overview.md) or [agentic retrieval](../../search-agentic-retrieval-concept.md).
+Recall that answers are *verbatim content* pulled from your index and might be missing phrases that a user would expect to see. To get *composed answers* as generated by a chat completion model, considering using a [RAG pattern](../../retrieval-augmented-generation-overview.md) or [agentic retrieval](../../search-agentic-retrieval-concept.md).
 
 ```bash
 Extractive Answers:

articles/search/includes/quickstarts/semantic-ranker-intro.md

@@ -69,7 +69,7 @@ This quickstart assumes an existing index, modified to include a semantic config
 
    Your response should be similar to the following example, as scored by the default BM25 L1 ranker for full text search. For readability, the example selects just the "HotelName" "HotelId", and "Description" fields.
 
-   This query is a keyword search. The matches contain verbatim matches on the query terms (walking, distance, live, music) or a linguistic variant of one of the terms (walk, living).
+   This query is a keyword search. The results contain verbatim matches on the query terms (walking, distance, live, music) or on a linguistic variant (walk, living).
 
     ```json
     "@odata.count": 13,

articles/search/includes/quickstarts/semantic-ranker-python.md

@@ -261,7 +261,7 @@ In this final query, return semantic answers.
 
 Semantic ranker can produce an answer to a query string that has the characteristics of a question. The generated answer is extracted verbatim from your content so it won't include composed content like what you might expect from a chat completion model. If the semantic answer isn't useful for your scenario, you can omit `semantic_answers` from your code.
 
-To get a semantic answer, the question and answer must be closely aligned, and the model must find content that clearly answers the question. If potential answers fail to meet a confidence threshold, the model doesn't return an answer. For demonstration purposes, the question in this example is designed to get a response so that you can see the syntax.
+To produce a semantic answer, the question and answer must be closely aligned, and the model must find content that clearly answers the question. If potential answers fail to meet a confidence threshold, the model doesn't return an answer. For demonstration purposes, the question in this example is designed to get a response so that you can see the syntax.
 
 1. Add `answers` to the query.
 
@@ -297,7 +297,7 @@ To get a semantic answer, the question and answer must be closely aligned, and t
 
 1. Output should look similar to the following example, where the best answer to question is pulled from one of the results.
 
-    Recall that answers are verbatim content pulled from your index and might be missing phrases that a user would expect to see. To get composed answers as generated by a chat completion model, considering using a [RAG pattern](../../retrieval-augmented-generation-overview.md) or [agentic retrieval](../../search-agentic-retrieval-concept.md).
+    Recall that answers are *verbatim content* pulled from your index and might be missing phrases that a user would expect to see. To get *composed answers* as generated by a chat completion model, considering using a [RAG pattern](../../retrieval-augmented-generation-overview.md) or [agentic retrieval](../../search-agentic-retrieval-concept.md).
 
     ```bash
     Semantic Answer: Nature is Home on the beach. Explore the shore by day, and then come home to our shared living space to relax around a stone fireplace, sip something warm, and explore the<em> library </em>by night. Save up to 30 percent. Valid Now through the end of the year. Restrictions and blackouts may apply.

articles/search/includes/quickstarts/semantic-ranker-rest.md

@@ -285,7 +285,7 @@ In this final query, return semantic answers.
 
 Semantic ranker can produce an answer to a query string that has the characteristics of a question. The generated answer is extracted verbatim from your content so it won't include composed content like what you might expect from a chat completion model. If the semantic answer isn't useful for your scenario, you can omit `semantic_answers` from your code.
 
-To get a semantic answer, the question and answer must be closely aligned, and the model must find content that clearly answers the question. If potential answers fail to meet a confidence threshold, the model doesn't return an answer. For demonstration purposes, the question in this example is designed to get a response so that you can see the syntax.
+To produce a semantic answer, the question and answer must be closely aligned, and the model must find content that clearly answers the question. If potential answers fail to meet a confidence threshold, the model doesn't return an answer. For demonstration purposes, the question in this example is designed to get a response so that you can see the syntax.
 
 1. Formulate the request using a search string that asks a question.
 
@@ -306,7 +306,7 @@ To get a semantic answer, the question and answer must be closely aligned, and t
 
 1. Output consists of 41 results for the new query, with "@search.answers" for the question in the query about hotels for people who like to read.
 
-   Recall that answers are verbatim content pulled from your index and might be missing phrases that a user would expect to see. To get composed answers as generated by a chat completion model, considering using a [RAG pattern](../../retrieval-augmented-generation-overview.md) or [agentic retrieval](../../search-agentic-retrieval-concept.md).
+   Recall that answers are *verbatim content* pulled from your index and might be missing phrases that a user would expect to see. To get *composed answers* as generated by a chat completion model, considering using a [RAG pattern](../../retrieval-augmented-generation-overview.md) or [agentic retrieval](../../search-agentic-retrieval-concept.md).
 
    In this example, the answer is considered as a strong fit for the question.