@@ -265,7 +265,7 @@ print(f"Documents uploaded to index '{index_name}'")
 
 A knowledge source is a reusable reference to source data. The following code creates a knowledge source that targets the index you previously created.
 
-`source_data_fields` specifies which index fields are included in citation references. Our example includes only human-readable fields to avoid lengthy, uninterpretable embeddings in responses.
+`source_data_fields` specifies which index fields are included in citation references. This example includes only human-readable fields to avoid lengthy, uninterpretable embeddings in responses.
 
 For more information about this step, see [Create a search index knowledge source](agentic-knowledge-source-how-to-search-index.md).
 

@@ -4,7 +4,9 @@ author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 11/14/2025
+ms.date: 01/14/2026
+ms.custom: dev-focus
+ai-usage: ai-assisted
 ---
 
 [!INCLUDE [Feature preview](../previews/preview-generic.md)]
@@ -486,70 +488,7 @@ Reference Type: KnowledgeBaseSearchIndexReference
   "SourceData": {},
   "RerankerScore": 2.6344998
 }
-Reference Type: KnowledgeBaseSearchIndexReference
-{
-  "DocKey": "earth_at_night_508_page_194_verbalized",
-  "Id": "1",
-  "ActivitySource": 3,
-  "SourceData": {},
-  "RerankerScore": 2.630955
-}
-Reference Type: KnowledgeBaseSearchIndexReference
-{
-  "DocKey": "earth_at_night_508_page_105_verbalized",
-  "Id": "3",
-  "ActivitySource": 2,
-  "SourceData": {},
-  "RerankerScore": 2.5884187
-}
-Reference Type: KnowledgeBaseSearchIndexReference
-{
-  "DocKey": "earth_at_night_508_page_189_verbalized",
-  "Id": "4",
-  "ActivitySource": 3,
-  "SourceData": {},
-  "RerankerScore": 2.465418
-}
-Reference Type: KnowledgeBaseSearchIndexReference
-{
-  "DocKey": "earth_at_night_508_page_193_verbalized",
-  "Id": "6",
-  "ActivitySource": 3,
-  "SourceData": {},
-  "RerankerScore": 2.4560246
-}
-Reference Type: KnowledgeBaseSearchIndexReference
-{
-  "DocKey": "earth_at_night_508_page_174_verbalized",
-  "Id": "2",
-  "ActivitySource": 1,
-  "SourceData": {},
-  "RerankerScore": 2.3254027
-}
-Reference Type: KnowledgeBaseSearchIndexReference
-{
-  "DocKey": "earth_at_night_508_page_176_verbalized",
-  "Id": "5",
-  "ActivitySource": 1,
-  "SourceData": {},
-  "RerankerScore": 2.257256
-}
-Reference Type: KnowledgeBaseSearchIndexReference
-{
-  "DocKey": "earth_at_night_508_page_177_verbalized",
-  "Id": "7",
-  "ActivitySource": 1,
-  "SourceData": {},
-  "RerankerScore": 2.1968744
-}
-Reference Type: KnowledgeBaseSearchIndexReference
-{
-  "DocKey": "earth_at_night_508_page_125_verbalized",
-  "Id": "8",
-  "ActivitySource": 2,
-  "SourceData": {},
-  "RerankerScore": 2.086579
-}
+... // Trimmed for brevity
 Response:
 ... // Trimmed for brevity
 Activity:
@@ -575,7 +514,7 @@ Now that you've run the code, let's break down the key steps:
 
 ### Create a search index
 
-In Azure AI Search, an index is a structured collection of data. The following code defines an index named `earth-at-night`, which you previously specified using the `indexName` variable.
+In Azure AI Search, an index is a structured collection of data. The following code defines an index named `earth-at-night`.
 
 The index schema contains fields for document identification and page content, embeddings, and numbers. The schema also includes configurations for semantic ranking and vector search, which uses your `text-embedding-3-large` deployment to vectorize text and match documents based on semantic or conceptual similarity.
 
@@ -652,6 +591,8 @@ await indexClient.CreateOrUpdateIndexAsync(index);
 Console.WriteLine($"Index '{indexName}' created or updated successfully.");
 ```
 
+Reference: [SearchField](/dotnet/api/azure.search.documents.indexes.models.searchfield), [SimpleField](/dotnet/api/azure.search.documents.indexes.models.simplefield), [VectorSearch](/dotnet/api/azure.search.documents.indexes.models.vectorsearch), [SemanticSearch](/dotnet/api/azure.search.documents.indexes.models.semanticsearch), [SearchIndex](/dotnet/api/azure.search.documents.indexes.models.searchindex), [SearchIndexClient](/dotnet/api/azure.search.documents.indexes.searchindexclient)
+
 ### Upload documents to the index
 
 Currently, the `earth-at-night` index is empty. The following code populates the index with JSON documents from [NASA's Earth at Night e-book](https://raw.githubusercontent.com/Azure-Samples/azure-search-sample-data/refs/heads/main/nasa-e-book/earth-at-night-json/documents.json). As required by Azure AI Search, each document conforms to the fields and data types defined in the index schema.
@@ -678,11 +619,13 @@ await searchIndexingBufferedSender.FlushAsync();
 Console.WriteLine($"Documents uploaded to index '{indexName}' successfully.");
 ```
 
+Reference: [SearchClient](/dotnet/api/azure.search.documents.searchclient), [SearchIndexingBufferedSender](/dotnet/api/azure.search.documents.searchindexingbufferedsender-1)
+
 ### Create a knowledge source
 
 A knowledge source is a reusable reference to source data. The following code defines a knowledge source named `earth-knowledge-source` that targets the `earth-at-night` index.
 
-`SourceDataFields` specifies which index fields are included in citation references. Our example includes only human-readable fields to avoid lengthy, uninterpretable embeddings in responses.
+`SourceDataFields` specifies which index fields are included in citation references. This example includes only human-readable fields to avoid lengthy, uninterpretable embeddings in responses.
 
 ```csharp
 // Create a knowledge source
@@ -698,9 +641,11 @@ await indexClient.CreateOrUpdateKnowledgeSourceAsync(indexKnowledgeSource);
 Console.WriteLine($"Knowledge source '{knowledgeSourceName}' created or updated successfully.");
 ```
 
+Reference: [SearchIndexKnowledgeSource](/dotnet/api/azure.search.documents.indexes.models.searchindexknowledgesource)
+
 ### Create a knowledge base
 
-To target `earth-knowledge-source` and your `gpt-5-mini` deployment at query time, you need a knowledge base. The following code defines a knowledge base named `earth-knowledge-base`, which you previously specified using the `knowledgeBaseName` variable.
+To target `earth-knowledge-source` and your `gpt-5-mini` deployment at query time, you need a knowledge base. The following code defines a knowledge base named `earth-knowledge-base`.
 
 `OutputMode` is set to `AnswerSynthesis`, enabling natural-language answers that cite the retrieved documents and follow the provided `AnswerInstructions`.
 
@@ -730,6 +675,8 @@ await indexClient.CreateOrUpdateKnowledgeBaseAsync(knowledgeBase);
 Console.WriteLine($"Knowledge base '{knowledgeBaseName}' created or updated successfully.");
 ```
 
+Reference: [KnowledgeBaseAzureOpenAIModel](/dotnet/api/azure.search.documents.indexes.models.knowledgebaseazureopenaimodel), [KnowledgeBase](/dotnet/api/azure.search.documents.indexes.models.knowledgebase)
+
 ### Set up messages
 
 Messages are the input for the retrieval route and contain the conversation history. Each message includes a role that indicates its origin, such as `system` or `user`, and content in natural language. The LLM you use determines which roles are valid.
@@ -791,6 +738,8 @@ messages.Add(new Dictionary<string, string>
 });
 ```
 
+Reference: [KnowledgeBaseRetrievalClient](/dotnet/api/azure.search.documents.knowledgebases.knowledgebaseretrievalclient?view=azure-dotnet-preview&preserve-view=true), [KnowledgeBaseRetrievalRequest](/dotnet/api/azure.search.documents.knowledgebases.models.knowledgebaseretrievalrequest?view=azure-dotnet-preview&preserve-view=true)
+
 #### Review the response, activity, and references
 
 The following code displays the response, activity, and references from the retrieval pipeline, where:

@@ -11,7 +11,7 @@ ms.date: 11/05/2025
 
 In this quickstart, you use [agentic retrieval](../../agentic-retrieval-overview.md) to create a conversational search experience powered by large language models (LLMs) and your proprietary data. Agentic retrieval breaks down complex user queries into subqueries, runs the subqueries in parallel, and extracts grounding data from documents indexed in Azure AI Search. The output is intended for integration with agentic and custom chat solutions.
 
-Although you can provide your own data, this quickstart uses [sample JSON documents](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/nasa-e-book/earth-at-night-json) from NASA's Earth at Night e-book. The documents describe general science topics and images of Earth at night as observed from space.
+Although you can use your own data, this quickstart uses [sample JSON documents](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/nasa-e-book/earth-at-night-json) from NASA's Earth at Night e-book. The documents describe general science topics and images of Earth at night as observed from space.
 
 > [!TIP]
 > The Java version of this quickstart uses the 2025-05-01-preview REST API version, which uses the previous "knowledge agent" terminology and doesn't support the latest features available in the 2025-11-01-preview. To use these features, see the C#, Python, or REST version.

@@ -4,7 +4,9 @@ author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 12/19/2025
+ms.date: 01/14/2026
+ms.custom: dev-focus
+ai-usage: ai-assisted
 ---
 
 [!INCLUDE [Feature preview](../previews/preview-generic.md)]
@@ -539,19 +541,7 @@ Reference Type: searchIndex
   "rerankerScore": 2.6692379,
   "docKey": "earth_at_night_508_page_174_verbalized"
 }
-Reference Type: searchIndex
-{
-  "type": "searchIndex",
-  "id": "1",
-  "activitySource": 3,
-  "sourceData": {
-    "id": "earth_at_night_508_page_186_verbalized",
-    "page_chunk": "## Appendix A\n\n### NASA's Black Marble Product Suite\n\nNASA's Black Marble product suite provides estimates of daily nighttime lights and other intrinsic surface optical properties of Earth at night. The product is based on the Day/Night Band (DNB) sensor of the Visible Infrared Imaging Radiometer Suite (VIIRS) instrument onboard the Suomi National Polar-orbiting Partnership (NPP) satellite. The VIIRS DNB is a highly sensitive, low-light sensor capable of measuring daily global nighttime light emissions and reflections, allowing users to identify sources and intensities of these artificial lights, and monitor changes over a period of time. Like any optical sensor, the principal challenge in using VIIRS DNB data is to account for variations in light captured by the sensor. Certainly, there are variations in the sources and intensity of anthropogenic light due to changing human processes like urbanization, oil and gas production, nighttime commercial fishing, and infrastructure development. However, these processes can only be studied when other naturally-occurring factors that influence nighttime lights are removed. For example, variations in lunar lighting due to consistent changes in Moon phase cause fluctuations in the amount of light shining on Earth. Similarly, land-cover dynamics (e.g., seasonal vegetation, snow and ice cover), as well as atmospheric conditions (e.g., clouds, aerosols, airglow, and auroras), influence the intensity of the light captured by the sensor as it travels over various parts of the world.\n\nTo realize the full potential of the VIIRS DNB time series record for nighttime lights applications, NASA's Black Marble product suite was developed, building on a history of 20 years of research on how light changes when it reflects off of surfaces with different angular and spectral properties. Through complex modeling, scientists can now predict how moonlight, snow, vegetation, terrain, and clouds impact the lights we see from space, allowing for more accurate assessments of human and environmental activity at night.\n\n<!-- PageFooter=\"170 Earth at Night\" -->",
-    "page_number": 186
-  },
-  "rerankerScore": 2.5997617,
-  "docKey": "earth_at_night_508_page_186_verbalized"
-}
+... // Trimmed for brevity
 
 ❓ Follow-up question: How do I find lava at night?
 
@@ -676,6 +666,8 @@ const searchClient = new SearchClient(process.env.AZURE_SEARCH_ENDPOINT, 'earth_
 await searchIndexClient.createOrUpdateIndex(index);
 ```
 
+Reference: [SearchField](/javascript/api/@azure/search-documents/searchfield), [VectorSearch](/javascript/api/@azure/search-documents/vectorsearch), [SemanticSearch](/javascript/api/@azure/search-documents/semanticsearch), [SearchIndex](/javascript/api/@azure/search-documents/searchindex), [SearchIndexClient](/javascript/api/@azure/search-documents/searchindexclient), [SearchClient](/javascript/api/@azure/search-documents/searchclient), [DefaultAzureCredential](/javascript/api/@azure/identity/defaultazurecredential)
+
 ### Upload documents to the index
 
 Currently, the `earth-at-night` index is empty. The following code populates the index with JSON documents from [NASA's Earth at Night e-book](https://raw.githubusercontent.com/Azure-Samples/azure-search-sample-data/refs/heads/main/nasa-e-book/earth-at-night-json/documents.json). As required by Azure AI Search, each document conforms to the fields and data types defined in the index schema.
@@ -716,11 +708,13 @@ while (count !== documents.length) {
 console.log(`✓ All ${documents.length} documents indexed successfully!`);
 ```
 
+Reference: [SearchIndexingBufferedSender](/javascript/api/@azure/search-documents/searchindexingbufferedsender)
+
 ### Create a knowledge source
 
 A knowledge source is a reusable reference to source data. The following code defines a knowledge source named `earth-knowledge-source` that targets the `earth-at-night` index.
 
-`source_data_fields` specifies which index fields are included in citation references. Our example includes only human-readable fields to avoid lengthy, uninterpretable embeddings in responses.
+`source_data_fields` specifies which index fields are included in citation references. This example includes only human-readable fields to avoid lengthy, uninterpretable embeddings in responses.
 
 ```javascript
 await searchIndexClient.createKnowledgeSource({
@@ -739,6 +733,8 @@ await searchIndexClient.createKnowledgeSource({
 console.log(`✅ Knowledge source 'earth-knowledge-source' created successfully.`);
 ```
 
+Reference: [SearchIndexKnowledgeSource](/javascript/api/@azure/search-documents/searchindexknowledgesource)
+
 ### Create a knowledge base
 
 To target `earth-knowledge-source` and your `gpt-5-mini` deployment at query time, you need a knowledge base. The following code defines a knowledge base named `earth-knowledge-base`.
@@ -770,6 +766,8 @@ await searchIndexClient.createKnowledgeBase({
 console.log(`✅ Knowledge base 'earth-knowledge-base' created successfully.`);
 ```
 
+Reference: [KnowledgeBase](/javascript/api/@azure/search-documents/knowledgebase)
+
 ### Run the retrieval pipeline
 
 You're ready to run agentic retrieval. The following code sends a two-part user query to `earth-knowledge-base`, which:
@@ -818,6 +816,8 @@ const retrievalRequest = {
 const result = await knowledgeRetrievalClient.retrieveKnowledge(retrievalRequest);
 ```
 
+Reference: [KnowledgeRetrievalClient](/javascript/api/@azure/search-documents/knowledgeretrievalclient), [KnowledgeBaseRetrievalRequest](/javascript/api/@azure/search-documents/knowledgebaseretrievalrequest)
+
 ### Review the response, activity, and references
 
 The following code displays the response, activity, and references from the retrieval pipeline, where:

@@ -4,7 +4,9 @@ author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 11/10/2025
+ms.date: 01/14/2026
+ms.custom: dev-focus
+ai-usage: ai-assisted
 ---
 
 [!INCLUDE [Feature preview](../previews/preview-generic.md)]
@@ -428,115 +430,7 @@ references_content:
     "reranker_score": 2.722408,
     "doc_key": "earth_at_night_508_page_105_verbalized"
   },
-  {
-    "type": "searchIndex",
-    "id": "3",
-    "activity_source": 2,
-    "source_data": {
-      "id": "earth_at_night_508_page_104_verbalized",
-      "page_chunk": "<!-- PageHeader=\"Urban Structure\" -->\n\n### Location of Phoenix, Arizona\n\nThe image depicts a globe highlighting the location of Phoenix, Arizona, in the southwestern United States, marked with a blue pinpoint on the map of North America. Phoenix is situated in the central part of Arizona, which is in the southwestern region of the United States.\n\n---\n\n### Grid of City Blocks-Phoenix, Arizona\n\nLike many large urban areas of the central and western United States, the Phoenix metropolitan area is laid out along a regular grid of city blocks and streets. While visible during the day, this grid is most evident at night, when the pattern of street lighting is clearly visible from the low-Earth-orbit vantage point of the ISS.\n\nThis astronaut photograph, taken on March 16, 2013, includes parts of several cities in the metropolitan area, including Phoenix (image right), Glendale (center), and Peoria (left). While the major street grid is oriented north-south, the northwest-southeast oriented Grand Avenue cuts across the three cities at image center. Grand Avenue is a major transportation corridor through the western metropolitan area; the lighting patterns of large industrial and commercial properties are visible along its length. Other brightly lit properties include large shopping centers, strip malls, and gas stations, which tend to be located at the intersections of north-south and east-west trending streets.\n\nThe urban grid encourages growth outwards along a city's borders by providing optimal access to new real estate. Fueled by the adoption of widespread personal automobile use during the twentieth century, the Phoenix metropolitan area today includes 25 other municipalities (many of them largely suburban and residential) linked by a network of surface streets and freeways.\n\nWhile much of the land area highlighted in this image is urbanized, there are several noticeably dark areas. The Phoenix Mountains are largely public parks and recreational land. To the west, agricultural fields provide a sharp contrast to the lit streets of residential developments. The Salt River channel appears as a dark ribbon within the urban grid.\n\n\n<!-- PageFooter=\"Earth at Night\" -->\n<!-- PageNumber=\"88\" -->",
-      "page_number": 104
-    },
-    "reranker_score": 2.6451337,
-    "doc_key": "earth_at_night_508_page_104_verbalized"
-  },
-  {
-    "type": "searchIndex",
-    "id": "1",
-    "activity_source": 1,
-    "source_data": {
-      "id": "earth_at_night_508_page_174_verbalized",
-      "page_chunk": "<!-- PageHeader=\"Holiday Lights\" -->\n\n## Holiday Lights\n\n### Bursting with Holiday Energy-United States\n\nNASA researchers found that nighttime lights in the United States shine 20 to 50 percent brighter in December due to holiday light displays and other activities during Christmas and New Year's when compared to light output during the rest of the year.\n\nThe next five maps (see also pages 161-163), created using data from the VIIRS DNB on the Suomi NPP satellite, show changes in lighting intensity and location around many major cities, comparing the nighttime light signals from December 2012 and beyond.\n\n---\n\n#### Figure 1. Location Overview\n\nA map of the western hemisphere with a marker indicating the mid-Atlantic region of the eastern United States, where the study of holiday lighting intensity was focused.\n\n---\n\n#### Figure 2. Holiday Lighting Intensity: Mid-Atlantic United States (2012\u20132014)\n\nA map showing Maryland, New Jersey, Delaware, Virginia, West Virginia, Ohio, Kentucky, Tennessee, North Carolina, South Carolina, and surrounding areas. Major cities labeled include Washington, D.C., Richmond, Norfolk, and Raleigh.\n\nThe map uses colors to indicate changes in holiday nighttime lighting intensity between 2012 and 2014:\n\n- **Green/bright areas**: More holiday lighting (areas shining 20\u201350% brighter in December).\n- **Yellow areas**: No change in lighting.\n- **Dim/grey areas**: Less holiday lighting.\n\nKey observations from the map:\n\n- The Washington, D.C. metropolitan area shows significant increases in lighting during the holidays, extending into Maryland and Virginia.\n- Urban centers such as Richmond (Virginia), Norfolk (Virginia), Raleigh (North Carolina), and clusters in Tennessee and South Carolina also experience notable increases in light intensity during December.\n- Rural areas and the interiors of West Virginia, Kentucky, and North Carolina show little change or less holiday lighting, corresponding to population density and urbanization.\n\n**Legend:**\n\n| Holiday Lighting Change | Color on Map   |\n|------------------------|---------------|\n| More                   | Green/bright  |\n| No Change              | Yellow        |\n| Less         
-          | Dim/grey      |\n\n_The scale bar indicates a distance of 100 km for reference._\n\n---\n\n<!-- PageFooter=\"158 Earth at Night\" -->",
-      "page_number": 174
-    },
-    "reranker_score": 2.476761,
-    "doc_key": "earth_at_night_508_page_174_verbalized"
-  },
-  {
-    "type": "searchIndex",
-    "id": "2",
-    "activity_source": 3,
-    "source_data": {
-      "id": "earth_at_night_508_page_124_verbalized",
-      "page_chunk": "# Urban Development\n\n## Figure: Location Highlight on Globe\n\nThis figure depicts a globe focused on North America, with a marker pinpointing the central region of the United States. The highlighted location represents the geographical focus of the text discussion on US urban development and transportation networks.\n\n---\n\n## Urban Development\n\n### Lighting Paths\u2014Across the United States\n\nThe United States has more miles of roads than any other nation in the world\u20144.1 million miles (6.6 million kilometers) to be precise, which is roughly 40 percent more than second-ranked India. About 47,000 miles (75,639 kilometers) of those roads are part of the Interstate Highway System, established by President Dwight Eisenhower in the 1950s. The country/region also has 127,000 miles (204,000 kilometers) of railroad tracks and about 25,000 miles (40,000 kilometers) of navigable rivers and canals (not including the Great Lakes). The imprint of that transportation web becomes easy to see at night.\n\nThe VIIRS DNB on the Suomi NPP satellite acquired this nighttime view (top image, right) of the continental United States on October 1, 2013. The roadway map (bottom image, right) traces the path of the major interstate highways, railroads, and rivers of the United States. Comparing the two images, you quickly see how the cities and settlements align with the transportation corridors. In the early days of the republic, post roads and toll roads for horse-drawn carts and carriages were built to connect eastern cities like Boston, New York, Baltimore, and Philadelphia, though relatively few travelers made the long, unlit journeys. Railroads became the dominant transportation method for people and cargo in the middle of the nineteenth century, establishing longer links across the Nation and waypoints across the Midwest, the Great Plains, and the Rockies. Had nighttime satellite images existed in that era, they probably would show only dim pearls of light around major cities in the east and scattered across the country/region; the strands of steel tracks and cobbled roads that connected them would be invisible from space.\n\nEventually, cars and trucks became the dominant form of transportation in the United States. Drivers then needed roads and lighting to keep them safe on those roads. As the Nation grew in the twentieth century, the development of new cities and suburbs often conformed to the path of the interstate highways, adding light along the paths between the cities.\n\nOver the years, the length of navigable rivers has been a constant, as is their relative lack of light. Even today the only light seems to be the occasional port cities along riverbanks and the light of ships themselves.\n\n---\n\n**Table: Summary of U.S. Transportation Infrastructure**\n\n| Infrastructure Type     | Total Mileage (mi) | Total Mileage (km) |\n|------------------------|--------------------|--------------------|\n| Roads (All)            | 4,100,000          | 6,600,000          |\n| Interstate Highways    | 47,000             | 75,639             |\n| Railroads              | 127,000            | 204,000            |\n| Navigable Rivers/Canals| 25,000             | 40,000             |\n\n---\n\n<!-- PageFooter=\"108 Earth at Night\" -->",
-      "page_number": 124
-    },
-    "reranker_score": 2.466304,
-    "doc_key": "earth_at_night_508_page_124_verbalized"
-  },
-  {
-    "type": "searchIndex",
-    "id": "4",
-    "activity_source": 1,
-    "source_data": {
-      "id": "earth_at_night_508_page_176_verbalized",
-      "page_chunk": "# Holiday Lights\n\n## Figure 1: Location Marker on Globe\n\n**Description:**  \nA world map focused on the Western Hemisphere, with a marker placed in the eastern United States. This image serves to indicate the geographic focus of the following data and discussion about holiday lighting patterns, particularly those observed in the United States.\n\n---\n\nHoliday lights increase most dramatically in the suburbs and outskirts of major cities, where there is more yard space and a prevalence of single-family homes. Central urban areas do not see as large an increase in lighting, but they still experience a brightening of 20 to 30 percent during the holidays. This pattern holds true across the U.S., which remains ethnically and religiously diverse but participates in a nationally shared tradition of increased holiday lighting during holiday seasons.\n\nBeyond the cultural implications, this trend has significant consequences for energy consumption. The availability of a daily, global dynamic dataset of nighttime lights offers new insights into the broad societal forces influencing energy decisions. As noted by the Intergovernmental Panel on Climate Change, improvements in energy efficiency and conservation are essential to reducing greenhouse gas emissions. Examining daily nightlight data provides a valuable perspective on urban and suburban life, helping to reveal the underlying patterns and drivers of energy use.\n\n*(Images continue on pages 161-163)*\n\n---\n\n*Page 160 Earth at Night*",
-      "page_number": 176
-    },
-    "reranker_score": 2.3416197,
-    "doc_key": "earth_at_night_508_page_176_verbalized"
-  },
-  {
-    "type": "searchIndex",
-    "id": "6",
-    "activity_source": 1,
-    "source_data": {
-      "id": "earth_at_night_508_page_175_verbalized",
-      "page_chunk": "# Holiday Lights\n\nFrom 2013 to the average light output for the rest of 2012 to 2014, the change in light usage is subtle on any given night. However, when averaged over days and weeks, the pattern becomes more perceptible. Areas where light usage increased in December are marked in green, areas with little change are marked in yellow, and areas where less light was used are marked in red.\n\nThe light output from 70 U.S. cities was examined as a first step toward determining patterns in urban energy use. Researchers found that light intensity increased by 30 to 50 percent in December in many areas, which may be related to holiday lighting.\n\n---\n\n## Figure 1: Location Reference\n\nA globe highlights the southeastern region of the United States, pinpointing the area of interest for the study of holiday light usage, focusing on states like Tennessee, North Carolina, South Carolina, Georgia, and Alabama.\n\n---\n\n## Figure 2: Holiday Lighting Patterns in the Southeastern United States (2012\u20132014)\n\nThis map highlights several cities in the southeastern United States, including Nashville, Charlotte, Columbia, Birmingham, and Atlanta. The states of Tennessee, North Carolina, South Carolina, Alabama, and Georgia are outlined, along with the Atlantic Ocean to the east.\n\n### Key Observations:\n- The most significant concentrations of nighttime lighting are seen in major metropolitan areas, with Atlanta having the largest and most intense area of light.\n- Other notable clusters of increased light output are visible in Nashville, Charlotte, Birmingham, and Columbia.\n- The map reflects changes in light usage during December of 2012\u20132014, with \u201cmore\u201d lighting (green shading) concentrated around urban areas, indicating an increase due to holiday lighting displays.\n\n**Map Details:**\n- Time frame: 2012\u20132014\n- Locations marked: Nashville (Tennessee), Charlotte (North Carolina), Columbia (South Carolina), Birmingham (Alabama), Atlanta (Georgia)\n- Scale: 100 km bar provided\n- North directional arrow included\n\n---\n\n### Legend:\n- **Green Shading**: Areas where light usage increased in December (likely due to holiday lights)\n- **Yellow Shading**: Areas with little change in light usage\n- **Red Shading**: Areas where less light was used\n\n---\n\n#### Page Footer: \u201cno change\u201d\n#### Page Number: 159",
-      "page_number": 175
-    },
-    "reranker_score": 2.3052866,
-    "doc_key": "earth_at_night_508_page_175_verbalized"
-  },
-  {
-    "type": "searchIndex",
-    "id": "9",
-    "activity_source": 1,
-    "source_data": {
-      "id": "earth_at_night_508_page_177_verbalized",
-      "page_chunk": "# Holiday Lights\n\n## Holiday Lighting in Florida (2012\u20132014)\n\nThis figure presents a nighttime satellite map of Florida, highlighting changes in holiday lighting between 2012 and 2014. The map covers major urban areas including Jacksonville, Orlando, Tampa Bay, and Miami, with the Gulf of Mexico to the west.\n\nKey observations from the figure:\n- The map displays areas of increased, decreased, or unchanged outdoor lighting intensity during the holiday season.\n- Major metropolitan regions such as Miami, Tampa Bay, Orlando, and Jacksonville show noticeable concentrations of holiday lighting, with many surrounding areas experiencing changes in brightness compared to the non-holiday period.\n- Color coding (not described in the image but referenced):  \n  - **Less**: Areas where holiday lighting decreased  \n  - **No change**: Areas where lighting remained stable  \n  - **More**: Areas where holiday lighting increased\n\n**Legend:**\n- The figure includes a scale bar indicating a span of 100 km for distance estimation.\n- The map is oriented with north at the top.\n\n**Geographic Labels:**\n- Jacksonville (northeast Florida)\n- Orlando (central Florida)\n- Tampa Bay (west-central Florida)\n- Miami (southeast Florida)\n- The Gulf of Mexico (to the west of the peninsula)\n\n**Takeaway:**\nThe map visualizes spatial patterns in holiday lighting, indicating that urban and suburban areas in Florida experience substantial increases in nighttime brightness during the holiday period, particularly in and around major cities.\n\n<!-- PageNumber=\"161\" -->",
-      "page_number": 177
-    },
-    "reranker_score": 2.2241132,
-    "doc_key": "earth_at_night_508_page_177_verbalized"
-  },
-  {
-    "type": "searchIndex",
-    "id": "5",
-    "activity_source": 3,
-    "source_data": {
-      "id": "earth_at_night_508_page_12_verbalized",
-      "page_chunk": "## Preface\n\nTo keen observers, the nocturnal Earth is not pitch black, featureless, or static. The stars and the Moon provide illumination that differs from, and complements, daylight. Natural Earth processes such as volcanic eruptions, auroras, lightning, and meteors entering the atmosphere generate localized visible light on timescales ranging from subsecond (lightning), to days, weeks (forest fires), and months (volcanic eruptions).\n\nMost interesting and unique (as far as we know) to Earth, is the nighttime visible illumination emitted from our planet that is associated with human activities. Whether purposefully designed to banish darkness (such as lighting for safety, industrial activities, commerce, and transportation) or a secondary result of (such as gas flares associated with mining and hydrocarbon extraction activities, or nocturnal commercial fishing), anthropogenic sources of nighttime light are often broadly distributed in space and sustained in time\u2014over years and even decades. Because these light sources are inextricably tied to human activities and societies, extensive and long-term measurement and monitoring of Earth's anthropogenic nocturnal lights can provide valuable insights into the spatial distribution of our species and the ways in which society is changing\u2014and is changed by\u2014the environment on a wide range of time scales.\n\nOver the past four decades, sensitive imaging instruments have been operated on low-Earth-orbiting satellites to measure natural and human-caused visible nocturnal illumination, both reflected and Earth-generated. The satellite sensors provide unique imagery: global coverage yet with high spatial resolution, and frequent measurements over long periods of time.\n\nThe combined, multisatellite global nocturnal illumination dataset contains a treasure trove of unique information about our planet and our species\u2014and the",
-      "page_number": 12
-    },
-    "reranker_score": 2.128052,
-    "doc_key": "earth_at_night_508_page_12_verbalized"
-  },
-  {
-    "type": "searchIndex",
-    "id": "7",
-    "activity_source": 3,
-    "source_data": {
-      "id": "earth_at_night_508_page_125_verbalized",
-      "page_chunk": "# Urban Development\n\n**Date:** October 1, 2013\n\n---\n\n## Figure: Urban Development and Infrastructure in the United States\n\nThis figure comprises two maps of the continental United States, highlighting the patterns of urban development and infrastructure.\n\n### Top Panel: Nighttime Lights Map (October 1, 2013)\n\nThis map displays the United States as seen from space at night on October 1, 2013. Major observations include:\n\n- A dense concentration of bright spots representing urban and suburban areas with prominent lighting, especially along the east coast, the Midwest (notably around Chicago), Texas, and California.\n- The west and central parts of the country/region, such as the Rocky Mountains and deserts, appear much darker, indicating sparse population and fewer urban centers.\n- The boundaries of the United States are outlined for reference.\n- Major urban corridors are clearly visible, including the heavily lit regions running from Boston through New York City, Philadelphia, Baltimore, D.C., Atlanta, and further south, as well as the line of cities from Los Angeles through southern California.\n\n### Bottom Panel: Major Transport and River Networks\n\nThis map outlines the primary interstate highways, railroad lines, and major river systems in the continental United States, using different colors to distinguish among them:\n\n| Feature    | Color       | Description                                                                       |\n|------------|-------------|-----------------------------------------------------------------------------------|\n| Interstate | Red         | Key high-speed roadways, forming a vast national network and connecting cities     |\n| Railroad   | Green       | Major rail lines paralleling some highway routes, providing freight and passenger service |\n| River      | Blue        | Major river systems used historically for transport, industry, and urban siting    |\n\n- The locations of interstate highways closely follow the distribution of nighttime lights, as seen in the top panel.\n- Railroad networks are especially dense in the Midwest and northeast, regions with both high population density and industrial activity.\n- Major rivers, such as the Mississippi, Missouri, and Ohio, are marked in blue, reflecting their importance for historical urban development.\n\n**Scale:** Both maps include a scale bar representing 500 km and a North arrow for orientation.\n\n---\n\n**Summary:**  \nThe figure visually demonstrates the relationship between urban development (as observed through nighttime satellite imagery) and the underlying networks of interstates, railroads, and rivers that have historically influenced the growth and connectivity of American cities. Most urbanized and densely lit areas correspond to nodes and crossroads within this transportation and river network.\n\n---\n\n**Page 109**",
-      "page_number": 125
-    },
-    "reranker_score": 2.108246,
-    "doc_key": "earth_at_night_508_page_125_verbalized"
-  },
-  {
-    "type": "searchIndex",
-    "id": "8",
-    "activity_source": 2,
-    "source_data": {
-      "id": "earth_at_night_508_page_179_verbalized",
-      "page_chunk": "# Holiday Lights\n\n## Figure 1: Geographic Context of Holiday Lighting Study\n\nThis figure shows a map of the globe focused on North America, with a blue marker pointing to the region in the southwestern United States. This highlighted area includes parts of California, Nevada, and Arizona, encompassing the cities of Los Angeles, San Diego, Las Vegas, and Phoenix. This is the region of the study of holiday lighting.\n\n---\n\n## Figure 2: Changes in Holiday Lighting (2012\u20132014)\n\nThis figure is a satellite map of the southwestern United States and northwestern Mexico, annotated with state and city names:\n\n- **California** (including Los Angeles and San Diego)\n- **Nevada** (including Las Vegas)\n- **Arizona** (including Phoenix)\n- **Mexico** (including Tijuana)\n\nThe map shows holiday lighting patterns, using color to indicate change in light intensity during the holiday period (presumably Christmas season) between 2012 and 2014.\n\n### Map Legend\n\n| Color      | Meaning                     |\n|------------|-----------------------------|\n| Greenish   | More holiday lighting       |\n| Yellow     | No change in lighting       |\n| Red        | Less holiday lighting       |\n\n### Observations\n\n- Major urban areas such as Los Angeles, San Diego, Las Vegas, and Phoenix show increased lighting during the holiday period (marked primarily in green).\n- Some areas show no significant change, especially in less densely populated zones.\n- A few small areas may show a decrease in holiday lighting (if red is present).\n\n- The scale of the map includes a reference bar showing 50 km for distance.\n\n---\n\n### Holiday Lighting Change Key\n\n- **Less** (Red)\n- **No change** (Yellow)\n- **More** (Green)\n\n---\n\n<!-- PageNumber=\"163\" -->",
-      "page_number": 179
-    },
-    "reranker_score": 2.1016884,
-    "doc_key": "earth_at_night_508_page_179_verbalized"
-  }
+  ... // Trimmed for brevity
 ]
 Retrieved content from 'earth-knowledge-base' successfully.
 response_content:
@@ -570,7 +464,7 @@ Now that you've run the code, let's break down the key steps:
 
 ### Create a search index
 
-In Azure AI Search, an index is a structured collection of data. The following code defines an index named `earth-at-night`, which you previously specified using the `index_name` variable.
+In Azure AI Search, an index is a structured collection of data. The following code defines an index named `earth-at-night`.
 
 The index schema contains fields for document identification and page content, embeddings, and numbers. The schema also includes configurations for semantic ranking and vector search, which uses your `text-embedding-3-large` deployment to vectorize text and match documents based on semantic similarity.
 
@@ -620,6 +514,8 @@ index_client.create_or_update_index(index)
 print(f"Index '{index_name}' created or updated successfully.")
 ```
 
+Reference: [SearchField](/python/api/azure-search-documents/azure.search.documents.indexes.models.searchfield), [VectorSearch](/python/api/azure-search-documents/azure.search.documents.indexes.models.vectorsearch), [SemanticSearch](/python/api/azure-search-documents/azure.search.documents.indexes.models.semanticsearch), [SearchIndex](/python/api/azure-search-documents/azure.search.documents.indexes.models.searchindex), [SearchIndexClient](/python/api/azure-search-documents/azure.search.documents.indexes.searchindexclient)
+
 ### Upload documents to the index
 
 Currently, the `earth-at-night` index is empty. The following code populates the index with JSON documents from [NASA's Earth at Night e-book](https://raw.githubusercontent.com/Azure-Samples/azure-search-sample-data/refs/heads/main/nasa-e-book/earth-at-night-json/documents.json). As required by Azure AI Search, each document conforms to the fields and data types defined in the index schema.
@@ -635,11 +531,13 @@ with SearchIndexingBufferedSender(endpoint=search_endpoint, index_name=index_nam
 print(f"Documents uploaded to index '{index_name}' successfully.")
 ```
 
+Reference: [SearchIndexingBufferedSender](/python/api/azure-search-documents/azure.search.documents.searchindexingbufferedsender)
+
 ### Create a knowledge source
 
 A knowledge source is a reusable reference to source data. The following code defines a knowledge source named `earth-knowledge-source` that targets the `earth-at-night` index.
 
-`source_data_fields` specifies which index fields are included in citation references. Our example includes only human-readable fields to avoid lengthy, uninterpretable embeddings in responses.
+`source_data_fields` specifies which index fields are included in citation references. This example includes only human-readable fields to avoid lengthy, uninterpretable embeddings in responses.
 
 ```python
 # Create a knowledge source
@@ -657,9 +555,11 @@ index_client.create_or_update_knowledge_source(knowledge_source=ks)
 print(f"Knowledge source '{knowledge_source_name}' created or updated successfully.")
 ```
 
+Reference: [SearchIndexKnowledgeSource](/python/api/azure-search-documents/azure.search.documents.indexes.models.searchindexknowledgesource)
+
 ### Create a knowledge base
 
-To target `earth-knowledge-source` and your `gpt-5-mini` deployment at query time, you need a knowledge base. The following code defines a knowledge base named `earth-knowledge-base`, which you previously specified using the `knowledge_base_name` variable.
+To target `earth-knowledge-source` and your `gpt-5-mini` deployment at query time, you need a knowledge base. The following code defines a knowledge base named `earth-knowledge-base`.
 
 `output_mode` is set to `ANSWER_SYNTHESIS`, enabling natural-language answers that cite the retrieved documents and follow the provided `answer_instructions`.
 
@@ -688,6 +588,8 @@ index_client.create_or_update_knowledge_base(knowledge_base)
 print(f"Knowledge base '{knowledge_base_name}' created or updated successfully.")
 ```
 
+Reference: [KnowledgeBase](/python/api/azure-search-documents/azure.search.documents.indexes.models.knowledgebase)
+
 ### Set up messages
 
 Messages are the input for the retrieval route and contain the conversation history. Each message includes a role that indicates its origin, such as `system` or `user`, and content in natural language. The LLM you use determines which roles are valid.
@@ -755,6 +657,8 @@ result = agent_client.retrieve(retrieval_request=req)
 print(f"Retrieved content from '{knowledge_base_name}' successfully.")
 ```
 
+Reference: [KnowledgeBaseRetrievalClient](/python/api/azure-search-documents/azure.search.documents.knowledgebases.knowledgebaseretrievalclient), [KnowledgeBaseRetrievalRequest](/python/api/azure-search-documents/azure.search.documents.knowledgebases.models.knowledgebaseretrievalrequest)
+
 #### Review the response, activity, and references
 
 The following code displays the response, activity, and references from the retrieval pipeline, where:

@@ -4,7 +4,9 @@ author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 12/05/2025
+ms.date: 01/14/2026
+ms.custom: dev-focus
+ai-usage: ai-assisted
 ---
 
 [!INCLUDE [Feature preview](../previews/preview-generic.md)]
@@ -13,7 +15,7 @@ In this quickstart, you use [agentic retrieval](../../agentic-retrieval-overview
 
 A *knowledge base* orchestrates agentic retrieval by decomposing complex queries into subqueries, running the subqueries against one or more *knowledge sources*, and returning results with metadata. By default, the knowledge base outputs raw content from your sources, but this quickstart uses the answer synthesis output mode for natural-language answer generation.
 
-Although you can provide your own data, this quickstart uses [sample JSON documents](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/nasa-e-book/earth-at-night-json) from NASA's Earth at Night e-book. The documents describe general science topics and images of Earth at night as observed from space.
+Although you can use your own data, this quickstart uses [sample JSON documents](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/nasa-e-book/earth-at-night-json) from NASA's Earth at Night e-book. The documents describe general science topics and images of Earth at night as observed from space.
 
 > [!TIP]
 > Want to get started right away? See the [azure-search-rest-samples](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart-agentic-retrieval) GitHub repository.
@@ -387,7 +389,7 @@ Now that you've run the code, let's break down the key steps:
 
 ### Create a search index
 
-In Azure AI Search, an index is a structured collection of data. The following code uses [Indexes - Create (REST API)](/rest/api/searchservice/indexes/create) to define an index named `earth-at-night`, which you previously specified using the `@index-name` variable.
+In Azure AI Search, an index is a structured collection of data. The following code defines an index named `earth-at-night`.
 
 The index schema contains fields for document identification and page content, embeddings, and numbers. The schema also includes configurations for semantic ranking and vector search, which uses your `text-embedding-3-large` deployment to vectorize text and match documents based on semantic similarity.
 
@@ -467,12 +469,13 @@ Authorization: Bearer {{token}}
 }
 ```
 
+Reference: [Indexes - Create](/rest/api/searchservice/indexes/create)
+
 ### Upload documents to the index
 
-Currently, the `earth-at-night` index is empty. The following code uses [Documents - Index (REST API)](/rest/api/searchservice/documents/index) to populate the index with JSON documents from NASA's Earth at Night e-book. As required by Azure AI Search, each document conforms to the fields and data types defined in the index schema.
+Currently, the `earth-at-night` index is empty. The following code populates the index with JSON documents from NASA's Earth at Night e-book. As required by Azure AI Search, each document conforms to the fields and data types defined in the index schema.
 
 ```HTTP
-
 ### Upload documents
 POST {{search-url}}/indexes/{{index-name}}/docs/index?api-version={{api-version}}  HTTP/1.1
 Content-Type: application/json
@@ -502,11 +505,13 @@ Authorization: Bearer {{token}}
 }
 ```
 
+Reference: [Documents - Index](/rest/api/searchservice/documents/index)
+
 ### Create a knowledge source
 
-A knowledge source is a reusable reference to source data. The following code uses [Knowledge Sources - Create (REST API)](/rest/api/searchservice/knowledge-sources/create?view=rest-searchservice-2025-11-01-preview&preserve-view=true) to define a knowledge source named `earth-knowledge-source` that targets the `earth-at-night` index.
+A knowledge source is a reusable reference to source data. The following code defines a knowledge source named `earth-knowledge-source` that targets the `earth-at-night` index.
 
-`sourceDataFields` specifies which index fields are included in citation references. Our example includes only human-readable fields to avoid lengthy, uninterpretable embeddings in responses.
+`sourceDataFields` specifies which index fields are included in citation references. This example includes only human-readable fields to avoid lengthy, uninterpretable embeddings in responses.
 
 ```HTTP
 ### Create a knowledge source
@@ -529,9 +534,11 @@ Authorization: Bearer {{token}}
 }
 ```
 
+Reference: [Knowledge Sources - Create](/rest/api/searchservice/knowledge-sources/create?view=rest-searchservice-2025-11-01-preview&preserve-view=true)
+
 ### Create a knowledge base
 
-To target your `earth-knowledge-source` and `gpt-5-mini` deployment at query time, you need a knowledge base. The following code uses [Knowledge Bases - Create (REST API)](/rest/api/searchservice/knowledge-bases/create?view=rest-searchservice-2025-11-01-preview&preserve-view=true) to define a base named `earth-knowledge-base`, which you previously specified using the `@knowledge-base-name` variable.
+To target your `earth-knowledge-source` and `gpt-5-mini` deployment at query time, you need a knowledge base. The following code defines a base named `earth-knowledge-base`.
 
 `outputMode` is set to `answerSynthesis`, enabling natural-language answers that cite the retrieved documents and follow the provided `answerInstructions`.
 
@@ -563,9 +570,11 @@ Authorization: Bearer {{token}}
 }
 ```
 
+Reference: [Knowledge Bases - Create](/rest/api/searchservice/knowledge-bases/create?view=rest-searchservice-2025-11-01-preview&preserve-view=true)
+
 ### Run the retrieval pipeline
 
-You're ready to run agentic retrieval. The following code uses [Knowledge Retrieval - Retrieve (REST API)](/rest/api/searchservice/knowledge-retrieval/retrieve?view=rest-searchservice-2025-11-01-preview&preserve-view=true) to send a two-part user query to `earth-knowledge-base`, which:
+You're ready to run agentic retrieval. The following code sends a two-part user query to `earth-knowledge-base`, which:
 
 1. Analyzes the entire conversation to infer the user's information need.
 1. Decomposes the compound query into focused subqueries.
@@ -606,6 +615,8 @@ Authorization: Bearer {{token}}
 }
 ```
 
+Reference: [Knowledge Retrieval - Retrieve](/rest/api/searchservice/knowledge-retrieval/retrieve?view=rest-searchservice-2025-11-01-preview&preserve-view=true)
+
 The output should contain the following components:
 
 + `response` provides a synthesized, LLM-generated answer to the query that cites the retrieved documents. When answer synthesis isn't enabled, this section contains content extracted directly from the documents.

@@ -4,7 +4,9 @@ author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 12/19/2025
+ms.date: 01/14/2026
+ms.custom: dev-focus
+ai-usage: ai-assisted
 ---
 
 [!INCLUDE [Feature preview](../previews/preview-generic.md)]
@@ -598,19 +600,7 @@ Reference Type: searchIndex
   "rerankerScore": 2.6692379,
   "docKey": "earth_at_night_508_page_174_verbalized"
 }
-Reference Type: searchIndex
-{
-  "type": "searchIndex",
-  "id": "1",
-  "activitySource": 3,
-  "sourceData": {
-    "id": "earth_at_night_508_page_186_verbalized",
-    "page_chunk": "## Appendix A\n\n### NASA's Black Marble Product Suite\n\nNASA's Black Marble product suite provides estimates of daily nighttime lights and other intrinsic surface optical properties of Earth at night. The product is based on the Day/Night Band (DNB) sensor of the Visible Infrared Imaging Radiometer Suite (VIIRS) instrument onboard the Suomi National Polar-orbiting Partnership (NPP) satellite. The VIIRS DNB is a highly sensitive, low-light sensor capable of measuring daily global nighttime light emissions and reflections, allowing users to identify sources and intensities of these artificial lights, and monitor changes over a period of time. Like any optical sensor, the principal challenge in using VIIRS DNB data is to account for variations in light captured by the sensor. Certainly, there are variations in the sources and intensity of anthropogenic light due to changing human processes like urbanization, oil and gas production, nighttime commercial fishing, and infrastructure development. However, these processes can only be studied when other naturally-occurring factors that influence nighttime lights are removed. For example, variations in lunar lighting due to consistent changes in Moon phase cause fluctuations in the amount of light shining on Earth. Similarly, land-cover dynamics (e.g., seasonal vegetation, snow and ice cover), as well as atmospheric conditions (e.g., clouds, aerosols, airglow, and auroras), influence the intensity of the light captured by the sensor as it travels over various parts of the world.\n\nTo realize the full potential of the VIIRS DNB time series record for nighttime lights applications, NASA's Black Marble product suite was developed, building on a history of 20 years of research on how light changes when it reflects off of surfaces with different angular and spectral properties. Through complex modeling, scientists can now predict how moonlight, snow, vegetation, terrain, and clouds impact the lights we see from space, allowing for more accurate assessments of human and environmental activity at night.\n\n<!-- PageFooter=\"170 Earth at Night\" -->",
-    "page_number": 186
-  },
-  "rerankerScore": 2.5997617,
-  "docKey": "earth_at_night_508_page_186_verbalized"
-}
+... // Trimmed for brevity
 
 ❓ Follow-up question: How do I find lava at night?
 
@@ -735,6 +725,8 @@ const searchClient = new SearchClient<EarthAtNightDocument>(process.env.AZURE_SE
 await searchIndexClient.createOrUpdateIndex(index);
 ```
 
+Reference: [SearchField](/javascript/api/@azure/search-documents/searchfield), [VectorSearch](/javascript/api/@azure/search-documents/vectorsearch), [SemanticSearch](/javascript/api/@azure/search-documents/semanticsearch), [SearchIndex](/javascript/api/@azure/search-documents/searchindex), [SearchIndexClient](/javascript/api/@azure/search-documents/searchindexclient), [SearchClient](/javascript/api/@azure/search-documents/searchclient), [DefaultAzureCredential](/javascript/api/@azure/identity/defaultazurecredential)
+
 ### Upload documents to the index
 
 Currently, the `earth-at-night` index is empty. The following code populates the index with JSON documents from [NASA's Earth at Night e-book](https://raw.githubusercontent.com/Azure-Samples/azure-search-sample-data/refs/heads/main/nasa-e-book/earth-at-night-json/documents.json). As required by Azure AI Search, each document conforms to the fields and data types defined in the index schema.
@@ -775,11 +767,13 @@ while (count !== documents.length) {
 console.log(`✓ All ${documents.length} documents indexed successfully!`);
 ```
 
+Reference: [SearchIndexingBufferedSender](/javascript/api/@azure/search-documents/searchindexingbufferedsender)
+
 ### Create a knowledge source
 
 A knowledge source is a reusable reference to source data. The following code defines a knowledge source named `earth-knowledge-source` that targets the `earth-at-night` index.
 
-`source_data_fields` specifies which index fields are included in citation references. Our example includes only human-readable fields to avoid lengthy, uninterpretable embeddings in responses.
+`source_data_fields` specifies which index fields are included in citation references. This example includes only human-readable fields to avoid lengthy, uninterpretable embeddings in responses.
 
 ```typescript
 await searchIndexClient.createKnowledgeSource({
@@ -798,6 +792,8 @@ await searchIndexClient.createKnowledgeSource({
 console.log(`✅ Knowledge source 'earth-knowledge-source' created successfully.`);
 ```
 
+Reference: [SearchIndexKnowledgeSource](/javascript/api/@azure/search-documents/searchindexknowledgesource)
+
 ### Create a knowledge base
 
 To target `earth-knowledge-source` and your `gpt-5-mini` deployment at query time, you need a knowledge base. The following code defines a knowledge base named `earth-knowledge-base`.
@@ -829,6 +825,8 @@ await searchIndexClient.createKnowledgeBase({
 console.log(`✅ Knowledge base 'earth-knowledge-base' created successfully.`); 
 ```
 
+Reference: [KnowledgeBase](/javascript/api/@azure/search-documents/knowledgebase)
+
 ### Run the retrieval pipeline
 
 You're ready to run agentic retrieval. The following code sends a two-part user query to `earth-knowledge-base`, which:
@@ -877,6 +875,8 @@ const retrievalRequest = {
 const result = await knowledgeRetrievalClient.retrieveKnowledge(retrievalRequest);
 ```
 
+Reference: [KnowledgeRetrievalClient](/javascript/api/@azure/search-documents/knowledgeretrievalclient), [KnowledgeBaseRetrievalRequest](/javascript/api/@azure/search-documents/knowledgebaseretrievalrequest)
+
 ### Review the response, activity, and references
 
 The following code displays the response, activity, and references from the retrieval pipeline, where:

@@ -4,122 +4,126 @@ author: rotabor
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 11/20/2025
+ms.date: 01/14/2026
+ms.custom: dev-focus
+ai-usage: ai-assisted
 ---
 
-In this quickstart, you work with a .NET app to create, populate, and query vectors. The code examples perform these operations by using the [Azure AI Search client library](/dotnet/api/overview/azure/search). The library provides an abstraction over the REST API for access to index operations such as data ingestion, search operations, and index management operations.
+In this quickstart, you use a .NET app to create, load, and query a [vector index](../../vector-store.md). The code performs these operations by using the [Azure AI Search client library for .NET](/dotnet/api/overview/azure/search), which provides an abstraction over the REST APIs to access index operations.
 
-In Azure AI Search, a [vector store](../../vector-store.md) has an index schema that defines vector and nonvector fields, a vector search configuration for algorithms that create the embedding space, and settings on vector field definitions that are evaluated at query time. The [Create Index](/rest/api/searchservice/indexes/create-or-update) REST API creates the vector store.
+In Azure AI Search, a vector index has an index schema that defines vector and nonvector fields, a vector search configuration for algorithms that create the embedding space, and settings on vector field definitions that are evaluated at query time. [Indexes - Create or Update](/rest/api/searchservice/indexes/create-or-update) (REST API) creates the vector index.
 
 > [!NOTE]
 > This quickstart omits the vectorization step and provides inline embeddings. If you want to add [built-in data chunking and vectorization](../../vector-search-integrated-vectorization.md) over your own content, try the [**Import data (new)** wizard](../../search-get-started-portal-import-vectors.md) for an end-to-end walkthrough.
 
 ## Prerequisites
 
-- An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
++ An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
 
-- An Azure AI Search service. [Create a service](../../search-create-service-portal.md) or [find an existing service](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/CognitiveSearch) in your current subscription.
-    - You can use a free search service for most of this quickstart, but we recommend the Basic tier or higher for larger data files.
-    - To run the query example that invokes [semantic reranking](../../semantic-search-overview.md), your search service must have [semantic ranker enabled](../../semantic-how-to-enable-disable.md).
++ An [Azure AI Search service](../../search-create-service-portal.md).
 
-- [Visual Studio Code](https://code.visualstudio.com/download) or [Visual Studio](https://visualstudio.com).
+    + You can use the Free tier for most of this quickstart, but we recommend Basic or higher for larger data files.
 
-- [Git](https://git-scm.com/downloads) to clone the sample repo.
+    + For [keyless authentication](../../search-get-started-rbac.md) with Microsoft Entra ID, assign the **Search Index Data Contributor role** to your user account.
+    
+    + To run the semantic hybrid query, you must [enable semantic ranker](../../semantic-how-to-enable-disable.md).
+
++ [Visual Studio Code](https://code.visualstudio.com/download) or [Visual Studio](https://visualstudio.com) to run the code.
+
++ [Git](https://git-scm.com/downloads) to clone the sample repo.
 
 ## Get service information
 
-Requests to the search endpoint must be authenticated and authorized. While it's possible to use API keys or roles for this task, we recommend [using a keyless connection via Microsoft Entra ID](../../search-get-started-rbac.md).
+Requests to the search endpoint must be authenticated and authorized. While it's possible to use API keys for this task, we recommend [using a keyless connection via Microsoft Entra ID](../../search-get-started-rbac.md).
 
-This quickstart uses `DefaultAzureCredential`, which simplifies authentication in both development and production scenarios. However, for production scenarios, you might have more advanced requirements that require a different approach. See [Authenticate .NET apps to Azure services by using the Azure SDK for .NET](/dotnet/azure/sdk/authentication/) to understand all of your options.
+This quickstart uses `DefaultAzureCredential`, which simplifies authentication in both development and production scenarios. However, for production scenarios, you might have more advanced requirements that require a different approach. To understand all of your options, see [Authenticate .NET apps to Azure services by using the Azure SDK for .NET](/dotnet/azure/sdk/authentication/).
 
 ## Clone the code and setup environment
 
-1. Clone the repo containing the code for this quickstart. 
+1. Clone the repo containing the code for this quickstart.
 
    ```bash
    git clone https://github.com/Azure-Samples/azure-search-dotnet-samples
    ```
-  
-   This repo has .NET code examples for several articles each in a separate subfolder.
 
-1. Open the subfolder `quickstart-Vector-Search` in Visual Studio Code, or double click the `.sln` file to open the solution in Visual Studio.
+1. Open the `quickstart-vector-search` folder in Visual Studio Code or double-click the `VectorSearchQuickstart.sln` file to open the solution in Visual Studio.
+
+1. Open `appsettings.json` in both `VectorSearchCreatePopulateIndex` and `VectorSearchExamples` folders. 
 
-1. Open the `appsettings.json` files in the `VectorSearchExamples` and `VectorSearchCreatePopulateIndex` folders. Update the following values: 
+1. Set `Endpoint` to your search service URL, which should be similar to `https://mydemo.search.windows.net`.
 
-   - `AZURE_SEARCH_ENDPOINT`: Find the url of your Azure AI Search service in the [Azure portal](https://portal.azure.com). On the **Overview** page of your search resource, look for the URL field. An example endpoint might look like `https://mydemo.search.windows.net`. 
-   - `AZURE_SEARCH_INDEX_NAME`: Leave the default value provided in the file or enter your own index name.
+1. Set `IndexName` to a unique name for your index. You can also use the default `hotels-vector-quickstart` name.
 
-## Create the vector index and upload documents
+## Create a vector index and upload documents
 
-To run search queries against the Azure AI Search service, you first need to create a search index and upload documents to the service.
+To run search queries against your Azure AI Search service, you must first create a search index and upload documents to the index.
 
-1. Open a new terminal in the `VectorSearchCreatePopulateIndex` folder.
+To create and populate the index:
 
-1. Run the project using the `dotnet run` command:
+1. Open a terminal in the `VectorSearchCreatePopulateIndex` folder.
+
+1. Use the `dotnet run` command to run the project.
 
     ```dotnetcli
     dotnet run
     ```
 
-The following code executes to create an index:
-
-:::code language="csharp" source="~/azure-search-dotnet-samples/quickstart-vector-search/vectorsearchcreatepopulateindex/program.cs" id="CreateSearchindex":::
-
-The following code uploads the JSON formatted documents in the `hotel-samples.json` file to the Azure AI Search service:
-
-:::code language="csharp" source="~/azure-search-dotnet-samples/quickstart-vector-search/vectorsearchcreatepopulateindex/program.cs" id="UploadDocs":::
-
-After you run the project, the following output is printed:
-
-```output
-Key: 1, Succeeded: True
-Key: 2, Succeeded: True
-Key: 3, Succeeded: True
-Key: 4, Succeeded: True
-Key: 48, Succeeded: True
-Key: 49, Succeeded: True
-Key: 13, Succeeded: True
-```
-
-Key takeaways:
-
-- Your code interacts with a specific search index hosted in your Azure AI Search service through the `SearchClient`, which is the main object provided by the `azure-search-documents` package. The `SearchClient` provides access to index operations such as:
+    The following code executes to create an index:
+    
+    :::code language="csharp" source="~/azure-search-dotnet-samples/quickstart-vector-search/vectorsearchcreatepopulateindex/program.cs" id="CreateSearchindex":::
+    
+    The following code uploads JSON-formatted documents in the `hotel-samples.json` file to your search service.
+    
+    :::code language="csharp" source="~/azure-search-dotnet-samples/quickstart-vector-search/vectorsearchcreatepopulateindex/program.cs" id="UploadDocs":::
+    
+    After you run the project, the following output is printed.
+    
+    ```output
+    Key: 1, Succeeded: True
+    Key: 2, Succeeded: True
+    Key: 3, Succeeded: True
+    Key: 4, Succeeded: True
+    Key: 48, Succeeded: True
+    Key: 49, Succeeded: True
+    Key: 13, Succeeded: True
+    ```
+    
+    Key takeaways:
 
-    - **Data ingestion**: `UploadDocuments()`, `MergeDocuments()`, `DeleteDocuments()`
-    - **Search operations**: `Search()`, `Autocomplete()`, `Suggest()`
-    - **Index management operations**: `CreateOrUpdateIndex()`
+    + Your code interacts with a specific search index hosted in your Azure AI Search service through the SearchClient, which is the main object provided by the azure-search-documents package. The SearchClient provides access to index operations, such as:
 
-- Vector fields contain floating point values. The dimensions attribute has a minimum of 2 and a maximum of 4096 floating point values each. This size of embeddings generated by the Azure OpenAI **text-embedding-3-small** model for this quickstart is 1536.
+        + Data ingestion: `UploadDocuments()`, `MergeDocuments()`, `DeleteDocuments()`
 
-## Run search queries
+        + Search operations: `Search()`, `Autocomplete()`, `Suggest()`
+        
+        + Index management operations: `CreateOrUpdateIndex()`
+    
+    + Vector fields contain floating point values. The dimensions attribute has a minimum of 2 and a maximum of 4096 floating point values each. This quickstart sets the dimensions attribute to 1,536 because that's the size of embeddings generated by the `text-embedding-ada-002` model.
 
-After the index is created and documents are loaded, you can issue vector queries against them by calling `SearchAsync()` with various parameters.
+## Run queries
 
-1. In the `VectorSearchExamples` folder, open the `Program.cs` file.
-1. Open a new terminal in the `VectorSearchExamples` folder.
+To issue the vector queries in this section, open `Program.cs` in the `VectorSearchExamples` folder, and then open a terminal in the `VectorSearchExamples` folder.
 
-In the following sections, you run queries against the `hotels-vector-quickstart` index. The queries include:
+Queries in this section:
 
-- [Single vector search](#single-vector-search)
-- [Single vector search with filter](#single-vector-search-with-filter)
-- [Hybrid search](#hybrid-search)
-- [Semantic hybrid search with filter](#semantic-hybrid-search-with-a-filter)
++ [Single vector search](#single-vector-search)
++ [Single vector search with filter](#single-vector-search-with-filter)
++ [Hybrid search](#hybrid-search)
++ [Semantic hybrid search with filter](#semantic-hybrid-search-with-a-filter)
 
 ### Single vector search
 
-The first example demonstrates a basic scenario where you want to find document descriptions that closely match the search string.
+The first query demonstrates a basic scenario where you want to find document descriptions that closely match the search string.
 
-1. In the `Program.cs` file of the `VectorSearchExamples` folder, uncomment the method call `SearchExamples.SearchSingleVector(searchClient, vectorizedResult);`. This method executes the following search function in the `SearchExamples.cs` class:
+To create a single vector search:
 
-    :::code language="csharp" source="~/azure-search-dotnet-samples/quickstart-vector-search/vectorsearchexamples/SearchExamples.cs" id="SearchSingleVector":::
+1. In the `Program.cs` file of the `VectorSearchExamples` folder, uncomment the `SearchExamples.SearchSingleVector(searchClient, vectorizedResult);` method call.
 
-1. Run the project using the `dotnet run` command:
+    This method executes the following search function in the `SearchExamples.cs` class.
 
-    ```dotnetcli
-    dotnet run
-    ```
+    :::code language="csharp" source="~/azure-search-dotnet-samples/quickstart-vector-search/vectorsearchexamples/SearchExamples.cs" id="SearchSingleVector":::
 
-    After you run the project, the search results are printed in the output window:
+1. Run `dotnet run` to execute the query, which returns the following results.
     
     ```output
     Single Vector Search Results:
@@ -132,29 +136,31 @@ The first example demonstrates a basic scenario where you want to find document
 
 ### Single vector search with filter
 
-You can add filters, but the filters are applied to the nonvector content in your index. In this example, the filter applies to the `Tags` field to filter out any hotels that don't provide free Wi-Fi.
+In Azure AI Search, [filters](../../vector-search-filters.md) apply to nonvector fields in an index. This example filters on the `Tags` field to filter out any hotels that don't provide free Wi-Fi.
+
+To create a single vector search with a filter:
+
+1. In the `Program.cs` file of the `VectorSearchExamples` folder, uncomment the `SearchExamples.SearchSingleVectorWithFilter(searchClient, vectorizedResult);` method call.
 
-1. In the `Program.cs` file of the `VectorSearchExamples` folder, uncomment the method call `SearchExamples.SearchSingleVectorWithFilter(searchClient, vectorizedResult);`. This method executes the following search function in the `SearchExamples.cs` class:
+    This method executes the following search function in the `SearchExamples.cs` class.
 
     :::code language="csharp" source="~/azure-search-dotnet-samples/quickstart-vector-search/vectorsearchexamples/SearchExamples.cs" id="SearchSingleVectorWithFilter":::
 
-1.  Run the project again, and the status of each document is printed below it:
+1.  Run `dotnet run` to execute the query, which returns only hotels that provide free Wi-Fi. 
     
        ```output
         Single Vector Search With Filter Results:
         Score: 0.6605852, HotelId: 48, HotelName: Nordick's Valley Motel, Tags: continental breakfastair conditioningfree wifi
         Score: 0.57902366, HotelId: 2, HotelName: Old Century Hotel, Tags: poolfree wifiair conditioningconcierge
        ```
 
-       The query was the same as the previous [single vector search example](#single-vector-search), but it includes a post-processing exclusion filter and returns only the two hotels that have free Wi-Fi.
+1. For a geo filter, uncomment `SearchExamples.SingleSearchWithGeoFilter(searchClient, vectorizedResult);` in `Program.cs`.
 
-1. The next filter example uses a **geo filter**. In the `Program.cs` file of the `VectorSearchExamples` folder, uncomment the method call `SearchExamples.SingleSearchWithGeoFilter(searchClient, vectorizedResult);`. This method executes the following search function in the `SearchExamples.cs` class:
+    This method executes the following search function in the `SearchExamples.cs` class.
 
     :::code language="csharp" source="~/azure-search-dotnet-samples/quickstart-vector-search/vectorsearchexamples/SearchExamples.cs" id="SingleSearchWithGeoFilter":::
-   
-   The query was the same as the previous [single vector search example](#single-vector-search), but it includes a post-processing exclusion filter and returns only the two hotels within 300 kilometers.
 
-1.  Run the project again, and the status of each document is printed below it:
+1.  Run `dotnet run` to execute the query, which returns only hotels within 300 kilometers.
    
     ```output
     Vector query with a geo filter:
@@ -173,16 +179,20 @@ You can add filters, but the filters are applied to the nonvector content in you
 
 ### Hybrid search
 
-Hybrid search consists of keyword queries and vector queries in a single search request. This example runs the vector query and full-text search concurrently:
+[Hybrid search](../../hybrid-search-overview.md) combines keyword and vector queries in one request. This example runs the following full-text and vector query strings concurrently:
+
++ Search string: `historic hotel walk to restaurants and shopping`
++ Vector query string: `quintessential lodging near running trails, eateries, retail` (vectorized into a mathematical representation)
 
-- **Search string**: `historic hotel walk to restaurants and shopping`
-- **Vector query string** (vectorized into a mathematical representation): `Quintessential lodging near running trails, eateries, retail`
+To create a hybrid search:
 
-1. In the `Program.cs` file of the `VectorSearchExamples` folder, uncomment the method call `SearchExamples.SearchHybridVectorAndText(searchClient, vectorizedResult);`. This method executes the following search function in the `SearchExamples.cs` class:
+1. In the `Program.cs` file, uncomment the `SearchExamples.SearchHybridVectorAndText(searchClient, vectorizedResult);` method call.
+
+    This method executes the following search function in the `SearchExamples.cs` class.
 
     :::code language="csharp" source="~/azure-search-dotnet-samples/quickstart-vector-search/vectorsearchexamples/SearchExamples.cs" id="SearchHybridVectorAndText":::
 
-1.  Run the project again, and the status of each document is printed below it:
+1.  Run `dotnet run` to execute the query, which returns the following results.
 
        ```output
        Hybrid search results:
@@ -222,136 +232,140 @@ Hybrid search consists of keyword queries and vector queries in a single search
        Tags: poolfree wifiair conditioningconcierge
        ```
     
-Because Reciprocal Rank Fusion (RRF) merges results, it helps to review the inputs. The following results are from only the full-text query. The top two results are Sublime Palace Hotel and Luxury Lion Resort. The Sublime Palace Hotel has a stronger BM25 relevance score.
-
-```json
-{
-    "@search.score": 2.2626662,
-    "HotelName": "Sublime Palace Hotel",
-    "Description": "Sublime Palace Hotel is located in the heart of the historic center of Sublime in an extremely vibrant and lively area within short walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments. Sublime Palace is part of a lovingly restored 1800 palace."
-},
-{
-    "@search.score": 0.86421645,
-    "HotelName": "Luxury Lion Resort",
-    "Description": "Unmatched Luxury.  Visit our downtown hotel to indulge in luxury accommodations. Moments from the stadium, we feature the best in comfort"
-},
-```
-
-In the vector-only query, which uses HNSW for finding matches, the Sublime Palace Hotel drops to fourth position. Luxury Lion, which was second in the full-text search and third in the vector search, doesn't experience the same range of fluctuation, so it appears as a top match in a homogenized result set.
-
-```json
-"value": [
-    {
-        "@search.score": 0.857736,
-        "HotelId": "48",
-        "HotelName": "Nordick's Valley Motel",
-        "Description": "Only 90 miles (about 2 hours) from the nation's capital and nearby most everything the historic valley has to offer.  Hiking? Wine Tasting? Exploring the caverns?  It's all nearby and we have specially priced packages to help make our B&B your home base for fun while visiting the valley.",
-        "Category": "Boutique"
-    },
-    {
-        "@search.score": 0.8399129,
-        "HotelId": "49",
-        "HotelName": "Swirling Currents Hotel",
-        "Description": "Spacious rooms, glamorous suites and residences, rooftop pool, walking access to shopping, dining, entertainment and the city center.",
-        "Category": "Luxury"
-    },
-    {
-        "@search.score": 0.8383954,
-        "HotelId": "13",
-        "HotelName": "Luxury Lion Resort",
-        "Description": "Unmatched Luxury.  Visit our downtown hotel to indulge in luxury accommodations. Moments from the stadium, we feature the best in comfort",
-        "Category": "Resort and Spa"
-    },
+    Because Reciprocal Rank Fusion (RRF) merges results, it helps to review the inputs. The following results are from the full-text query only. The top two results are Sublime Palace Hotel and Luxury Lion Resort. The Sublime Palace Hotel has a stronger BM25 relevance score.
+
+    ```json
     {
-        "@search.score": 0.8254346,
-        "HotelId": "4",
+        "@search.score": 2.2626662,
         "HotelName": "Sublime Palace Hotel",
-        "Description": "Sublime Palace Hotel is located in the heart of the historic center of Sublime in an extremely vibrant and lively area within short walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments. Sublime Palace is part of a lovingly restored 1800 palace.",
-        "Category": "Boutique"
+        "Description": "Sublime Palace Hotel is located in the heart of the historic center of Sublime in an extremely vibrant and lively area within short walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments. Sublime Palace is part of a lovingly restored 1800 palace."
     },
     {
-        "@search.score": 0.82380056,
-        "HotelId": "1",
-        "HotelName": "Stay-Kay City Hotel",
-        "Description": "The hotel is ideally located on the main commercial artery of the city in the heart of New York.",
-        "Category": "Boutique"
-    },
-    {
-        "@search.score": 0.81514084,
-        "HotelId": "2",
-        "HotelName": "Old Century Hotel",
-        "Description": "The hotel is situated in a  nineteenth century plaza, which has been expanded and renovated to the highest architectural standards to create a modern, functional and first-class hotel in which art and unique historical elements coexist with the most modern comforts.",
-        "Category": "Boutique"
+        "@search.score": 0.86421645,
+        "HotelName": "Luxury Lion Resort",
+        "Description": "Unmatched Luxury.  Visit our downtown hotel to indulge in luxury accommodations. Moments from the stadium, we feature the best in comfort"
     },
-    {
-        "@search.score": 0.8133763,
-        "HotelId": "3",
-        "HotelName": "Gastronomic Landscape Hotel",
-        "Description": "The Hotel stands out for its gastronomic excellence under the management of William Dough, who advises on and oversees all of the Hotel’s restaurant services.",
-        "Category": "Resort and Spa"
-    }
-]
-```
+    ```
+
+    In the vector-only query, which uses HNSW for finding matches, the Sublime Palace Hotel drops to the fourth position. Luxury Lion, which was second in the full-text search and third in the vector search, doesn't experience the same range of fluctuation, so it appears as a top match in a homogenized result set.
+
+    ```json
+    "value": [
+        {
+            "@search.score": 0.857736,
+            "HotelId": "48",
+            "HotelName": "Nordick's Valley Motel",
+            "Description": "Only 90 miles (about 2 hours) from the nation's capital and nearby most everything the historic valley has to offer.  Hiking? Wine Tasting? Exploring the caverns?  It's all nearby and we have specially priced packages to help make our B&B your home base for fun while visiting the valley.",
+            "Category": "Boutique"
+        },
+        {
+            "@search.score": 0.8399129,
+            "HotelId": "49",
+            "HotelName": "Swirling Currents Hotel",
+            "Description": "Spacious rooms, glamorous suites and residences, rooftop pool, walking access to shopping, dining, entertainment and the city center.",
+            "Category": "Luxury"
+        },
+        {
+            "@search.score": 0.8383954,
+            "HotelId": "13",
+            "HotelName": "Luxury Lion Resort",
+            "Description": "Unmatched Luxury.  Visit our downtown hotel to indulge in luxury accommodations. Moments from the stadium, we feature the best in comfort",
+            "Category": "Resort and Spa"
+        },
+        {
+            "@search.score": 0.8254346,
+            "HotelId": "4",
+            "HotelName": "Sublime Palace Hotel",
+            "Description": "Sublime Palace Hotel is located in the heart of the historic center of Sublime in an extremely vibrant and lively area within short walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments. Sublime Palace is part of a lovingly restored 1800 palace.",
+            "Category": "Boutique"
+        },
+        {
+            "@search.score": 0.82380056,
+            "HotelId": "1",
+            "HotelName": "Stay-Kay City Hotel",
+            "Description": "The hotel is ideally located on the main commercial artery of the city in the heart of New York.",
+            "Category": "Boutique"
+        },
+        {
+            "@search.score": 0.81514084,
+            "HotelId": "2",
+            "HotelName": "Old Century Hotel",
+            "Description": "The hotel is situated in a  nineteenth century plaza, which has been expanded and renovated to the highest architectural standards to create a modern, functional and first-class hotel in which art and unique historical elements coexist with the most modern comforts.",
+            "Category": "Boutique"
+        },
+        {
+            "@search.score": 0.8133763,
+            "HotelId": "3",
+            "HotelName": "Gastronomic Landscape Hotel",
+            "Description": "The Hotel stands out for its gastronomic excellence under the management of William Dough, who advises on and oversees all of the Hotel’s restaurant services.",
+            "Category": "Resort and Spa"
+        }
+    ]
+    ```
 
 ### Semantic hybrid search with a filter
 
-The hybrid query with semantic ranking is filtered to show only the hotels within a 500-kilometer radius of Washington D.C.
+Add [semantic ranking](../../semantic-search-overview.md) to rerank results based on language understanding.
 
-1. In the `Program.cs` file of the `VectorSearchExamples` folder, uncomment the method call `SearchExamples.SearchHybridVectoryAndSemantic(searchClient, vectorizedResult);`. This method executes the following search function in the `SearchExamples.cs` class:
+To create a semantic hybrid search with a filter:
 
-    :::code language="csharp" source="~/azure-search-dotnet-samples/quickstart-vector-search/vectorsearchexamples/SearchExamples.cs" id="SearchHybridVectorAndSemantic":::
+1. In the `Program.cs` file, uncomment `SearchExamples.SearchHybridVectorAndSemantic(searchClient, vectorizedResult);` method call.
 
-1.  Run the project again, and review the output below the cell. The response is three hotels, which are filtered by location and faceted by `StateProvince` and semantically reranked to promote results that are closest to the search string query (`historic hotel walk to restaurants and shopping`).
+    This method executes the following search function in the `SearchExamples.cs` class.
 
-       The Swirling Currents Hotel now moves into the top spot. Without semantic ranking, Nordick's Valley Motel is number one. With semantic ranking, the machine comprehension models recognize that `historic` applies to "hotel, within walking distance to dining (restaurants) and shopping."
-    
-       ```output
-       Total semantic hybrid results: 7
-       - Score: 0.0317460335791111
-         Re-ranker Score: 2.6550590991973877
-         HotelId: 49
-         HotelName: Swirling Currents Hotel
-         Description: Spacious rooms, glamorous suites and residences, rooftop pool, walking access to shopping, dining, entertainment and the city center. Each room comes equipped with a microwave, a coffee maker and a minifridge. In-room entertainment includes complimentary Wi-Fi and flat-screen TVs.
-         Category: Suite
-       - Score: 0.03279569745063782
-         Re-ranker Score: 2.599761724472046
-         HotelId: 4
-         HotelName: Sublime Palace Hotel
-         Description: Sublime Palace Hotel is located in the heart of the historic center of Sublime in an extremely vibrant and lively area within short walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments. Sublime Cliff is part of a lovingly restored 19th century resort, updated for every modern convenience.
-         Category: Boutique
-       - Score: 0.03125
-         Re-ranker Score: 2.3480887413024902
-         HotelId: 2
-         HotelName: Old Century Hotel
-         Description: The hotel is situated in a nineteenth century plaza, which has been expanded and renovated to the highest architectural standards to create a modern, functional and first-class hotel in which art and unique historical elements coexist with the most modern comforts. The hotel also regularly hosts events like wine tastings, beer dinners, and live music.
-         Category: Boutique
-       - Score: 0.016393441706895828
-         Re-ranker Score: 2.2718777656555176
-         HotelId: 1
-         HotelName: Stay-Kay City Hotel
-         Description: This classic hotel is fully-refurbished and ideally located on the main commercial artery of the city in the heart of New York. A few minutes away is Times Square and the historic center of the city, as well as other places of interest that make New York one of America's most attractive and cosmopolitan cities.
-         Category: Boutique
-       - Score: 0.01515151560306549
-         Re-ranker Score: 2.0582215785980225
-         HotelId: 3
-         HotelName: Gastronomic Landscape Hotel
-         Description: The Gastronomic Hotel stands out for its culinary excellence under the management of William Dough, who advises on and oversees all of the Hotel’s restaurant services.
-         Category: Suite
-       ```
+    :::code language="csharp" source="~/azure-search-dotnet-samples/quickstart-vector-search/vectorsearchexamples/SearchExamples.cs" id="SearchHybridVectorAndSemantic":::
 
-Key takeaways:
+1. Run `dotnet run` to execute the query, which returns the following hotels. The hotels are filtered by location, faceted by `StateProvince`, and semantically reranked to promote results that are closest to the search string query (`historic hotel walk to restaurants and shopping`).
 
-- In a hybrid search, you can integrate vector search with full-text search over keywords. Filters, spell check, and semantic ranking apply to textual content only, and not vectors. In this final query, there's no semantic `answer` because the system didn't produce one that was sufficiently strong.
+    The Swirling Currents Hotel now moves to the top spot. Without semantic ranking, Nordick's Valley Motel is number one. With semantic ranking, the machine comprehension models recognize that `historic` applies to "hotel within walking distance to dining (restaurants) and shopping."
+    
+    ```output
+    Total semantic hybrid results: 7
+    - Score: 0.0317460335791111
+      Re-ranker Score: 2.6550590991973877
+      HotelId: 49
+      HotelName: Swirling Currents Hotel
+      Description: Spacious rooms, glamorous suites and residences, rooftop pool, walking access to shopping, dining, entertainment and the city center. Each room comes equipped with a microwave, a coffee maker and a minifridge. In-room entertainment includes complimentary Wi-Fi and flat-screen TVs.
+      Category: Suite
+    - Score: 0.03279569745063782
+      Re-ranker Score: 2.599761724472046
+      HotelId: 4
+      HotelName: Sublime Palace Hotel
+      Description: Sublime Palace Hotel is located in the heart of the historic center of Sublime in an extremely vibrant and lively area within short walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments. Sublime Cliff is part of a lovingly restored 19th century resort, updated for every modern convenience.
+      Category: Boutique
+    - Score: 0.03125
+      Re-ranker Score: 2.3480887413024902
+      HotelId: 2
+      HotelName: Old Century Hotel
+      Description: The hotel is situated in a nineteenth century plaza, which has been expanded and renovated to the highest architectural standards to create a modern, functional and first-class hotel in which art and unique historical elements coexist with the most modern comforts. The hotel also regularly hosts events like wine tastings, beer dinners, and live music.
+      Category: Boutique
+    - Score: 0.016393441706895828
+      Re-ranker Score: 2.2718777656555176
+      HotelId: 1
+      HotelName: Stay-Kay City Hotel
+      Description: This classic hotel is fully-refurbished and ideally located on the main commercial artery of the city in the heart of New York. A few minutes away is Times Square and the historic center of the city, as well as other places of interest that make New York one of America's most attractive and cosmopolitan cities.
+      Category: Boutique
+    - Score: 0.01515151560306549
+      Re-ranker Score: 2.0582215785980225
+      HotelId: 3
+      HotelName: Gastronomic Landscape Hotel
+      Description: The Gastronomic Hotel stands out for its culinary excellence under the management of William Dough, who advises on and oversees all of the Hotel's restaurant services.
+      Category: Suite
+    ```
+    
+    Key takeaways:
 
-- Actual results include more detail, including semantic captions and highlights. Results were modified for readability. To get the full structure of the response, run the request in the REST client.
+    + In a hybrid search, you can integrate vector search with full-text search over keywords. Filters, spell check, and semantic ranking apply to textual content only, and not vectors. In this final query, there's no semantic `answer` because the system didn't produce one that was sufficiently strong.
+    
+    + Actual results include more detail, including semantic captions and highlights. Results were modified for readability. To get the full structure of the response, run the request in the REST client.
 
-## Clean up
+## Clean up resources
 
 When you're working in your own subscription, it's a good idea at the end of a project to identify whether you still need the resources you created. Resources left running can cost you money. You can delete resources individually or delete the resource group to delete the entire set of resources.
 
 You can find and manage resources in the Azure portal by using the **All resources** or **Resource groups** link in the leftmost pane.
 
 ## Next steps
 
-- Review the repository of code samples for vector search capabilities in Azure AI Search for [.NET](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-dotnet)
-- Review the other .NET and Azure AI Search code samples in the [azure-search-dotnet-samples repo](https://github.com/Azure-Samples/azure-search-dotnet-samples)
\ No newline at end of file
++ Review the repository of code samples for vector search capabilities in Azure AI Search for [.NET](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-dotnet).
++ Review the other .NET and Azure AI Search code samples in the [azure-search-dotnet-samples repo](https://github.com/Azure-Samples/azure-search-dotnet-samples).

@@ -2,36 +2,41 @@
 author: KarlErickson
 ms.author: karler
 ms.service: azure-ai-search
-ms.custom: devx-track-java
+ms.custom: devx-track-java, dev-focus
 ms.topic: include
-ms.date: 12/15/2025
+ms.date: 01/14/2026
 ai-usage: ai-assisted
 ---
 
-In this quickstart, you use Java to create, load, and query vectors. The code examples perform these operations by using the [Azure AI Search client library](/java/api/overview/azure/search-documents-readme). The library provides an abstraction over the REST API for access to index operations such as data ingestion, search operations, and index management operations.
+In this quickstart, you use Java to create, load, and query a [vector index](../../vector-store.md). The code performs these operations by using the [Azure AI Search client library for Java](/java/api/overview/azure/search-documents-readme), which provides an abstraction over the REST APIs to access index operations.
 
-In Azure AI Search, a [vector store](../../vector-store.md) has an index schema that defines vector and nonvector fields, a vector search configuration for algorithms that create the embedding space, and settings on vector field definitions that are evaluated at query time. The [Create Index](/rest/api/searchservice/indexes/create-or-update) REST API creates the vector store.
+In Azure AI Search, a vector index has an index schema that defines vector and nonvector fields, a vector search configuration for algorithms that create the embedding space, and settings on vector field definitions that are evaluated at query time. [Indexes - Create or Update](/rest/api/searchservice/indexes/create-or-update) (REST API) creates the vector index.
 
 > [!NOTE]
 > This quickstart omits the vectorization step and provides inline embeddings. If you want to add [built-in data chunking and vectorization](../../vector-search-integrated-vectorization.md) over your own content, try the [**Import data (new)** wizard](../../search-get-started-portal-import-vectors.md) for an end-to-end walkthrough.
 
 ## Prerequisites
 
-- An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
++ An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
 
-- An Azure AI Search service. [Create a service](../../search-create-service-portal.md) or [find an existing service](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/CognitiveSearch) in your current subscription.
-    - The `Search Index Data Contributor` role assigned at the scope of the service.
-    - You can use a free search service for most of this quickstart, but we recommend the Basic tier or higher for larger data files.
-    - To run the query example that invokes [semantic reranking](../../semantic-search-overview.md), your search service must have [semantic ranker enabled](../../semantic-how-to-enable-disable.md).
++ An [Azure AI Search service](../../search-create-service-portal.md).
 
-- [Java 21 (LTS)](/java/openjdk/install).
+    + You can use the Free tier for most of this quickstart, but we recommend Basic or higher for larger data files.
 
-- [Maven](https://maven.apache.org/download.cgi).
+    + For [keyless authentication](../../search-get-started-rbac.md) with Microsoft Entra ID, assign the **Search Index Data Contributor role** to your user account.
+    
+    + To run the semantic hybrid query, you must [enable semantic ranker](../../semantic-how-to-enable-disable.md).
+
++ [Java 21 (LTS)](/java/openjdk/install).
+
++ [Maven](https://maven.apache.org/download.cgi).
 
-## Get service endpoints
+## Get service information
 
 In the remaining sections, you set up API calls to Azure OpenAI and Azure AI Search. Get the service endpoints so that you can provide them as variables in your code.
 
+To get the service endpoint:
+
 1. Sign in to the [Azure portal](https://portal.azure.com).
 
 1. [Find your search service](https://portal.azure.com/#blade/HubsExtension/BrowseResourceBlade/resourceType/Microsoft.Search%2FsearchServices).
@@ -48,7 +53,7 @@ In the remaining sections, you set up API calls to Azure OpenAI and Azure AI Sea
 
 1. Create a `pom.xml` file with required dependencies.
 
-   :::code language="xml" source="~/azure-search-java-samples/vector-quickstart/pom.xml" :::
+   :::code language="xml" source="~/azure-search-java-samples/quickstart-vector-search/pom.xml" :::
 
 1. Compile the project to resolve the dependencies.
 
@@ -86,25 +91,27 @@ az login --tenant <PUT YOUR TENANT ID HERE>
 
 You should now be logged in to Azure from your local device.
 
-## Create the vector index
+## Create a vector index
 
 In this section, you create a vector index in Azure AI Search with [SearchIndexClient](/java/api/com.azure.search.documents.indexes.searchindexclient).[createOrUpdateIndex](/java/api/com.azure.search.documents.indexes.searchindexclient#com-azure-search-documents-indexes-searchindexclient-createorupdateindex(com-azure-search-documents-indexes-models-searchindex)). The index schema defines the fields, including the vector field `DescriptionVector`.
 
-1. Create a `CreateIndex.java` file in the the `src/main/java/com/example/search` directory.
+To create a vector index:
+
+1. Create a `CreateIndex.java` file in the `src/main/java/com/example/search` directory.
 
 1. Copy the following code into the file.
 
-   :::code language="java" source="~/azure-search-java-samples/vector-quickstart/src/main/java/com/example/search/CreateIndex.java" :::
+   :::code language="java" source="~/azure-search-java-samples/quickstart-vector-search/src/main/java/com/example/search/CreateIndex.java" :::
 
-   The code file creates the index and defines the index schema, including the vector field `DescriptionVector`.
+   The code file creates the index and defines the index schema, including the `DescriptionVector` vector field.
 
 1. Run the file.
 
     ```bash
     mvn compile exec:java -Dexec.mainClass="com.example.search.CreateIndex"
     ```
 
-1. The output of this code shows that the index is created successfully:
+    The output of this code shows that the index is created successfully.
 
     ```output
     Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -113,29 +120,37 @@ In this section, you create a vector index in Azure AI Search with [SearchIndexC
     hotels-vector-quickstart created
     ```
 
-   Key takeaways when creating vector index with the `azure-search-documents` library:
+   Key takeaways:
+
+   + You define an index by creating a list of fields.
+
+   + This particular index supports multiple search capabilities, such as:
+
+      + Full-text keyword search (`setSearchable`)
+
+      + Vector search (enables hybrid search by collocating vector and nonvector fields) fields (`DescriptionVector` with `setVectorSearchProfileName`)
+      
+      + Semantic search 
+
+      + Faceted search (`SearchSuggester`)
 
-   - You define an index by creating a list of fields.
+      + Geo-spatial search (`Location` field with `SearchFieldDataType.GEOGRAPHY_POINT`)
 
-   - This particular index supports multiple search capabilities, such as:
-      - Full-text keyword search (`setSearchable`)
-      - Vector search (enables hybrid search by collocating vector and nonvector fields) fields (`DescriptionVector` with `setVectorSearchProfileName`)
-      - Semantic search 
-      - Faceted search (`SearchSuggester`)
-      - Geo-spatial search (`Location` field with `SearchFieldDataType.GEOGRAPHY_POINT`)
-      - Filtering, sorting (Many fields marked filterable and sortable)
+      + Filtering, sorting (many fields marked filterable and sortable)
 
 ## Upload documents to the index
 
-Creating and loading the index are separate steps. You created the index schema in the [previous step](#create-the-vector-index). Now you need to load documents into the index with [SearchClient](/java/api/com.azure.search.documents.searchclient).[uploadDocuments](/java/api/com.azure.search.documents.searchclient#com-azure-search-documents-searchclient-uploaddocuments(java-lang-iterable(-))). The documents contain the vectorized version of the article's description, which enables similarity search based on meaning rather than exact keywords.
+Creating and loading the index are separate steps. You created the index schema in the previous step. You now need to load documents into the index with [SearchClient](/java/api/com.azure.search.documents.searchclient).[uploadDocuments](/java/api/com.azure.search.documents.searchclient#com-azure-search-documents-searchclient-uploaddocuments(java-lang-iterable(-))). The documents contain the vectorized version of the article's description, which enables similarity search based on meaning rather than exact keywords.
 
 In Azure AI Search, the index stores all searchable content, while the search engine executes queries against that index.
 
+To upload documents to the index:
+
 1. Create an `UploadDocuments.java` file in the `src/main/java/com/example/search` directory.
 
 1. Copy the following code into the file.
 
-   :::code language="java" source="~/azure-search-java-samples/vector-quickstart/src/main/java/com/example/search/UploadDocuments.java" :::
+   :::code language="java" source="~/azure-search-java-samples/quickstart-vector-search/src/main/java/com/example/search/UploadDocuments.java" :::
 
     This code loads a collection of documents. Each document includes the vectorized version of the article's `Description`. This vector enables similarity search, where matching is based on meaning rather than exact keywords.
 
@@ -147,7 +162,7 @@ In Azure AI Search, the index stores all searchable content, while the search en
     mvn compile exec:java -Dexec.mainClass="com.example.search.UploadDocuments"
     ```
 
-1. The output of this code shows that the documents are indexed and ready for search:
+    The output of this code shows that the documents are indexed and ready for search.
 
     ```output
     Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -164,37 +179,42 @@ In Azure AI Search, the index stores all searchable content, while the search en
     All documents indexed successfully.
     ```
 
-    Key takeaways about the `uploadDocuments` method and this example:
+    Key takeaways:
 
     * Your code interacts with a specific search index hosted in your Azure AI Search service through the `SearchClient`. The `SearchClient` provides access to operations such as:
-        * Data ingestion - `uploadDocuments`, `mergeDocuments`, `deleteDocuments`, and so on.
-        * Search operations - `search`, `autocomplete`, `suggest`
-    * Vector fields contain floating point values. The dimensions attribute has a minimum of 2 and a maximum of 4096 floating point values each. This quickstart sets the dimensions attribute to 1,536 because that's the size of embeddings generated by the Azure OpenAI `text-embedding-ada-002` model.
+
+        * Data ingestion: `uploadDocuments`, `mergeDocuments`, `deleteDocuments`, and so on.
+
+        * Search operations: `search`, `autocomplete`, `suggest`
+
+    * Vector fields contain floating point values. The dimensions attribute has a minimum of 2 and a maximum of 4096 floating point values each. This quickstart sets the dimensions attribute to 1,536 because that's the size of embeddings generated by the `text-embedding-ada-002` model.
 
 ## Create the query as a vector
 
 The example vector queries are based on two strings:
 
-- **Search string**: `historic hotel walk to restaurants and shopping`
-- **Vector query string** (vectorized into a mathematical representation): `quintessential lodging near running trails, eateries, retail`
++ Search string: `historic hotel walk to restaurants and shopping`
++ Vector query string: `quintessential lodging near running trails, eateries, retail` (vectorized into a mathematical representation)
 
 The vector query string is semantically similar to the search string, but it includes terms that don't exist in the search index. If you do a keyword search for `quintessential lodging near running trails, eateries, retail`, results are zero. We use this example to show how you can get relevant results even if there are no matching terms.
 
 Create a `QueryVector.java` file in the `src/main/java/com/example/search` directory and add the code to create the query vector.
 
-:::code language="java" source="~/azure-search-java-samples/vector-quickstart/src/main/java/com/example/search/QueryVector.java" :::
+:::code language="java" source="~/azure-search-java-samples/quickstart-vector-search/src/main/java/com/example/search/QueryVector.java" :::
 
 This code is used in the following sections to perform vector searches. The query vector is created using an embedding model from Azure OpenAI.
 
 ## Create a single vector search
 
 The first example demonstrates a basic scenario where you want to find document descriptions that closely match the search string using the [SearchClient](/java/api/com.azure.search.documents.searchclient).[search](/java/api/com.azure.search.documents.searchasyncclient#com-azure-search-documents-searchasyncclient-search(java-lang-string)) and the [VectorQuery](/java/api/com.azure.search.documents.models.vectorquery) and [SearchOptions](/java/api/com.azure.search.documents.models.searchoptions).
 
+To create a single vector search:
+
 1. Create a `SearchSingle.java` file in the `src/main/java/com/example/search` directory.
 
 1. Copy the following code into the file.
 
-    :::code language="java" source="~/azure-search-java-samples/vector-quickstart/src/main/java/com/example/search/SearchSingle.java" :::
+    :::code language="java" source="~/azure-search-java-samples/quickstart-vector-search/src/main/java/com/example/search/SearchSingle.java" :::
 
     The `vectorQuery` contains the configuration of the vectorized query including the vectorized text of the query input as retrieved through `QueryVector.getVectorList`. `setFields` determines which vector fields are searched and `setKNearestNeighborsCount` specifies the number of nearest neighbors to return.
 
@@ -206,7 +226,7 @@ The first example demonstrates a basic scenario where you want to find document
     mvn compile exec:java -Dexec.mainClass="com.example.search.SearchSingle"
     ```
 
-1. The output of this code shows the relevant docs for the query `quintessential lodging near running trails, eateries, retail`.
+    The output of this code shows the relevant docs for the query `quintessential lodging near running trails, eateries, retail`.
 
     ```output
     Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -226,11 +246,13 @@ The first example demonstrates a basic scenario where you want to find document
 
 You can add filters, but the filters are applied to the nonvector content in your index. In this example, the filter applies to the `Tags` field to filter out any hotels that don't provide free Wi-Fi. This search uses [SearchClient](/java/api/com.azure.search.documents.searchclient).[SearchClient](/java/api/com.azure.search.documents.searchclient) and [SearchOptions](/java/api/com.azure.search.documents.models.searchoptions). 
 
+To create a single vector search with a filter:
+
 1. Create a `SearchSingleWithFilter.java` file in the `src/main/java/com/example/search` directory.
 
 1. Copy the following code into the file.
 
-    :::code language="java" source="~/azure-search-java-samples/vector-quickstart/src/main/java/com/example/search/SearchSingleWithFilter.java" :::
+    :::code language="java" source="~/azure-search-java-samples/quickstart-vector-search/src/main/java/com/example/search/SearchSingleWithFilter.java" :::
 
     This code has the same search functionality as the previous search, but it adds a post-processing exclusion filter for hotels with `free wifi`.
 
@@ -240,7 +262,7 @@ You can add filters, but the filters are applied to the nonvector content in you
     mvn compile exec:java -Dexec.mainClass="com.example.search.SearchSingleWithFilter"
     ```
 
-1. The output of this code shows the relevant documents for the query with the filter for `free wifi` applied:
+    The output of this code shows the relevant documents for the query with the filter for `free wifi` applied.
 
     ```output
     Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -255,19 +277,21 @@ You can add filters, but the filters are applied to the nonvector content in you
 
 You can specify a geospatial filter to limit results to a specific geographic area. In this example, the filter limits results to hotels within 300 kilometers of Washington D.C. (coordinates: `-77.03241 38.90166`). Geospatial distances are always in kilometers. This search uses [SearchClient](/java/api/com.azure.search.documents.searchclient).[SearchClient](/java/api/com.azure.search.documents.searchclient) and [SearchOptions](/java/api/com.azure.search.documents.models.searchoptions).
 
+To create a single vector search with a geospatial filter:
+
 1. Create a `SearchSingleWithFilterGeo.java` file in the `src/main/java/com/example/search` directory.
 
 1. Copy the following code into the file.
 
-    :::code language="java" source="~/azure-search-java-samples/vector-quickstart/src/main/java/com/example/search/SearchSingleWithFilterGeo.java" :::
+    :::code language="java" source="~/azure-search-java-samples/quickstart-vector-search/src/main/java/com/example/search/SearchSingleWithFilterGeo.java" :::
 
 1. Build and run the file.
 
     ```bash
     mvn compile exec:java -Dexec.mainClass="com.example.search.SearchSingleWithFilterGeo"
     ```
 
-1. The output of this code shows the relevant documents for the query with the geospatial post-processing exclusion filter applied.
+    The output of this code shows the relevant documents for the query with the geospatial post-processing exclusion filter applied.
 
     ```output
     Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -280,26 +304,28 @@ You can specify a geospatial filter to limit results to a specific geographic ar
 
 ## Create a hybrid search
 
-Hybrid search consists of keyword queries and vector queries in a single search request. This example runs the vector query and full-text search concurrently:
+[Hybrid search](../../hybrid-search-overview.md) combines keyword and vector queries in one request. This example runs the following full-text and vector query strings concurrently:
 
-- **Search string**: `historic hotel walk to restaurants and shopping`
-- **Vector query string** (vectorized into a mathematical representation): `quintessential lodging near running trails, eateries, retail`
++ Search string: `historic hotel walk to restaurants and shopping`
++ Vector query string: `quintessential lodging near running trails, eateries, retail` (vectorized into a mathematical representation)
 
 This search uses [SearchClient](/java/api/com.azure.search.documents.searchclient).[SearchClient](/java/api/com.azure.search.documents.searchclient) and [SearchOptions](/java/api/com.azure.search.documents.models.searchoptions).
 
+Tp create a hybrid search:
+
 1. Create a `SearchHybrid.java` file in the `src/main/java/com/example/search` directory.
 
 1. Copy the following code into the file.
 
-    :::code language="java" source="~/azure-search-java-samples/vector-quickstart/src/main/java/com/example/search/SearchHybrid.java" :::
+    :::code language="java" source="~/azure-search-java-samples/quickstart-vector-search/src/main/java/com/example/search/SearchHybrid.java" :::
 
 1. Build and run the file.
 
     ```bash
     mvn compile exec:java -Dexec.mainClass="com.example.search.SearchHybrid"
     ```
 
-1. The output of this code shows the relevant documents for the hybrid search.
+    The output of this code shows the relevant documents for the hybrid search.
 
     ```output
     Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -342,7 +368,7 @@ This search uses [SearchClient](/java/api/com.azure.search.documents.searchclien
       Tags: ["pool","free wifi","air conditioning","concierge"]
     ```
 
-    Because Reciprocal Rank Fusion (RRF) merges results, it helps to review the inputs. The following results are from only the full-text query. The top two results are Sublime Palace Hotel and Luxury Lion Resort. The Sublime Palace Hotel has a stronger BM25 relevance score.
+    Because Reciprocal Rank Fusion (RRF) merges results, it helps to review the inputs. The following results are from the full-text query only. The top two results are Sublime Palace Hotel and Luxury Lion Resort. The Sublime Palace Hotel has a stronger BM25 relevance score.
 
     ```json
        {
@@ -357,7 +383,7 @@ This search uses [SearchClient](/java/api/com.azure.search.documents.searchclien
        },
     ```
 
-    In the vector-only query, which uses HNSW for finding matches, the Sublime Palace Hotel drops to fourth position. Luxury Lion, which was second in the full-text search and third in the vector search, doesn't experience the same range of fluctuation, so it appears as a top match in a homogenized result set.
+    In the vector-only query, which uses HNSW for finding matches, the Sublime Palace Hotel drops to the fourth position. Luxury Lion, which was second in the full-text search and third in the vector search, doesn't experience the same range of fluctuation, so it appears as a top match in a homogenized result set.
 
    ```json
    "value": [
@@ -419,19 +445,21 @@ Here's the last query in the collection to extend the semantic hybrid search wit
 
 This search uses [SearchClient](/java/api/com.azure.search.documents.searchclient).[SearchClient](/java/api/com.azure.search.documents.searchclient) and [SearchOptions](/java/api/com.azure.search.documents.models.searchoptions). 
 
+To create a semantic hybrid search:
+
 1. Create a `SearchSemanticHybrid.java` file in the `src/main/java/com/example/search` directory.
 
 1. Copy the following code into the file.
 
-    :::code language="java" source="~/azure-search-java-samples/vector-quickstart/src/main/java/com/example/search/SearchSemanticHybrid.java" :::
+    :::code language="java" source="~/azure-search-java-samples/quickstart-vector-search/src/main/java/com/example/search/SearchSemanticHybrid.java" :::
 
 1. Build and run the file.
 
     ```bash
     mvn compile exec:java -Dexec.mainClass="com.example.search.SearchSemanticHybrid"
     ```
 
-1. The output of this code shows the relevant documents for the semantic hybrid search.
+    The output of this code shows the relevant documents for the semantic hybrid search.
 
     ```output
     Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -484,19 +512,19 @@ This search uses [SearchClient](/java/api/com.azure.search.documents.searchclien
 
     - Actual results include more detail, including semantic captions and highlights. Results were modified for readability. To get the full structure of the response, run the request in the REST client.
 
-## Clean up
+## Clean up resources
 
 When you're working in your own subscription, it's a good idea at the end of a project to identify whether you still need the resources you created. Resources left running can cost you money. You can delete resources individually or delete the resource group to delete the entire set of resources.
 
 You can find and manage resources in the Azure portal by using the **All resources** or **Resource groups** link in the leftmost pane.
 
-If you want to keep your search service but delete the index and its documents, you can delete the index programmatically.
+Alternatively, to delete the vector index you created in this quickstart programmatically:
 
 1. Create a `DeleteIndex.java` file in the `src/main/java/com/example/search` directory.
 
 1. Add the following code to the file.
 
-    :::code language="java" source="~/azure-search-java-samples/vector-quickstart/src/main/java/com/example/search/DeleteIndex.java" :::
+    :::code language="java" source="~/azure-search-java-samples/quickstart-vector-search/src/main/java/com/example/search/DeleteIndex.java" :::
 
 1. Build and run the file.
 
@@ -506,4 +534,4 @@ If you want to keep your search service but delete the index and its documents,
 
 ## Next steps
 
-- Review the repository of code samples for vector search capabilities in Azure AI Search for [Java](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-java)
++ Review the repository of code samples for vector search capabilities in Azure AI Search for [Java](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-java).

@@ -4,44 +4,48 @@ author: diberry
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 11/20/2025
+ms.date: 01/14/2026
+ms.custom: dev-focus
+ai-usage: ai-assisted
 ---
 
-In this quickstart, you use JavaScript to create, load, and query vectors. The code examples perform these operations by using the [Azure AI Search client library](/javascript/api/overview/azure/search-documents-readme). The library provides an abstraction over the REST API for access to index operations such as data ingestion, search operations, and index management operations.
+In this quickstart, you use JavaScript to create, load, and query a [vector index](../../vector-store.md). The code performs these operations by using the [Azure AI Search client library for JavaScript](/javascript/api/overview/azure/search-documents-readme), which provides an abstraction over the REST APIs to access index operations.
 
-In Azure AI Search, a [vector store](../../vector-store.md) has an index schema that defines vector and nonvector fields, a vector search configuration for algorithms that create the embedding space, and settings on vector field definitions that are evaluated at query time. The [Create Index](/rest/api/searchservice/indexes/create-or-update) REST API creates the vector store.
+In Azure AI Search, a vector index has an index schema that defines vector and nonvector fields, a vector search configuration for algorithms that create the embedding space, and settings on vector field definitions that are evaluated at query time. [Indexes - Create or Update](/rest/api/searchservice/indexes/create-or-update) (REST API) creates the vector index.
 
 > [!NOTE]
 > This quickstart omits the vectorization step and provides inline embeddings. If you want to add [built-in data chunking and vectorization](../../vector-search-integrated-vectorization.md) over your own content, try the [**Import data (new)** wizard](../../search-get-started-portal-import-vectors.md) for an end-to-end walkthrough.
 
 ## Prerequisites
 
-- An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
++ An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
 
-- An Azure AI Search service. [Create a service](../../search-create-service-portal.md) or [find an existing service](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/CognitiveSearch) in your current subscription.
-    - The `Search Index Data Contributor` role assigned at the scope of the service.
-    - You can use a free search service for most of this quickstart, but we recommend the Basic tier or higher for larger data files.
-    - To run the query example that invokes [semantic reranking](../../semantic-search-overview.md), your search service must have [semantic ranker enabled](../../semantic-how-to-enable-disable.md).
++ An [Azure AI Search service](../../search-create-service-portal.md).
 
-- [Visual Studio Code](https://code.visualstudio.com/download).
+    + You can use the Free tier for most of this quickstart, but we recommend Basic or higher for larger data files.
 
-- [Node.JS with LTS](https://nodejs.org/en/download/).
+    + For [keyless authentication](../../search-get-started-rbac.md) with Microsoft Entra ID, assign the **Search Index Data Contributor role** to your user account.
+    
+    + To run the semantic hybrid query, you must [enable semantic ranker](../../semantic-how-to-enable-disable.md).
+
++ [Visual Studio Code](https://code.visualstudio.com/download).
+
++ [Node.JS with LTS](https://nodejs.org/en/download/).
 
 ## Get service endpoints
 
 In the remaining sections, you set up API calls to Azure OpenAI and Azure AI Search. Get the service endpoints so that you can provide them as variables in your code.
 
+To get the service endpoint:
+
 1. Sign in to the [Azure portal](https://portal.azure.com).
 
 1. [Find your search service](https://portal.azure.com/#blade/HubsExtension/BrowseResourceBlade/resourceType/Microsoft.Search%2FsearchServices).
 
-1. On the **Overview** home page, copy the URL. An example endpoint might look like `https://example.search.windows.net`. 
-
+1. On the **Overview** home page, copy the URL. An example endpoint might look like `https://example.search.windows.net`.
 
 ## Set up the Node.JS project
 
-Set up project with Visual Studio Code and JavaScript.
-
 1. Start Visual Studio Code in a new directory.
 
    ```bash
@@ -57,8 +61,7 @@ Set up project with Visual Studio Code and JavaScript.
 
    This creates a `package.json` file with default values.
 
-
-1. Install the following npm packages.
+1. Install the following `npm` packages.
 
    ```bash
    npm install @azure/identity @azure/search-documents dotenv
@@ -73,6 +76,7 @@ Set up project with Visual Studio Code and JavaScript.
 ## Set up environment variables for local development
 
 1. Create a `.env` file in your `vector-quickstart` project directory.
+
 1. Add the following environment variables to the `.env` file, replacing the values with your own service endpoints and keys.
 
    ```plaintext
@@ -95,11 +99,12 @@ az login --tenant <PUT YOUR TENANT ID HERE>
 
 You should now be logged in to Azure from your local device.
 
-
-## Create the vector index 
+## Create a vector index
 
 In this section, you create a vector index in Azure AI Search with [SearchIndexClient](/javascript/api/@azure/search-documents/searchindexclient).[createOrUpdateIndex](/javascript/api/@azure/search-documents/searchindexclient#@azure-search-documents-searchindexclient-createorupdateindex). The index schema defines the fields, including the vector field `DescriptionVector`. 
 
+To create a vector index:
+
 1. Create a `createIndex.js` file in the `src` directory.
 
 1. Copy the following code into the file. 
@@ -108,12 +113,13 @@ In this section, you create a vector index in Azure AI Search with [SearchIndexC
 
     The code file adds the dependencies, environment variables, and JavaScript type for `HotelDocument` to the top of the file. Add the `createIndex` function to create the index. The function defines the index schema, including the vector field `DescriptionVector`.
 
-1. Run the file:
+1. Run the file.
 
     ```bash
     node -r dotenv/config src/createIndex.js
     ```
-1. The output of this code shows that the index is created successfully:
+
+   The output of this code shows that the index is created successfully.
 
     ```output
     Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -122,25 +128,32 @@ In this section, you create a vector index in Azure AI Search with [SearchIndexC
     hotels-vector-quickstart created
     ```
 
-   Key takeaways when creating vector index with the `@azure/search-documents` library:
+   Key takeaways:
+
+   + You define an index by creating a list of fields. 
+
+   + This particular index supports multiple search capabilities, such as:
 
-   - You define an index by creating a list of fields. 
+      + Full-text keyword search (`searchable`)
 
-   - This particular index supports multiple search capabilities, such as:
-      - Full-text keyword search (`searchable`)
-      - Vector search (enables hybrid search by collocating vector and nonvector fields) fields (`DescriptionVector` with `vectorSearchProfileName`)
-      - Semantic search 
-      - Faceted search (`searchSuggester`)
-      - Geo-spatial search (`Location` field with `geo.distance`)
-      - Filtering, sorting (Many fields marked filterable and sortable)
+      + Vector search (enables hybrid search by collocating vector and nonvector fields) fields (`DescriptionVector` with `vectorSearchProfileName`)
 
+      + Semantic search 
+
+      + Faceted search (`searchSuggester`)
+
+      + Geo-spatial search (`Location` field with `geo.distance`)
+
+      + Filtering, sorting (many fields marked filterable and sortable)
 
 ## Upload documents to the index
 
-Creating and loading the index are separate steps. You created the index schema in the [previous step](#create-the-vector-index). Now you need to load documents into the index with [SearchClient](/javascript/api/@azure/search-documents/searchclient).[uploadDocuments](/javascript/api/%40azure/search-documents/searchclient#@azure-search-documents-searchclient-uploaddocuments). The documents contain the vectorized version of the article's description, which enables similarity search based on meaning rather than exact keywords.
+Creating and loading the index are separate steps. You created the index schema in the previous step. You now need to load documents into the index with [SearchClient](/javascript/api/@azure/search-documents/searchclient).[uploadDocuments](/javascript/api/%40azure/search-documents/searchclient#@azure-search-documents-searchclient-uploaddocuments). The documents contain the vectorized version of the article's description, which enables similarity search based on meaning rather than exact keywords.
 
 In Azure AI Search, the index stores all searchable content, while the search engine executes queries against that index.
 
+To upload documents to the index:
+
 1. Create an `uploadDocuments.js` file in the `src` directory.
 1. Copy the following code into the file.
 
@@ -150,12 +163,13 @@ In Azure AI Search, the index stores all searchable content, while the search en
 
     Because this quickstart article searches the index immediately, the `waitUntilIndexed` function waits until the index is ready for search operations. This is important because the index needs to be fully populated with documents before you can perform searches.
 
-1. Build and run the file:
+1. Build and run the file.
 
     ```bash
     node -r dotenv/config src/uploadDocuments.js
     ```
-1. The output of this code shows that the documents are indexed and ready for search:
+
+   The output of this code shows that the documents are indexed and ready for search.
 
     ```output
     Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -172,34 +186,39 @@ In Azure AI Search, the index stores all searchable content, while the search en
     All documents indexed successfully.
     ```
 
-    Key takeaways about the uploadDocuments() method and this example:
-    
-    * Your code interacts with a specific search index hosted in your Azure AI Search service through the SearchClient, which is the main object provided by the @azure/search-documents package. The SearchClient provides access to index operations such as:
-        * Data ingestion - uploadDocuments(), mergeDocuments(), deleteDocuments(), etc.
-        * Search operations - search(), autocomplete(), suggest()
-        * Index management operations such as createIndex(), deleteIndex(), getIndex(), etc.
-    * Vector fields contain floating point values. The dimensions attribute has a minimum of 2 and a maximum of 4096 floating point values each. This quickstart sets the dimensions attribute to 1,536 because that's the size of embeddings generated by the Azure OpenAI text-embedding-ada-002 model.
+    Key takeaways:
+
+    * Your code interacts with a specific search index hosted in your Azure AI Search service through the `SearchClient`, which is the main object provided by the @azure/search-documents package. The `SearchClient` provides access to index operations, such as:
+
+        * Data ingestion: `uploadDocuments`, `mergeDocuments`, `deleteDocuments`, and so on.
+
+        * Search operations: `search`, `autocomplete`, `suggest`
+
+        * Index management operations: `createIndex`, `deleteIndex`, `getIndex`, and so on.
+
+    * Vector fields contain floating point values. The dimensions attribute has a minimum of 2 and a maximum of 4096 floating point values each. This quickstart sets the dimensions attribute to 1,536 because that's the size of embeddings generated by the `text-embedding-ada-002` model.
 
 ## Create the query as a vector
 
 The example vector queries are based on two strings:
 
-- **Search string**: `historic hotel walk to restaurants and shopping`
-- **Vector query string** (vectorized into a mathematical representation): `quintessential lodging near running trails, eateries, retail`
++ Search string: `historic hotel walk to restaurants and shopping`
++ Vector query string: `quintessential lodging near running trails, eateries, retail` (vectorized into a mathematical representation)
 
 The vector query string is semantically similar to the search string, but it includes terms that don't exist in the search index. If you do a keyword search for `quintessential lodging near running trails, eateries, retail`, results are zero. We use this example to show how you can get relevant results even if there are no matching terms.
 
-1. Create a `queryVector.js` file in the `src` directory and add the code to create the query vector.
+Create a `queryVector.js` file in the `src` directory and add the code to create the query vector.
 
-    :::code language="javascript" source="~/azure-search-javascript-samples/quickstart-vector-js/src/queryVector.js" :::
-
-1. This code is used in the following sections to perform vector searches. The query vector is created using an embedding model from Azure OpenAI.
+:::code language="javascript" source="~/azure-search-javascript-samples/quickstart-vector-js/src/queryVector.js" :::
 
+This code is used in the following sections to perform vector searches. The query vector is created using an embedding model from Azure OpenAI.
 
 ## Create a single vector search
 
 The first example demonstrates a basic scenario where you want to find document descriptions that closely match the search string using the [SearchClient](/javascript/api/@azure/search-documents/searchclient).[search](/javascript/api/@azure/search-documents/searchclient#@azure-search-documents-searchclient-search) and the [VectorQuery](/javascript/api/@azure/search-documents/vectorquery) and [SearchOptions](/javascript/api/@azure/search-documents/searchoptions).
 
+To create a single vector search:
+
 1. Create a `searchSingle.js` file in the `src` directory.
 
 1. Copy the following code into the file.
@@ -210,13 +229,13 @@ The first example demonstrates a basic scenario where you want to find document
 
     The vector query string is `quintessential lodging near running trails, eateries, retail`, which is vectorized into 1,536 embeddings for this query.
 
-1. Build and run the file:
+1. Build and run the file.
 
     ```bash
     node -r dotenv/config src/searchSingle.js
     ```
 
-1. The output of this code shows the relevant docs for the query `quintessential lodging near running trails, eateries, retail`. 
+   The output of this code shows the relevant docs for the query `quintessential lodging near running trails, eateries, retail`.
 
     ```output
     Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -238,6 +257,8 @@ The first example demonstrates a basic scenario where you want to find document
 
 You can add filters, but the filters are applied to the nonvector content in your index. In this example, the filter applies to the `Tags` field to filter out any hotels that don't provide free Wi-Fi. This search uses [SearchClient](/javascript/api/@azure/search-documents/searchclient).[search](/javascript/api/@azure/search-documents/searchclient#@azure-search-documents-searchclient-search) and the [VectorQuery](/javascript/api/@azure/search-documents/vectorquery) and [SearchOptions](/javascript/api/@azure/search-documents/searchoptions). 
 
+To create a single vector search with a filter:
+
 1. Create a `searchSingleWithFilter.js` file in the `src` directory.
 
 1. Copy the following code into the file.
@@ -246,12 +267,13 @@ You can add filters, but the filters are applied to the nonvector content in you
 
     Add the dependencies, environment variables, and the same search functionality as the previous search with a post-processing exclusion filter added for hotels with `free wifi`.
 
-1. Build and run the file:
+1. Build and run the file.
 
     ```bash
     node -r dotenv/config src/searchSingleWithFilter.js
     ```
-1. The output of this code shows the relevant documents for the query with the filter for `free wifi` applied:
+
+   The output of this code shows the relevant documents for the query with the filter for `free wifi` applied.
 
     ```output
     Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -267,18 +289,20 @@ You can add filters, but the filters are applied to the nonvector content in you
 
 You can specify a geospatial filter to limit results to a specific geographic area. In this example, the filter limits results to hotels within 300 kilometers of Washington D.C. (coordinates: `-77.03241 38.90166`). Geospatial distances are always in kilometers. This search uses [SearchClient](/javascript/api/@azure/search-documents/searchclient).[search](/javascript/api/@azure/search-documents/searchclient#@azure-search-documents-searchclient-search) and the [VectorQuery](/javascript/api/@azure/search-documents/vectorquery) and [SearchOptions](/javascript/api/@azure/search-documents/searchoptions). 
 
+To create a search with a geospatial filter:
+
 1. Create a `searchSingleWithFilterGeo.js` file in the `src` directory.
 
 1. Copy the following code into the file.
 
     :::code language="javascript" source="~/azure-search-javascript-samples/quickstart-vector-js/src/searchSingleWithFilterGeo.js" :::
-1. Build and run the file:
+1. Build and run the file.
 
     ```bash
     node -r dotenv/config src/searchSingleWithFilterGeo.js
     ```
 
-1. The output of this code shows the relevant documents for the query with the geospatial post-processing exclusion filter applied:
+   The output of this code shows the relevant documents for the query with the geospatial post-processing exclusion filter applied.
 
     ```output
     Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -290,26 +314,28 @@ You can specify a geospatial filter to limit results to a specific geographic ar
     - HotelId: 49, HotelName: Swirling Currents Hotel, Tags: N/A, Score 0.602634072303772
     ```
 
-
 ## Create a hybrid search
 
 Hybrid search consists of keyword queries and vector queries in a single search request. This example runs the vector query and full-text search concurrently:
 
-- **Search string**: `historic hotel walk to restaurants and shopping`
-- **Vector query string** (vectorized into a mathematical representation): `quintessential lodging near running trails, eateries, retail`
++ Search string: `historic hotel walk to restaurants and shopping`
++ Vector query string: `quintessential lodging near running trails, eateries, retail` (vectorized into a mathematical representation)
 
 This search uses [SearchClient](/javascript/api/@azure/search-documents/searchclient).[search](/javascript/api/@azure/search-documents/searchclient#@azure-search-documents-searchclient-search) and the [VectorQuery](/javascript/api/@azure/search-documents/vectorquery) and [SearchOptions](/javascript/api/@azure/search-documents/searchoptions). 
 
+To create a hybrid search:
+
 1. Create a `searchHybrid.js` file in the `src` directory.
 1. Copy the following code into the file.
 
     :::code language="javascript" source="~/azure-search-javascript-samples/quickstart-vector-js/src/searchHybrid.js" :::
-1. Build and run the file:
+1. Build and run the file.
 
     ```bash
     node -r dotenv/config src/searchHybrid.js
     ```
-1. The output of this code shows the relevant documents for the hybrid search:
+
+   The output of this code shows the relevant documents for the hybrid search.
 
     ```output
     Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -353,7 +379,7 @@ This search uses [SearchClient](/javascript/api/@azure/search-documents/searchcl
       Tags: ["pool","free wifi","air conditioning","concierge"]
     ```
 
-    Because Reciprocal Rank Fusion (RRF) merges results, it helps to review the inputs. The following results are from only the full-text query. The top two results are Sublime Palace Hotel and Luxury Lion Resort. The Sublime Palace Hotel has a stronger BM25 relevance score.
+    Because Reciprocal Rank Fusion (RRF) merges results, it helps to review the inputs. The following results are from the full-text query only. The top two results are Sublime Palace Hotel and Luxury Lion Resort. The Sublime Palace Hotel has a stronger BM25 relevance score.
 
     ```json
        {
@@ -368,7 +394,7 @@ This search uses [SearchClient](/javascript/api/@azure/search-documents/searchcl
        },
     ```
 
-    In the vector-only query, which uses HNSW for finding matches, the Sublime Palace Hotel drops to fourth position. Luxury Lion, which was second in the full-text search and third in the vector search, doesn't experience the same range of fluctuation, so it appears as a top match in a homogenized result set.
+    In the vector-only query, which uses HNSW for finding matches, the Sublime Palace Hotel drops to the fourth position. Luxury Lion, which was second in the full-text search and third in the vector search, doesn't experience the same range of fluctuation, so it appears as a top match in a homogenized result set.
    
    ```json
    "value": [
@@ -430,18 +456,21 @@ Here's the last query in the collection to extend the semantic hybrid search wit
 
 This search uses [SearchClient](/javascript/api/@azure/search-documents/searchclient).[search](/javascript/api/@azure/search-documents/searchclient#@azure-search-documents-searchclient-search) and the [VectorQuery](/javascript/api/@azure/search-documents/vectorquery) and [SearchOptions](/javascript/api/@azure/search-documents/searchoptions). 
 
+To create a semantic hybrid search:
+
 1. Create a `searchSemanticHybrid.js` file in the `src` directory.
+
 1. Copy the following code into the file.
 
     :::code language="javascript" source="~/azure-search-javascript-samples/quickstart-vector-js/src/searchSemanticHybrid.js" :::
 
-1. Build and run the file:
+1. Build and run the file.
 
     ```bash
     node -r dotenv/config src/searchSemanticHybrid.js
     ```
 
-1. The output of this code shows the relevant documents for the semantic hybrid search:
+   The output of this code shows the relevant documents for the semantic hybrid search.
 
     ```output
     Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -495,25 +524,25 @@ This search uses [SearchClient](/javascript/api/@azure/search-documents/searchcl
 
     - Actual results include more detail, including semantic captions and highlights. Results were modified for readability. To get the full structure of the response, run the request in the REST client.
 
-## Clean up
+## Clean up resources
 
 When you're working in your own subscription, it's a good idea at the end of a project to identify whether you still need the resources you created. Resources left running can cost you money. You can delete resources individually or delete the resource group to delete the entire set of resources.
 
 You can find and manage resources in the Azure portal by using the **All resources** or **Resource groups** link in the leftmost pane.
 
-If you want to keep your search service but delete the index and its documents, you can delete the index programmatically.
+Alternatively, to delete the vector index you created in this quickstart programmatically:
 
 1. Create a `deleteIndex.js` file in the `src` directory.
 1. Add the dependencies, environment variables, and code to delete the index.
 
     :::code language="javascript" source="~/azure-search-javascript-samples/quickstart-vector-js/src/deleteIndex.js" :::
 
-1. Build and run the file:
+1. Build and run the file.
 
     ```bash
     node -r dotenv/config src/deleteIndex.js
     ```
 
 ## Next steps
 
-- Review the repository of code samples for vector search capabilities in Azure AI Search for [JavaScript](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-javascript)
\ No newline at end of file
++ Review the repository of code samples for vector search capabilities in Azure AI Search for [JavaScript](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-javascript).
\ No newline at end of file

@@ -4,35 +4,40 @@ author: rotabor
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 11/20/2025
+ms.date: 01/14/2026
+ms.custom: dev-focus
+ai-usage: ai-assisted
 ---
 
-In this quickstart, you use a Jupyter notebook to create, load, and query vectors. The code examples perform these operations by using the [Azure AI Search client library](/python/api/overview/azure/search-documents-readme). The library provides an abstraction over the REST API for access to index operations such as data ingestion, search operations, and index management operations.
+In this quickstart, you use a Jupyter notebook to create, load, and query a [vector index](../../vector-store.md). The code performs these operations by using the [Azure AI Search client library for Python](/python/api/overview/azure/search-documents-readme), which provides an abstraction over the REST APIs to access index operations.
 
-In Azure AI Search, a [vector store](../../vector-store.md) has an index schema that defines vector and nonvector fields, a vector search configuration for algorithms that create the embedding space, and settings on vector field definitions that are evaluated at query time. The [Create Index](/rest/api/searchservice/indexes/create-or-update) REST API creates the vector store.
+In Azure AI Search, a vector index has an index schema that defines vector and nonvector fields, a vector search configuration for algorithms that create the embedding space, and settings on vector field definitions that are evaluated at query time. [Indexes - Create or Update](/rest/api/searchservice/indexes/create-or-update) (REST API) creates the vector index.
 
 > [!NOTE]
 > This quickstart omits the vectorization step and provides inline embeddings. If you want to add [built-in data chunking and vectorization](../../vector-search-integrated-vectorization.md) over your own content, try the [**Import data (new)** wizard](../../search-get-started-portal-import-vectors.md) for an end-to-end walkthrough.
 
 ## Prerequisites
 
-- An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
++ An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
 
-- An Azure AI Search service. [Create a service](../../search-create-service-portal.md) or [find an existing service](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/CognitiveSearch) in your current subscription.
-    - You can use a free search service for most of this quickstart, but we recommend the Basic tier or higher for larger data files.
-    - To run the query example that invokes [semantic reranking](../../semantic-search-overview.md), your search service must have [semantic ranker enabled](../../semantic-how-to-enable-disable.md).
++ An [Azure AI Search service](../../search-create-service-portal.md).
 
-- [Visual Studio Code](https://code.visualstudio.com/download) with the [Python extension](https://marketplace.visualstudio.com/items?itemName=ms-python.python) and [Jupyter package](https://pypi.org/project/jupyter/).
+    + You can use the Free tier for most of this quickstart, but we recommend Basic or higher for larger data files.
 
-- [Git](https://git-scm.com/downloads) to clone the repo containing the Jupyter notebook and other related files.
+    + For [keyless authentication](../../search-get-started-rbac.md) with Microsoft Entra ID, assign the **Search Index Data Contributor role** to your user account.
+    
+    + To run the semantic hybrid query, you must [enable semantic ranker](../../semantic-how-to-enable-disable.md).
+
++ [Visual Studio Code](https://code.visualstudio.com/download) with the [Python extension](https://marketplace.visualstudio.com/items?itemName=ms-python.python) and [Jupyter package](https://pypi.org/project/jupyter/).
+
++ [Git](https://git-scm.com/downloads) to clone the sample repo.
 
 ## Get service information
 
-Requests to the search endpoint must be authenticated and authorized. While it's possible to use API keys or roles for this task, we recommend [using a keyless connection via Microsoft Entra ID](../../search-get-started-rbac.md).
+Requests to the search endpoint must be authenticated and authorized. While it's possible to use API keys for this task, we recommend [using a keyless connection via Microsoft Entra ID](../../search-get-started-rbac.md).
 
 This quickstart uses `DefaultAzureCredential`, which simplifies authentication in both development and production scenarios. However, for production scenarios, you might have more advanced requirements that require a different approach. See [Authenticate Python apps to Azure services by using the Azure SDK for Python](/azure/developer/python/sdk/authentication/overview) to understand all of your options.
 
-
 ## Clone the code and setup environment
 
 1. Clone the repo containing the code for this quickstart. 
@@ -41,25 +46,15 @@ This quickstart uses `DefaultAzureCredential`, which simplifies authentication i
    git clone https://github.com/Azure-Samples/azure-search-python-samples
    ```
   
-   This repo has Python code examples for several articles each in a separate subfolder.
-
-1. In Visual Studio Code, open the subfolder `Quickstart-Vector-Search`.
+1. In Visual Studio Code, open the `Quickstart-Vector-Search` folder.
 
-   There are three files in this folder:
+1. Rename the `sample.env` file to `.env`.
 
-   - `vector-search-quickstart.ipynb`
-   - `requirements.txt`
-   - `sample.env`
-
-1. Rename the `sample.env` file to `.env` and modify the values in the `.env` file. 
-
-   Use the search service URL as the `AZURE_SEARCH_ENDPOINT`. You can find the url in the [Azure portal](https://portal.azure.com). Go to your Azure AI Search service, on the **Overview** page, look for the URL field. An example endpoint might look like `https://mydemo.search.windows.net`. 
-   
-   Finally, choose a new `AZURE_SEARCH_INDEX_NAME` name, or use the one provided in the file.
+1. Set `AZURE_SEARCH_ENDPOINT` to your search service URL, which should be similar to `https://mydemo.search.windows.net`.
 
-1. In Visual Studio Code, work in an environment. On the **View** menu, select **Terminal...**, or select <kbd>Ctrl</kbd>+<kbd>`</kbd>.
+1. Set `AZURE_SEARCH_INDEX_NAME` to a unique name for your index. You can also use the default `vector-search-quickstart` name.
 
-1. Run the following commands in the terminal:
+1. Select **View** > **New Terminal**, and then run the following commands to create and activate a virtual environment.
 
    ```bash
    python -m venv .venv
@@ -68,25 +63,21 @@ This quickstart uses `DefaultAzureCredential`, which simplifies authentication i
    ```
    
    > [!Note] 
-   > This assumes you're using Git Bash in your Terminal, and you're running on Windows. If you're using a different shell and/or a different operating system, adjust these instructions for your specific environment.
+   > + This step assumes you're using Git Bash in your terminal and running on Windows. If you're using a different shell and/or operating system, adjust these instructions to your specific environment.
+   >
+   > + The `where python` command validates that you're working from the virtual environment by listing `python.exe` in the `Quickstart-Vector-Search\.venv\` folder and other locations from your machine's directory.
 
-   If prompted, allow Visual Studio Code to use the new environment.
+1. If prompted, allow Visual Studio Code to use the new environment.
 
-   The `where python` command validates that you're working from the virtual environment by listing `python.exe` in the `Quickstart-Vector-Search\.venv\` folder, and other locations from your machine's directory.
-
-1. Install the required libraries by running the following command:
+1. Install the required libraries.
 
    ```bash
    pip install requirements.txt
    ```
 
-1. In Visual Studio Code, open the `vector-search-quickstart.ipynb`.
-
-   > [!Note]
-   > If this is the first time you have used a Jupyter Notebook (.ipynb) in Visual Studio Code, you will be prompted to install the Jupyter Notebook kernel and possibly other tools. Choose to install the suggested tools to continue with this quickstart.
+1. Open the `vector-search-quickstart.ipynb` file.
 
-
-1. Find the cell below section titled "Install packages and set variables" and select the **Execute Cell (Ctrl + Alt + Enter)** button (which looks like a typical run button) to the left of the cell. Executing the cell loads the environment variables, creates the DefaultAzureCredential, and prints values to the output to confirm that the notebook's dependencies and `.env` are set up correctly.
+1. Run the `Install packages and set variables` code cell to load the environment variables.
 
    ```python
    # Load environment variables from .env file
@@ -105,7 +96,7 @@ This quickstart uses `DefaultAzureCredential`, which simplifies authentication i
    print(f"Using Azure Search index: {index_name}")
    !pip list 
    ```
-   Executing this cell produces the following output.
+   The output includes some of the installed packages.
 
    ```output
    Using Azure Search endpoint: https://<search-service-name>.search.windows.net
@@ -127,14 +118,13 @@ This quickstart uses `DefaultAzureCredential`, which simplifies authentication i
    ...
    ```
   
-   There are many more packages that you can view in a scrollable element (see the message below the cell results).
-
+## Create a vector index
 
-## Create the vector index
+The code in `vector-search-quickstart.ipynb` uses several methods from the `azure.search.documents` library to create the vector index and searchable fields.
 
-The code in the `vector-search-quickstart.ipynb` uses several methods from the `azure.search.documents` library to create the vector index and searchable fields.
+To create the vector index:
 
-1. Find the cell below section titled "Create an index" and execute the cell to create the index.
+1. Run the `Create an index` code cell.
 
    ```python
    from azure.search.documents.indexes import SearchIndexClient
@@ -218,33 +208,39 @@ The code in the `vector-search-quickstart.ipynb` uses several methods from the `
    print(f' {result.name} created')
    ```
 
-   If the index is created successfully, you see the following result below the cell:
+   If the index is created successfully, the following output is displayed below the code cell.
 
    ```output
    vector-search-quickstart created
    ```
 
-   Key takeaways when creating vector index with the `azure.search.documents`:
+   Key takeaways:
+
+   + You define an index by creating a list of fields. Each field is created using a helper method that defines the field type and its settings.
+
+   + This particular index supports multiple search capabilities, such as:
+
+      + Full-text keyword search (`SearchableField(name="HotelName", ...)`, `SearchableField(name="Description", ...)`)
 
-   - You define an index by creating a list of fields. Each field is created using a helper method that defines the field type and its settings.
+      + Vector search (enables hybrid search by collocating vector and nonvector fields) fields (`DescriptionVector`)
 
-   - This particular index supports multiple search capabilities, such as:
-      - Full-text keyword search (`SearchableField(name="HotelName", ...)`, `SearchableField(name="Description", ...)`)
-      - Vector search (enables hybrid search by collocating vector and nonvector fields) fields (`DescriptionVector`)
-      - Semantic search (`semantic_search=SemanticSearch(configurations=[semantic_config])`)
-      - Faceted search (`facetable=True`)
-      - Semantic search (`semantic_search=SemanticSearch(configurations=[semantic_config])`)
-      - Geo-spatial search (`Location` field is `GeographyPoint`)
-      - Filtering, sorting (Many fields marked filterable and sortable)
+      + Semantic search (`semantic_search=SemanticSearch(configurations=[semantic_config])`)
 
+      + Faceted search (`facetable=True`)
 
-## Upload documents
+      + Geo-spatial search (`Location` field is `GeographyPoint`)
 
-Creating and loading the index are separate steps. You created the index schema [in the previous step](#create-a-vector-index). Now you need to load documents into the index.
+      + Filtering, sorting (many fields marked filterable and sortable)
+
+## Upload documents to the index
+
+Creating and loading the index are separate steps. You created the index schema in the previous step. You now need to load documents into the index.
  
 In Azure AI Search, the index stores all searchable content, while the search engine executes queries against that index.
 
-1. Find the cell below section titled "Create documents payload" and execute the cell. This cell contains the following code (truncated for brevity):
+To upload documents to the index:
+
+1. Run the `Create documents payload` code cell.
 
    ```python
       # Create a documents payload
@@ -290,7 +286,7 @@ In Azure AI Search, the index stores all searchable content, while the search en
    > [!IMPORTANT]
    > The code in this example isn't runnable. Several characters or lines are removed for brevity. Instead, run the code in the Jupyter notebook.
    
-1. Find the cell below section titled "Upload the documents" and execute the cell. This cell contains the following code (truncated for brevity):
+1. Run the `Upload the documents` code cell.
 
    ```python
    # Upload documents to the index
@@ -308,9 +304,9 @@ In Azure AI Search, the index stores all searchable content, while the search en
    index_client = SearchIndexClient(endpoint=search_endpoint, credential=credential)
    ```
 
-   This creates an instance of the search client by calling the `SearchClient()` constructor, then calls the `upload_documents()` method on the object. 
+   This creates an instance of the search client by calling the `SearchClient()` constructor and then calling the `upload_documents()` method on the object. 
 
-   After you run the cell, the status of each document is printed below it:
+   After you run the cell, the status of each document is printed below it.
 
    ```output
    Key: 1, Succeeded: True, ErrorMessage: None
@@ -322,43 +318,45 @@ In Azure AI Search, the index stores all searchable content, while the search en
    Key: 13, Succeeded: True, ErrorMessage: None
    ```
 
-   Key takeaways about the `upload_documents()` method and this example:
+   Key takeaways:
 
-   - Your code interacts with a specific search index hosted in your Azure AI Search service through the `SearchClient`, which is the main object provided by the `azure-search-documents` package. The `SearchClient` provides access to index operations such as:
+   + Your code interacts with a specific search index hosted in your Azure AI Search service through the `SearchClient`, which is the main object provided by the `azure-search-documents` package. The `SearchClient` provides access to index operations, such as:
 
-      - **Data ingestion** - `upload_documents()`, `merge_documents()`, `delete_documents()`, etc.
-      - **Search operations** - `search()`, `autocomplete()`, `suggest()`
-      - **Index management operations** 
+      + Data ingestion: `upload_documents()`, `merge_documents()`, `delete_documents()`, etc.
+      
+      + Search operations: `search()`, `autocomplete()`, `suggest()`
 
-   - Vector fields contain floating point values. The dimensions attribute has a minimum of 2 and a maximum of 4096 floating point values each. This quickstart sets the dimensions attribute to 1,536 because that's the size of embeddings generated by the Azure OpenAI **text-embedding-ada-002** model.
+      + Index management operations: `get_index_statistics()`, `get_document_count()`
+
+   + Vector fields contain floating point values. The dimensions attribute has a minimum of 2 and a maximum of 4096 floating point values each. This quickstart sets the dimensions attribute to 1,536 because that's the size of embeddings generated by the `text-embedding-ada-002` model.
 
 ## Run queries
 
-Now that documents are loaded, you can issue vector queries against them by calling `search_client.search()` and passing in a VectorizedQuery object, the fields you want returned, the number of results, and so on.
+Now that documents are loaded, you can issue vector queries against them by calling `search_client.search()` and passing in a `VectorizedQuery` object, the fields you want returned, the number of results, and so on.
 
-In the next sections, we run queries against the `hotels-vector-quickstart` index. The queries include:
+Queries in this section:
 
-- [Single vector search](#single-vector-search)
-- [Single vector search with filter](#single-vector-search-with-filter)
-- [Hybrid search](#hybrid-search)
-- [Semantic hybrid search](#semantic-hybrid-search)
++ [Single vector search](#single-vector-search)
++ [Single vector search with filter](#single-vector-search-with-filter)
++ [Hybrid search](#hybrid-search)
++ [Semantic hybrid search](#semantic-hybrid-search)
 
 ### Create the vector query string
 
 The example vector queries are based on two strings:
 
-- **Search string**: `historic hotel walk to restaurants and shopping`
-- **Vector query string** (vectorized into a mathematical representation): `quintessential lodging near running trails, eateries, retail`
++ Search string: `historic hotel walk to restaurants and shopping`
++ Vector query string: `quintessential lodging near running trails, eateries, retail` (vectorized into a mathematical representation)
 
 The vector query string is semantically similar to the search string, but it includes terms that don't exist in the search index. If you do a keyword search for `quintessential lodging near running trails, eateries, retail`, results are zero. We use this example to show how you can get relevant results even if there are no matching terms.
 
-- Find the cell below section titled "Create the vector query string" and execute the cell. This loads the `vector` variable with the vectorized query data required to run all of the searches in the next sections.
+1. Run the `Create the vector query string` code cell. This loads the `vector` variable with the vectorized query data required to run all of the searches in the next sections.
 
 ### Single vector search
 
 The first example demonstrates a basic scenario where you want to find document descriptions that closely match the search string.
 
-- Find the cell below section titled "Single vector search" and execute the cell. This block contains the request to query the search index.
+1. Run the `Single vector search` code cell. This block contains the request to query the search index.
 
    ```python
    # IMPORTANT: Before you run this code, make sure the documents were successfully
@@ -402,7 +400,7 @@ The first example demonstrates a basic scenario where you want to find document
 
    `search_client.search()` returns a dict-like object. Each result provides a search score, which can be accessed using `score = result.get("@search.score", "N/A")`. While not displayed in this example, in a similarity search, the response always includes `k` results ordered by the value similarity score.
 
-   After you run the cell, the status of each document is printed below it:
+   After you run the cell, the status of each document is printed below it.
 
    ```output
    Total results: 5
@@ -417,7 +415,9 @@ The first example demonstrates a basic scenario where you want to find document
 
 You can add filters, but the filters are applied to the nonvector content in your index. In this example, the filter applies to the `Tags` field to filter out any hotels that don't provide free Wi-Fi.
 
-1. Find the cell below section titled "Single vector search with filter" and execute the cell. This cell contains the request to query the search index.
+To create a single vector search with a filter:
+
+1. Run the `Single vector search with filter` code cell. This cell contains the request to query the search index.
 
     ```python
    if vector:
@@ -458,7 +458,7 @@ You can add filters, but the filters are applied to the nonvector content in you
 
    The query was the same as the previous [single vector search example](#single-vector-search), but it includes a post-processing exclusion filter and returns only the two hotels that have free Wi-Fi.
 
-1. The next filter example uses a **geo filter**. Run the cell in the section titled "Vector query with a geo filter". This block contains the request to query the search index.
+1. The next filter example uses a geo filter. Run the `Vector query with a geo filter` code cell. This block contains the request to query the search index.
 
    ```python
    if vector:
@@ -520,10 +520,12 @@ You can add filters, but the filters are applied to the nonvector content in you
 
 Hybrid search consists of keyword queries and vector queries in a single search request. This example runs the vector query and full-text search concurrently:
 
-- **Search string**: `historic hotel walk to restaurants and shopping`
-- **Vector query string** (vectorized into a mathematical representation): `quintessential lodging near running trails, eateries, retail`
++ Search string: `historic hotel walk to restaurants and shopping`
++ Vector query string: `quintessential lodging near running trails, eateries, retail` (vectorized into a mathematical representation)
 
-- Find the cell below section titled "Hybrid search" and execute the cell. This block contains the request to query the search index.
+To create a hybrid search:
+
+1. Run the `Hybrid search` code cell. This block contains the request to query the search index.
 
    ```python
    if vector:
@@ -561,7 +563,7 @@ Hybrid search consists of keyword queries and vector queries in a single search
       print("No vector loaded, skipping search.")    
    ```
 
-   Review the response:
+1. Review the output below the cell.
 
    ```output
    Total hybrid results: 7
@@ -601,7 +603,7 @@ Hybrid search consists of keyword queries and vector queries in a single search
      Tags: ['pool', 'free wifi', 'air conditioning', 'concierge']
    ```
 
-   Because Reciprocal Rank Fusion (RRF) merges results, it helps to review the inputs. The following results are from only the full-text query. The top two results are Sublime Palace Hotel and Luxury Lion Resort. The Sublime Palace Hotel has a stronger BM25 relevance score.
+   Because Reciprocal Rank Fusion (RRF) merges results, it helps to review the inputs. The following results are from the full-text query only. The top two results are Sublime Palace Hotel and Luxury Lion Resort. The Sublime Palace Hotel has a stronger BM25 relevance score.
 
    ```json
    {
@@ -616,7 +618,7 @@ Hybrid search consists of keyword queries and vector queries in a single search
    },
    ```
 
-   In the vector-only query, which uses HNSW for finding matches, the Sublime Palace Hotel drops to fourth position. Luxury Lion, which was second in the full-text search and third in the vector search, doesn't experience the same range of fluctuation, so it appears as a top match in a homogenized result set.
+   In the vector-only query, which uses HNSW for finding matches, the Sublime Palace Hotel drops to the fourth position. Luxury Lion, which was second in the full-text search and third in the vector search, doesn't experience the same range of fluctuation, so it appears as a top match in a homogenized result set.
    
    ```json
    "value": [
@@ -676,7 +678,9 @@ Hybrid search consists of keyword queries and vector queries in a single search
 
 Here's the last query in the collection. This hybrid query specifies the semantic query type and a semantic configuration, demonstrating that you can build a hybrid query that uses semantic reranking.
 
-- Find the cell below section titled "Semantic hybrid search" and execute the cell. This code block contains the request to query the search index.
+To create a semantic hybrid search:
+
+1. Run the `Semantic hybrid search` code cell. This code block contains the request to query the search index.
 
    ```python
    if semantic_hybrid_query_vector:
@@ -719,9 +723,9 @@ Here's the last query in the collection. This hybrid query specifies the semanti
       print("No vector loaded, skipping search.")
    ```
 
-   Review the output below the cell.
+1. Review the output below the cell.
 
-   With semantic ranking, the Swirling Currents Hotel now moves into the top spot. W
+   With semantic ranking, the Swirling Currents Hotel now moves into the top spot.
 
    ```output
    Total semantic hybrid results: 7
@@ -757,23 +761,23 @@ Here's the last query in the collection. This hybrid query specifies the semanti
      Category: Suite
    ```
 
-You can think of the semantic ranking as a way to improve the relevance of search results by understanding the meaning behind the words in the query and the content of the documents. In this case, the semantic ranking helps to identify hotels that are not only relevant to the keywords but also match the intent of the query:
-
-Key takeaways:
-
-- Vector search is specified through the `vectors.value` property. Keyword search is specified through the `search` property.
-
-- In a hybrid search, you can integrate vector search with full-text search over keywords. Filters, spell check, and semantic ranking apply to textual content only, and not vectors. In this final query, there's no semantic `answer` because the system didn't produce one that was sufficiently strong.
-
-- Actual results include more detail, including semantic captions and highlights. Results were modified for readability. To get the full structure of the response, run the request in the REST client.
+    You can think of the semantic ranking as a way to improve the relevance of search results by understanding the meaning behind the words in the query and the content of the documents. In this case, the semantic ranking helps to identify hotels that are not only relevant to the keywords but also match the intent of the query:
+    
+    Key takeaways:
+    
+    + Vector search is specified through the `vectors.value` property. Keyword search is specified through the `search` property.
+    
+    + In a hybrid search, you can integrate vector search with full-text search over keywords. Filters, spell check, and semantic ranking apply to textual content only, and not vectors. In this final query, there's no semantic `answer` because the system didn't produce one that was sufficiently strong.
+    
+    + Actual results include more detail, including semantic captions and highlights. Results were modified for readability. To get the full structure of the response, run the request in the REST client.
 
-## Clean up
+## Clean up resources
 
 When you're working in your own subscription, it's a good idea at the end of a project to identify whether you still need the resources you created. Resources left running can cost you money. You can delete resources individually or delete the resource group to delete the entire set of resources.
 
 You can find and manage resources in the Azure portal by using the **All resources** or **Resource groups** link in the leftmost pane.
 
-If you want to keep the search service, but delete the index and documents, you can use the `SearchIndexClient` object's `delete_index()` method. Find the cell below section titled "Clean up" and execute the cell if you want to delete the `hotels-vector-quickstart` index:
+Alternatively, you can run the `Clean up` code cell to delete the vector index created in this quickstart.
 
 ```python
 index_client.delete_index(index_name)
@@ -782,5 +786,5 @@ print(f"Index '{index_name}' deleted successfully.")
 
 ## Next steps
 
-- Review the repository of code samples for vector search capabilities in Azure AI Search for [Python](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-python)
-- Review the other Python and Azure AI Search code samples in the [azure-search-python-samples repo](https://github.com/Azure-Samples/azure-search-python-samples)
\ No newline at end of file
++ Review the repository of code samples for vector search capabilities in Azure AI Search for [Python](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-python).
++ Review the other Python and Azure AI Search code samples in the [azure-search-python-samples repo](https://github.com/Azure-Samples/azure-search-python-samples).

@@ -4,25 +4,29 @@ author: haileytapia
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 11/20/2025
+ms.date: 01/14/2026
+ms.custom: dev-focus
+ai-usage: ai-assisted
 ---
 
-In this quickstart, you use the [Azure AI Search REST APIs](/rest/api/searchservice) to create, load, and query vectors.
+In this quickstart, you use the [Azure AI Search REST APIs](/rest/api/searchservice) to create, load, and query a [vector index](../../vector-store.md).
 
-In Azure AI Search, a [vector store](../../vector-store.md) has an index schema that defines vector and nonvector fields, a vector search configuration for algorithms that create the embedding space, and settings on vector field definitions that are evaluated at query time. The [Create Index](/rest/api/searchservice/indexes/create-or-update) REST API creates the vector store.
+In Azure AI Search, a vector index has an index schema that defines vector and nonvector fields, a vector search configuration for algorithms that create the embedding space, and settings on vector field definitions that are evaluated at query time. [Indexes - Create or Update](/rest/api/searchservice/indexes/create-or-update) (REST API) creates the vector index.
 
 > [!NOTE]
 > This quickstart omits the vectorization step and provides inline embeddings. If you want to add [built-in data chunking and vectorization](../../vector-search-integrated-vectorization.md) over your own content, try the [**Import data (new)** wizard](../../search-get-started-portal-import-vectors.md) for an end-to-end walkthrough.
 
 ## Prerequisites
 
-- An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
++ An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
 
-- An Azure AI Search service. [Create a service](../../search-create-service-portal.md) or [find an existing service](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/CognitiveSearch) in your current subscription.
-    - You can use a free search service for most of this quickstart, but we recommend the Basic tier or higher for larger data files.
-    - To run the query example that invokes [semantic reranking](../../semantic-search-overview.md), your search service must have [semantic ranker enabled](../../semantic-how-to-enable-disable.md).
++ An [Azure AI Search service](../../search-create-service-portal.md).
 
-- [Visual Studio Code](https://code.visualstudio.com/download) with a [REST client](https://marketplace.visualstudio.com/items?itemName=humao.rest-client).
+    + You can use the Free tier for most of this quickstart, but we recommend Basic or higher for larger data files.
+    
+    + To run the semantic hybrid query, you must [enable semantic ranker](../../semantic-how-to-enable-disable.md).
+
++ [Visual Studio Code](https://code.visualstudio.com/download) with a [REST client](https://marketplace.visualstudio.com/items?itemName=humao.rest-client).
 
 ## Get service information
 
@@ -48,7 +52,6 @@ Select the tab that corresponds to your preferred authentication method. Use the
 
 #### [API key](#tab/api-key)
 
-
 1. Sign in to the [Azure portal](https://portal.azure.com) and [find your search service](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/CognitiveSearch).
 
 1. On the **Overview** home page, find the URL. An example endpoint might look like `https://mydemo.search.windows.net`. 
@@ -65,39 +68,42 @@ Select the tab that corresponds to your preferred authentication method. Use the
 
 You use one `.rest` or `.http` file to run all the requests in this quickstart. You can download the REST file that contains the code for this quickstart, or you can create a new file in Visual Studio Code and copy the code into it.
 
-1. In Visual Studio Code, create a new file with a `.rest` or `.http` file extension. For example, `az-search-vector-quickstart.rest`. Copy and paste the raw contents of the [Azure-Samples/azure-search-rest-samples/blob/main/Quickstart-vectors/az-search-vector-quickstart.rest](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart-vectors) file into this new file. 
+To create the code file:
 
-1. At the top of the file, replace the placeholder value for `@baseUrl` with your search service URL. See the [Get service information](#get-service-information) section for instructions on how to find your search service URL.
+1. In Visual Studio Code, create a file with a `.rest` or `.http` file extension, such as `az-search-vector-quickstart.rest`.
 
+1. Copy and paste the raw contents of the [az-search-vector-quickstart.rest](https://github.com/Azure-Samples/azure-search-rest-samples/blob/main/Quickstart-vectors/az-search-quickstart-vectors.rest) file into the new file. 
 
    ```http
    @baseUrl = PUT-YOUR-SEARCH-SERVICE-URL-HERE
    ```
 
-1. At the top of the file, replace the placeholder value for authentication. See the [Get service information](#get-service-information) section for instructions on how to get your Microsoft Entra token or API key.
+1. Set `@baseUrl` to the endpoint you obtained in [Get service information](#get-service-information).
 
-    For the **recommended** keyless authentication via Microsoft Entra ID, you need to replace `@apiKey` with the `@token` variable.
-
-   ```http
-   @token = PUT-YOUR-MICROSOFT-ENTRA-TOKEN-HERE
-   ```
+1. Set the key or token for authentication. You obtained this value in [Get service information](#get-service-information).
 
-    If you prefer to use an API key, replace `@apiKey` with the key you copied from the Azure portal.
+   + For the **recommended** keyless authentication with Microsoft Entra ID, replace `@apiKey` with the `@token` variable.
 
-    ```http
-    @apiKey = PUT-YOUR-ADMIN-KEY-HERE
-    ```
+        ```http
+        @token = PUT-YOUR-MICROSOFT-ENTRA-TOKEN-HERE
+        ```
 
-1. For the **recommended** keyless authentication via Microsoft Entra ID, you need to replace `api-key: {{apiKey}}` with `Authorization: Bearer {{token}}` in the request headers. Replace all instances of `api-key: {{apiKey}}` that you find in the file.
+    + If you prefer to use an API key, replace `@apiKey` with the key you copied from the Azure portal.
 
+        ```http
+        @apiKey = PUT-YOUR-ADMIN-KEY-HERE
+        ```
 
+1. For the **recommended** keyless authentication with Microsoft Entra ID, replace all instances of `api-key: {{apiKey}}` with `Authorization: Bearer {{token}}` in the request headers.
 
 ## Create a vector index
 
-You use the [Create Index](/rest/api/searchservice/indexes/create) REST API to create a vector index and set up the physical data structures on your search service.
+You use [Indexes - Create](/rest/api/searchservice/indexes/create) (REST API) to create a vector index and set up the physical data structures on your search service.
 
 The index schema in this example is organized around hotel content. Sample data consists of vector and nonvector descriptions of fictitious hotels. This schema includes configurations for vector indexing and queries, and for semantic ranking.
 
+To create a vector index:
+
 1. In Visual Studio Code, open the `az-search-vector-quickstart.rest` file you [created earlier](#create-or-download-the-code-file).
 
 1. Find the `### Create a new index` code block in the file. This block contains the request to create the `hotels-vector-quickstart` index on your search service. 
@@ -378,21 +384,23 @@ The index schema in this example is organized around hotel content. Sample data
     }
     ```
 
-Key takeaways about the [Create Index](/rest/api/searchservice/indexes/create) REST API:
-
-- The `fields` collection includes a required key field and text and vector fields (such as `Description` and `DescriptionVector`) for text and vector search. Colocating vector and nonvector fields in the same index enables hybrid queries. For instance, you can combine filters, text search with semantic ranking, and vectors into a single query operation.
-
-- Vector fields must be one of the [EDM data types used for vectors](/rest/api/searchservice/supported-data-types#edm-data-types-for-vector-fields), such as `type: Collection(Edm.Single)`. Vector fields also have `dimensions` and `vectorSearchProfile` properties.
-
-- The `vectorSearch` section is an array of Approximate Nearest Neighbor (ANN) algorithm configurations and profiles. Supported algorithms include Hierarchical Navigable Small World and exhaustive K-Nearest Neighbor. For more information, see [Relevance scoring in vector search](../../vector-search-ranking.md).
-
-- The (optional) `semantic` configuration enables reranking of search results. You can rerank results in queries of type `semantic` for string fields that are specified in the configuration. To learn more, see [Semantic ranking overview](../../semantic-search-overview.md).
+    Key takeaways:
+    
+    + The `fields` collection includes a required key field and text and vector fields (such as `Description` and `DescriptionVector`) for text and vector search. Colocating vector and nonvector fields in the same index enables hybrid queries. For instance, you can combine filters, text search with semantic ranking, and vectors into a single query operation.
+    
+    + Vector fields must be one of the [EDM data types used for vectors](/rest/api/searchservice/supported-data-types#edm-data-types-for-vector-fields), such as `type: Collection(Edm.Single)`. Vector fields also have `dimensions` and `vectorSearchProfile` properties.
+    
+    + The `vectorSearch` section is an array of Approximate Nearest Neighbor (ANN) algorithm configurations and profiles. Supported algorithms include Hierarchical Navigable Small World and exhaustive K-Nearest Neighbor. For more information, see [Relevance scoring in vector search](../../vector-search-ranking.md).
+    
+    + The (optional) `semantic` configuration enables reranking of search results. You can rerank results in queries of type `semantic` for string fields that are specified in the configuration. To learn more, see [Semantic ranking overview](../../semantic-search-overview.md).
 
-## Upload documents
+## Upload documents to the index
 
-Creating and loading the index are separate steps. You created the index schema [in the previous step](#create-a-vector-index). Now you need to load documents into the index.
+Creating and loading the index are separate steps. You created the index schema in the previous step. You now need to load documents into the index.
  
-In Azure AI Search, the index contains all searchable data and queries run on the search service. For REST calls, the data is provided as JSON documents. Use [Documents- Index REST API](/rest/api/searchservice/documents/) for this task. The URI is extended to include the `docs` collection and the `index` operation.
+In Azure AI Search, the index contains all searchable data and queries run on the search service. For REST calls, the data is provided as JSON documents. Use [Documents - Index](/rest/api/searchservice/documents/) (REST API) for this task. The URI is extended to include the `docs` collection and the `index` operation.
+
+To upload documents to the index:
 
 1. Formulate an upload documents request to upload documents to the `hotels-vector-quickstart` index on your search service.
 
@@ -639,32 +647,34 @@ In Azure AI Search, the index contains all searchable data and queries run on th
 
 1. Select **Send Request**. You should have an `HTTP/1.1 200 OK` response. The response body should include the JSON representation of the search documents.
 
-Key takeaways about the [Documents - Index REST API](/rest/api/searchservice/documents/) request:
-
-- Documents in the payload consist of fields defined in the index schema.
-
-- Vector fields contain floating point values. The dimensions attribute has a minimum of 2 and a maximum of `4096` floating point values each. This quickstart sets the dimensions attribute to 1,536 because that's the size of embeddings generated by the Azure OpenAI **text-embedding-3-small** model.
+    Key takeaways:
+    
+    + Documents in the payload consist of fields defined in the index schema.
+    
+    + Vector fields contain floating point values. The dimensions attribute has a minimum of 2 and a maximum of 4096 floating point values each. This quickstart sets the dimensions attribute to 1,536 because that's the size of embeddings generated by the `text-embedding-ada-002` model.
 
 ## Run queries
 
-Now that documents are loaded, you can run vector queries against them by using [Documents - Search Post (REST)](/rest/api/searchservice/documents/search-post).
+Now that documents are loaded, you can run vector queries against them by using [Documents - Search Post](/rest/api/searchservice/documents/search-post) (REST API).
 
-In the next sections, we run queries against the `hotels-vector-quickstart` index. The queries include:
+Queries in this section:
 
-- [Single vector search](#single-vector-search)
-- [Single vector search with filter](#single-vector-search-with-filter)
-- [Hybrid search](#hybrid-search)
-- [Semantic hybrid search](#semantic-hybrid-search)
++ [Single vector search](#single-vector-search)
++ [Single vector search with filter](#single-vector-search-with-filter)
++ [Hybrid search](#hybrid-search)
++ [Semantic hybrid search](#semantic-hybrid-search)
 
 The example queries are based on two strings:
 
-- **Search string**: `historic hotel walk to restaurants and shopping`
-- **Vector query string** (vectorized into a mathematical representation): `quintessential lodging near running trails, eateries, retail`
++ Search string: `historic hotel walk to restaurants and shopping`
++ Vector query string: `quintessential lodging near running trails, eateries, retail` (vectorized into a mathematical representation)
 
 The vector query string is semantically similar to the search string, but it includes terms that don't exist in the search index. If you do a keyword search for `quintessential lodging near running trails, eateries, retail`, results are zero in a pure keyword search without semantic ranking. We use this example to show how you can get relevant results using vectors, even if there are no matching terms.
 
 ### Single vector search
 
+To create a single vector search:
+
 1. Formulate the request. The query is a 1536 float representation of *quintessential lodging near running trails, eateries, retail*. The query is searching `DescriptionVector` and returning k-5 results. It's using the "exhaustive" override parameter to perform a full scan of the index instead of ANN. An exhaustive search is useful for small indexes.
 
     ```http
@@ -688,7 +698,7 @@ The vector query string is semantically similar to the search string, but it inc
         }
     ```
 
-   Key takeaways about the [Documents - Search Post](/rest/api/searchservice/documents/search-post) REST API:
+    Key takeaways about [Documents - Search Post](/rest/api/searchservice/documents/search-post) (REST API):
 
     + The `vectorQueries.vector` is the vector query string. It's a vector representation of *quintessential lodging near running trails, eateries, retail*, which is vectorized into 1,536 embeddings for this query.
 
@@ -776,6 +786,8 @@ The vector query string is semantically similar to the search string, but it inc
 
 You can add filters, but the filters are applied to the nonvector content in your index. In this example, the filter applies to the `Tags` field to filter out any hotels that don't provide free Wi-Fi.
 
+To create a single vector search with a filter:
+
 1. Formulate the request. This is the same request as the previous one, with an extra filter and filter mode parameter.
 
     ```http
@@ -906,8 +918,10 @@ You can add filters, but the filters are applied to the nonvector content in you
 
 Hybrid search consists of keyword queries and vector queries in a single search request. This example runs the vector query and full text search concurrently:
 
-- **Search string**: `historic hotel walk to restaurants and shopping`
-- **Vector query string** (vectorized into a mathematical representation): `quintessential lodging near running trails, eateries, retail`
++ Search string: `historic hotel walk to restaurants and shopping`
++ Vector query string: `quintessential lodging near running trails, eateries, retail` (vectorized into a mathematical representation)
+
+To create a hybrid search:
 
 1. Formulate the hybrid query.
 
@@ -936,95 +950,97 @@ Hybrid search consists of keyword queries and vector queries in a single search
 
 1. Select **Send Request**. You should have an `HTTP/1.1 200 OK` response. The response body should include the JSON representation of the search results.
 
-Because this is a hybrid query, results are [ranked by Reciprocal Rank Fusion (RRF)](../../hybrid-search-ranking.md#scores-in-a-hybrid-search-results). Notice that `@search.score` values have a different basis and are uniformly smaller values. RRF evaluates search scores of multiple search results, takes the inverse, and then merges and sorts the combined results. The `top` number of results are returned.
-
-Review the response, consisting of the top k-5 matches out of 7 matching documents in the index:
-
-```json
-{
-  "@odata.count": 7,
-  "value": [
-    {
-      "@search.score": 0.03279569745063782,
-      "HotelName": "Sublime Palace Hotel",
-      "Description": "Sublime Palace Hotel is located in the heart of the historic center of Sublime in an extremely vibrant and lively area within short walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments. Sublime Cliff is part of a lovingly restored 19th century resort, updated for every modern convenience."
-    },
-    {
-      "@search.score": 0.032522473484277725,
-      "HotelName": "Luxury Lion Resort",
-      "Description": "Unmatched Luxury. Visit our downtown hotel to indulge in luxury accommodations. Moments from the stadium and transportation hubs, we feature the best in convenience and comfort."
-    },
-    {
-      "@search.score": 0.03205128386616707,
-      "HotelName": "Nordick's Valley Motel",
-      "Description": "Only 90 miles (about 2 hours) from the nation's capital and nearby most everything the historic valley has to offer. Hiking? Wine Tasting? Exploring the caverns? It's all nearby and we have specially priced packages to help make our B&B your home base for fun while visiting the valley."
-    },
-    {
-      "@search.score": 0.0317460335791111,
-      "HotelName": "Swirling Currents Hotel",
-      "Description": "Spacious rooms, glamorous suites and residences, rooftop pool, walking access to shopping, dining, entertainment and the city center. Each room comes equipped with a microwave, a coffee maker and a minifridge. In-room entertainment includes complimentary Wi-Fi and flat-screen TVs."
-    },
+    Because this is a hybrid query, results are [ranked by Reciprocal Rank Fusion (RRF)](../../hybrid-search-ranking.md#scores-in-a-hybrid-search-results). Notice that `@search.score` values have a different basis and are uniformly smaller values. RRF evaluates search scores of multiple search results, takes the inverse, and then merges and sorts the combined results. The `top` number of results are returned.
+    
+    Review the response, consisting of the top k-5 matches out of 7 matching documents in the index:
+    
+    ```json
     {
-      "@search.score": 0.03125,
-      "HotelName": "Old Century Hotel",
-      "Description": "The hotel is situated in a nineteenth century plaza, which has been expanded and renovated to the highest architectural standards to create a modern, functional and first-class hotel in which art and unique historical elements coexist with the most modern comforts. The hotel also regularly hosts events like wine tastings, beer dinners, and live music."
+      "@odata.count": 7,
+      "value": [
+        {
+          "@search.score": 0.03279569745063782,
+          "HotelName": "Sublime Palace Hotel",
+          "Description": "Sublime Palace Hotel is located in the heart of the historic center of Sublime in an extremely vibrant and lively area within short walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments. Sublime Cliff is part of a lovingly restored 19th century resort, updated for every modern convenience."
+        },
+        {
+          "@search.score": 0.032522473484277725,
+          "HotelName": "Luxury Lion Resort",
+          "Description": "Unmatched Luxury. Visit our downtown hotel to indulge in luxury accommodations. Moments from the stadium and transportation hubs, we feature the best in convenience and comfort."
+        },
+        {
+          "@search.score": 0.03205128386616707,
+          "HotelName": "Nordick's Valley Motel",
+          "Description": "Only 90 miles (about 2 hours) from the nation's capital and nearby most everything the historic valley has to offer. Hiking? Wine Tasting? Exploring the caverns? It's all nearby and we have specially priced packages to help make our B&B your home base for fun while visiting the valley."
+        },
+        {
+          "@search.score": 0.0317460335791111,
+          "HotelName": "Swirling Currents Hotel",
+          "Description": "Spacious rooms, glamorous suites and residences, rooftop pool, walking access to shopping, dining, entertainment and the city center. Each room comes equipped with a microwave, a coffee maker and a minifridge. In-room entertainment includes complimentary Wi-Fi and flat-screen TVs."
+        },
+        {
+          "@search.score": 0.03125,
+          "HotelName": "Old Century Hotel",
+          "Description": "The hotel is situated in a nineteenth century plaza, which has been expanded and renovated to the highest architectural standards to create a modern, functional and first-class hotel in which art and unique historical elements coexist with the most modern comforts. The hotel also regularly hosts events like wine tastings, beer dinners, and live music."
+        }
+      ]
     }
-  ]
-}
-```
-
-Because RRF merges results, it helps to review the inputs individually. 
-
-The following results are from the full-text portion of the query: *historic hotel walk to restaurants and shopping*. In the full text query, the top three results are Sublime Palace Hotel, Stay-Kay City Hotel, and Luxury Lion Resort. The Sublime Palace Hotel has a stronger BM25 relevance score. In the fused query, only two of these matches are in the top 3, and the second match (Stay-Kay City Hotel) doesn't appear in the top 5 at all.
-
-```json
-  "value": [
-    {
-      "@search.score": 1.4868739,
-      "HotelName": "Sublime Palace Hotel",
-      "Description": "Sublime Palace Hotel is located in the heart of the historic center of Sublime in an extremely vibrant and lively area within short walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments. Sublime Cliff is part of a lovingly restored 19th century resort, updated for every modern convenience."
-    },
-    {
-      "@search.score": 1.2699215,
-      "HotelName": "Stay-Kay City Hotel",
-      "Description": "This classic hotel is fully-refurbished and ideally located on the main commercial artery of the city in the heart of New York. A few minutes away is Times Square and the historic centre of the city, as well as other places of interest that make New York one of America's most attractive and cosmopolitan cities."
-    },
-    {
-      "@search.score": 1.2456272,
-      "HotelName": "Luxury Lion Resort",
-      "Description": "Unmatched Luxury. Visit our downtown hotel to indulge in luxury accommodations. Moments from the stadium and transportation hubs, we feature the best in convenience and comfort."
-    },
-    ...
-  ]
-```
-
-In the vector portion query (*quintessential lodging near running trails, eateries, retail*) is a different string so we should expect different results. This query returns Nordick's Valley Motel, Luxury Lion Resort, and Sublime Palace Hotel as the top three matches. In the fused query, these results are in the top 3, but in reverse order.
-
-```json
-  "value": [
-    {
-      "@search.score": 0.6605852,
-      "HotelName": "Nordick's Valley Motel",
-      "Description": "Only 90 miles (about 2 hours) from the nation's capital and nearby most everything the historic valley has to offer. Hiking? Wine Tasting? Exploring the caverns? It's all nearby and we have specially priced packages to help make our B&B your home base for fun while visiting the valley."
-    },
-    {
-      "@search.score": 0.6333684,
-      "HotelName": "Luxury Lion Resort",
-      "Description": "Unmatched Luxury. Visit our downtown hotel to indulge in luxury accommodations. Moments from the stadium and transportation hubs, we feature the best in convenience and comfort."
-    },
-    {
-      "@search.score": 0.605672,
-      "HotelName": "Sublime Palace Hotel",
-      "Description": "Sublime Palace Hotel is located in the heart of the historic center of Sublime in an extremely vibrant and lively area within short walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments. Sublime Cliff is part of a lovingly restored 19th century resort, updated for every modern convenience."
-    },
-   ...
-  ]
-```
+    ```
+    
+    Because RRF merges results, it helps to review the inputs individually. 
+    
+    The following results are from the full-text portion of the query: *historic hotel walk to restaurants and shopping*. In the full text query, the top three results are Sublime Palace Hotel, Stay-Kay City Hotel, and Luxury Lion Resort. The Sublime Palace Hotel has a stronger BM25 relevance score. In the fused query, only two of these matches are in the top 3, and the second match (Stay-Kay City Hotel) doesn't appear in the top 5 at all.
+    
+    ```json
+      "value": [
+        {
+          "@search.score": 1.4868739,
+          "HotelName": "Sublime Palace Hotel",
+          "Description": "Sublime Palace Hotel is located in the heart of the historic center of Sublime in an extremely vibrant and lively area within short walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments. Sublime Cliff is part of a lovingly restored 19th century resort, updated for every modern convenience."
+        },
+        {
+          "@search.score": 1.2699215,
+          "HotelName": "Stay-Kay City Hotel",
+          "Description": "This classic hotel is fully-refurbished and ideally located on the main commercial artery of the city in the heart of New York. A few minutes away is Times Square and the historic centre of the city, as well as other places of interest that make New York one of America's most attractive and cosmopolitan cities."
+        },
+        {
+          "@search.score": 1.2456272,
+          "HotelName": "Luxury Lion Resort",
+          "Description": "Unmatched Luxury. Visit our downtown hotel to indulge in luxury accommodations. Moments from the stadium and transportation hubs, we feature the best in convenience and comfort."
+        },
+        ...
+      ]
+    ```
+    
+    In the vector portion query (*quintessential lodging near running trails, eateries, retail*) is a different string so we should expect different results. This query returns Nordick's Valley Motel, Luxury Lion Resort, and Sublime Palace Hotel as the top three matches. In the fused query, these results are in the top 3, but in reverse order.
+    
+    ```json
+      "value": [
+        {
+          "@search.score": 0.6605852,
+          "HotelName": "Nordick's Valley Motel",
+          "Description": "Only 90 miles (about 2 hours) from the nation's capital and nearby most everything the historic valley has to offer. Hiking? Wine Tasting? Exploring the caverns? It's all nearby and we have specially priced packages to help make our B&B your home base for fun while visiting the valley."
+        },
+        {
+          "@search.score": 0.6333684,
+          "HotelName": "Luxury Lion Resort",
+          "Description": "Unmatched Luxury. Visit our downtown hotel to indulge in luxury accommodations. Moments from the stadium and transportation hubs, we feature the best in convenience and comfort."
+        },
+        {
+          "@search.score": 0.605672,
+          "HotelName": "Sublime Palace Hotel",
+          "Description": "Sublime Palace Hotel is located in the heart of the historic center of Sublime in an extremely vibrant and lively area within short walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments. Sublime Cliff is part of a lovingly restored 19th century resort, updated for every modern convenience."
+        },
+       ...
+      ]
+    ```
 
 ### Semantic hybrid search
 
 Here's the last query in the collection. This hybrid query adds L2 semantic ranking that applies machine reading comprehension over the L1-ranked results, promoting more relevant matches to the top.
 
+To create a semantic hybrid search:
+
 1. Formulate the request. 
 
     ```http
@@ -1054,72 +1070,71 @@ Here's the last query in the collection. This hybrid query adds L2 semantic rank
 
 1. Select **Send Request**. You should have an `HTTP/1.1 200 OK` response. The response body should include the JSON representation of the search results.
 
-Review the response, consisting of a semantic reranking of the RRF-ranked results of the hybrid query. Semantic ranking works off of text inputs. In a text or hybrid query, this input is the text portion of the query (*historic hotel walk to restaurants and shopping*). To use semantic ranking on a pure vector query, such as the first example, or to explicitly control the text used for semantic ranking, [provide a semanticQuery string](../../semantic-how-to-query-request.md#set-up-the-query).
-
-After semantic reranking, Swirling Currents Hotel with its reference to *walking access to shopping, dining, entertainment and the city center* moves into the top spot. The machine comprehension model promotes *walking access to shopping and dining* as a closer match to *walk to restaurants and shopping*.
-
-Before semantic reranking, Sublime Palace, with its reference to *walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments* was number one.  
-
-```json
-{
-  "@odata.count": 7,
-  "@search.answers": [],
-  "value": [
-    {
-      "@search.score": 0.0317460335791111,
-      "@search.rerankerScore": 2.6550590991973877,
-      "HotelId": "49",
-      "HotelName": "Swirling Currents Hotel",
-      "Description": "Spacious rooms, glamorous suites and residences, rooftop pool, walking access to shopping, dining, entertainment and the city center. Each room comes equipped with a microwave, a coffee maker and a minifridge. In-room entertainment includes complimentary Wi-Fi and flat-screen TVs.",
-      "Category": "Suite"
-    },
-    {
-      "@search.score": 0.03279569745063782,
-      "@search.rerankerScore": 2.599761724472046,
-      "HotelId": "4",
-      "HotelName": "Sublime Palace Hotel",
-      "Description": "Sublime Palace Hotel is located in the heart of the historic center of Sublime in an extremely vibrant and lively area within short walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments. Sublime Cliff is part of a lovingly restored 19th century resort, updated for every modern convenience.",
-      "Category": "Boutique"
-    },
-    {
-      "@search.score": 0.03125,
-      "@search.rerankerScore": 2.3480887413024902,
-      "HotelId": "2",
-      "HotelName": "Old Century Hotel",
-      "Description": "The hotel is situated in a nineteenth century plaza, which has been expanded and renovated to the highest architectural standards to create a modern, functional and first-class hotel in which art and unique historical elements coexist with the most modern comforts. The hotel also regularly hosts events like wine tastings, beer dinners, and live music.",
-      "Category": "Boutique"
-    },
-    {
-      "@search.score": 0.03154495730996132,
-      "@search.rerankerScore": 2.2718777656555176,
-      "HotelId": "1",
-      "HotelName": "Stay-Kay City Hotel",
-      "Description": "This classic hotel is fully-refurbished and ideally located on the main commercial artery of the city in the heart of New York. A few minutes away is Times Square and the historic center of the city, as well as other places of interest that make New York one of America's most attractive and cosmopolitan cities.",
-      "Category": "Boutique"
-    },
+    Review the response, consisting of a semantic reranking of the RRF-ranked results of the hybrid query. Semantic ranking works off of text inputs. In a text or hybrid query, this input is the text portion of the query (*historic hotel walk to restaurants and shopping*). To use semantic ranking on a pure vector query, such as the first example, or to explicitly control the text used for semantic ranking, [provide a semanticQuery string](../../semantic-how-to-query-request.md#set-up-the-query).
+    
+    After semantic reranking, Swirling Currents Hotel with its reference to *walking access to shopping, dining, entertainment and the city center* moves into the top spot. The machine comprehension model promotes *walking access to shopping and dining* as a closer match to *walk to restaurants and shopping*.
+    
+    Before semantic reranking, Sublime Palace, with its reference to *walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments* was number one.  
+    
+    ```json
     {
-      "@search.score": 0.03053613007068634,
-      "@search.rerankerScore": 2.0582215785980225,
-      "HotelId": "3",
-      "HotelName": "Gastronomic Landscape Hotel",
-      "Description": "The Gastronomic Hotel stands out for its culinary excellence under the management of William Dough, who advises on and oversees all of the Hotel\u2019s restaurant services.",
-      "Category": "Suite"
+      "@odata.count": 7,
+      "@search.answers": [],
+      "value": [
+        {
+          "@search.score": 0.0317460335791111,
+          "@search.rerankerScore": 2.6550590991973877,
+          "HotelId": "49",
+          "HotelName": "Swirling Currents Hotel",
+          "Description": "Spacious rooms, glamorous suites and residences, rooftop pool, walking access to shopping, dining, entertainment and the city center. Each room comes equipped with a microwave, a coffee maker and a minifridge. In-room entertainment includes complimentary Wi-Fi and flat-screen TVs.",
+          "Category": "Suite"
+        },
+        {
+          "@search.score": 0.03279569745063782,
+          "@search.rerankerScore": 2.599761724472046,
+          "HotelId": "4",
+          "HotelName": "Sublime Palace Hotel",
+          "Description": "Sublime Palace Hotel is located in the heart of the historic center of Sublime in an extremely vibrant and lively area within short walking distance to the sites and landmarks of the city and is surrounded by the extraordinary beauty of churches, buildings, shops and monuments. Sublime Cliff is part of a lovingly restored 19th century resort, updated for every modern convenience.",
+          "Category": "Boutique"
+        },
+        {
+          "@search.score": 0.03125,
+          "@search.rerankerScore": 2.3480887413024902,
+          "HotelId": "2",
+          "HotelName": "Old Century Hotel",
+          "Description": "The hotel is situated in a nineteenth century plaza, which has been expanded and renovated to the highest architectural standards to create a modern, functional and first-class hotel in which art and unique historical elements coexist with the most modern comforts. The hotel also regularly hosts events like wine tastings, beer dinners, and live music.",
+          "Category": "Boutique"
+        },
+        {
+          "@search.score": 0.03154495730996132,
+          "@search.rerankerScore": 2.2718777656555176,
+          "HotelId": "1",
+          "HotelName": "Stay-Kay City Hotel",
+          "Description": "This classic hotel is fully-refurbished and ideally located on the main commercial artery of the city in the heart of New York. A few minutes away is Times Square and the historic center of the city, as well as other places of interest that make New York one of America's most attractive and cosmopolitan cities.",
+          "Category": "Boutique"
+        },
+        {
+          "@search.score": 0.03053613007068634,
+          "@search.rerankerScore": 2.0582215785980225,
+          "HotelId": "3",
+          "HotelName": "Gastronomic Landscape Hotel",
+          "Description": "The Gastronomic Hotel stands out for its culinary excellence under the management of William Dough, who advises on and oversees all of the Hotel\u2019s restaurant services.",
+          "Category": "Suite"
+        }
+      ]
     }
-  ]
-}
-```
+    ```
 
-> [!TIP]
->Semantically ranked results can include more detail, including semantic answers, captions, and highlights. Adding more parameters to the request produces the extra detail. For more information, see [Set up a semantic query](../../semantic-how-to-query-request.md?tabs=rest-query#set-up-the-query).
->
+    > [!TIP]
+    > Semantically ranked results can include more detail, including semantic answers, captions, and highlights. Adding more parameters to the request produces the extra detail. For more information, see [Set up a semantic query](../../semantic-how-to-query-request.md?tabs=rest-query#set-up-the-query).
 
-## Clean up
+## Clean up resources
 
 When you're working in your own subscription, it's a good idea at the end of a project to identify whether you still need the resources you created. Resources left running can cost you money. You can delete resources individually or delete the resource group to delete the entire set of resources.
 
 You can find and manage resources in the Azure portal by using the **All resources** or **Resource groups** link in the leftmost pane.
 
-If you want to keep the search service, but delete the index and documents, you can use the `DELETE` command in the REST client. This command (at the end of your `az-search-vector-quickstart.rest` file) deletes the `hotels-vector-quickstart` index:
+Alternatively, you can send the following request to delete the vector index created in this quickstart.
 
 ```http
 ### Delete an index
@@ -1130,6 +1145,4 @@ DELETE  {{baseUrl}}/indexes/hotels-vector-quickstart?api-version=2025-09-01 HTTP
 
 ## Next steps
 
-As a next step, we recommend learning how to invoke REST API calls [without API keys](../../search-get-started-rbac.md).
-
-You might also want to review the demo code for [Python](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-python), [C#](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-dotnet), or [JavaScript](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-javascript).
++ Learn how to invoke REST API calls [without API keys](../../search-get-started-rbac.md).