Merge pull request #251296 from HeidiSteen/heidist-fix

[azure search] GH fix, links

Author: prmerger-automator[bot]

articles/search/cognitive-search-tutorial-blob-dotnet.md

@@ -8,7 +8,7 @@ manager: nitinme
 
 ms.service: cognitive-search
 ms.topic: tutorial
-ms.date: 06/29/2023
+ms.date: 09/13/2023
 ms.custom: devx-track-csharp, devx-track-dotnet
 ---
 
@@ -125,9 +125,6 @@ To interact with your Azure Cognitive Search service you will need the service U
 
 1. In **Settings** > **Keys**, get an admin key for full rights on the service. You can copy either the primary or secondary key.
 
-<!-- This code sample doesn't include a query so the following sentence should be deleted.
-  Get the query key as well. It's a best practice to issue query requests with read-only access. -->
-
    ![Get the service name and admin key](media/search-get-started-javascript/service-name-and-keys.png)
 
 Having a valid key establishes trust, on a per request basis, between the application sending the request and the service that handles it.
@@ -164,10 +161,11 @@ For this project, install version 11 or later of the `Azure.Search.Documents` an
 
     ```json
     {
-      "SearchServiceUri": "Put your search service URI here",
-      "SearchServiceAdminApiKey": "Put your primary or secondary API key here",
-      "SearchServiceQueryApiKey": "Put your query API key here",
-      "AzureBlobConnectionString": "Put your Azure Blob connection string here",
+      "SearchServiceUri": "<YourSearchServiceUri>",
+      "SearchServiceAdminApiKey": "<YourSearchServiceAdminApiKey>",
+      "SearchServiceQueryApiKey": "<YourSearchServiceQueryApiKey>",
+      "AzureAIServicesKey": "<YourMultiRegionAzureAIServicesKey>",
+      "AzureBlobConnectionString": "<YourAzureBlobConnectionString>"
     }
     ```
 
@@ -204,7 +202,7 @@ public static void Main(string[] args)
 
     string searchServiceUri = configuration["SearchServiceUri"];
     string adminApiKey = configuration["SearchServiceAdminApiKey"];
-    string cognitiveServicesKey = configuration["CognitiveServicesKey"];
+    string azureAiServicesKey = configuration["AzureAIServicesKey"];
 
     SearchIndexClient indexClient = new SearchIndexClient(new Uri(searchServiceUri), new AzureKeyCredential(adminApiKey));
     SearchIndexerClient indexerClient = new SearchIndexerClient(new Uri(searchServiceUri), new AzureKeyCredential(adminApiKey));
@@ -512,12 +510,14 @@ private static KeyPhraseExtractionSkill CreateKeyPhraseExtractionSkill()
 Build the [`SearchIndexerSkillset`](/dotnet/api/azure.search.documents.indexes.models.searchindexerskillset) using the skills you created.
 
 ```csharp
-private static SearchIndexerSkillset CreateOrUpdateDemoSkillSet(SearchIndexerClient indexerClient, IList<SearchIndexerSkill> skills,string cognitiveServicesKey)
+private static SearchIndexerSkillset CreateOrUpdateDemoSkillSet(SearchIndexerClient indexerClient, IList<SearchIndexerSkill> skills,string azureAiServicesKey)
 {
     SearchIndexerSkillset skillset = new SearchIndexerSkillset("demoskillset", skills)
     {
+        // Azure AI services was formerly known as Cognitive Services.
+        // The APIs still use the old name, so we need to create a CognitiveServicesAccountKey object.
         Description = "Demo skillset",
-        CognitiveServicesAccount = new CognitiveServicesAccountKey(cognitiveServicesKey)
+        CognitiveServicesAccount = new CognitiveServicesAccountKey(azureAiServicesKey)
     };
 
     // Create the skillset in your search service.
@@ -559,7 +559,7 @@ skills.Add(splitSkill);
 skills.Add(entityRecognitionSkill);
 skills.Add(keyPhraseExtractionSkill);
 
-SearchIndexerSkillset skillset = CreateOrUpdateDemoSkillSet(indexerClient, skills, cognitiveServicesKey);
+SearchIndexerSkillset skillset = CreateOrUpdateDemoSkillSet(indexerClient, skills, azureAiServicesKey);
 ```
 
 ### Step 3: Create an index

articles/search/cognitive-search-tutorial-blob-python.md

@@ -9,7 +9,7 @@ ms.author: heidist
 ms.service: cognitive-search
 ms.devlang: python
 ms.topic: tutorial
-ms.date: 08/26/2022
+ms.date: 09/13/2023
 ms.custom: devx-track-python
 ---
 

articles/search/cognitive-search-tutorial-blob.md

@@ -6,7 +6,7 @@ author: HeidiSteen
 ms.author: heidist
 ms.service: cognitive-search
 ms.topic: tutorial
-ms.date: 01/31/2023
+ms.date: 09/13/2023
 ---
 
 # Tutorial: Use REST and AI to generate searchable content from Azure blobs

articles/search/retrieval-augmented-generation-overview.md

@@ -8,12 +8,12 @@ author: HeidiSteen
 ms.author: heidist
 ms.service: cognitive-search
 ms.topic: conceptual
-ms.date: 08/31/2023
+ms.date: 09/13/2023
 ---
 
 # Retrieval Augmented Generation (RAG) in Azure Cognitive Search
 
-Retrieval Augmentation Generation (RAG) is an architecture that augments the capabilities of a Large Language Model (LLM) like ChatGPT by adding an information retrieval system that provides the data. Adding an information retrieval system gives you control over the data used by an LLM. For an enterprise solution, RAG architecture means that you can constrain natural language processing to *your enterprise content* sourced from documents, images, audio, and video.
+Retrieval Augmentation Generation (RAG) is an architecture that augments the capabilities of a Large Language Model (LLM) like ChatGPT by adding an information retrieval system that provides the data. Adding an information retrieval system gives you control over the data used by an LLM when it formulates a response. For an enterprise solution, RAG architecture means that you can constrain natural language processing to *your enterprise content* sourced from vectorized documents, images, audio, and video.
 
 The decision about which information retrieval system to use is critical because it determines the inputs to the LLM. The information retrieval system should provide:
 
@@ -25,7 +25,7 @@ The decision about which information retrieval system to use is critical because
 
 + Integration with LLMs.
 
-Azure Cognitive Search is a [proven solution for information retrieval](https://github.com/Azure-Samples/azure-search-openai-demo) in a RAG architecture because it provides compatible indexing and query capabilities, with the infrastructure and security of the Azure cloud. Through code and other components, you can design a comprehensive RAG solution that includes all of the elements for generative AI over your proprietary content.
+Azure Cognitive Search is a [proven solution for information retrieval](https://github.com/Azure-Samples/azure-search-openai-demo) in a RAG architecture. It provides indexing and query capabilities, with the infrastructure and security of the Azure cloud. Through code and other components, you can design a comprehensive RAG solution that includes all of the elements for generative AI over your proprietary content.
 
 > [!NOTE]
 > New to LLM and RAG concepts? This [video clip](https://youtu.be/2meEvuWAyXs?t=404) from a Microsoft presentation offers a simple explanation.
@@ -38,7 +38,7 @@ Microsoft has several built-in implementations for using Cognitive Search in a R
 
 + Azure Machine Learning, a search index can be used as a [vector store](/azure/machine-learning/concept-vector-stores). You can [create a vector index in an Azure Machine Learning prompt flow](/azure/machine-learning/how-to-create-vector-index) that uses your Cognitive Search service for storage and retrieval.
 
-If you need a custom approach however, you can create your own custom RAG solution. The remainder of this article explores how Cognitive Search fits into a custom solution.
+If you need a custom approach however, you can create your own custom RAG solution. The remainder of this article explores how Cognitive Search fits into a custom RAG solution.
 
 > [!NOTE]
 > Prefer to look at code? You can review the [Azure Cognitive Search OpenAI demo](https://github.com/Azure-Samples/azure-search-openai-demo) for an example.
@@ -77,7 +77,7 @@ Cognitive Search doesn't provide native LLM integration, web frontends, or vecto
 
 In Cognitive Search, all searchable content is stored in a search index that's hosted on your search service in the cloud. A search index is designed for fast queries with millisecond response times, so its internal data structures exist to support that objective. To that end, a search index stores *indexed content*, and not whole content files like entire PDFs or images. Internally, the data structures include inverted indexes of [tokenized text](https://lucene.apache.org/core/7_5_0/test-framework/org/apache/lucene/analysis/Token.html), vector indexes for embeddings, and unaltered text for cases where verbatim matching is required (for example, in filters, fuzzy search, regular expression queries).
 
-When you set up the data for your RAG solution, you use the features that create and load an index in Cognitive Search. An index includes fields that duplicate or represent your source content. An index field might be simple transference (a title or description in a source document becomes a title or description in a search index), or a field might contain the output of an external process, such as vectorization or skill processing that generates a text description of an image.
+When you set up the data for your RAG solution, you use the features that create and load an index in Cognitive Search. An index includes fields that duplicate or represent your source content. An index field might be simple transference (a title or description in a source document becomes a title or description in a search index), or a field might contain the output of an external process, such as vectorization or skill processing that generates a representation or text description of an image.
 
 Since you probably know what kind of content you want to search over, consider the indexing features that are applicable to each content type:
 
@@ -244,10 +244,8 @@ print("\n-------------------\nPrompt:\n" + prompt)
 > [!NOTE]
 > Some Cognitive Search features are intended for human interaction and aren't useful in a RAG pattern. Specifically, you can skip autocomplete and suggestions. Other features like facets and orderby might be useful, but would be uncommon in a RAG scenario.
 
-<!-- Vanity URL for this article, currently used only in the vector search overview doc
-https://aka.ms/what-is-rag -->
-
 ## See also
 
 + [Retrieval Augmented Generation: Streamlining the creation of intelligent natural language processing models](https://ai.meta.com/blog/retrieval-augmented-generation-streamlining-the-creation-of-intelligent-natural-language-processing-models/)
 + [Retrieval Augmented Generation using Azure Machine Learning prompt flow](/azure/machine-learning/concept-retrieval-augmented-generation)
++ [Azure Cognitive Search and LangChain: A Seamless Integration for Enhanced Vector Search Capabilities](https://techcommunity.microsoft.com/t5/azure-ai-services-blog/azure-cognitive-search-and-langchain-a-seamless-integration-for/ba-p/3901448)

articles/search/vector-search-overview.md

@@ -134,4 +134,4 @@ Azure Cognitive Search uses Hierarchical Navigable Small Worlds (HNSW), which is
 + [Try the quickstart](search-get-started-vector.md)
 + [Learn more about vector indexing](vector-search-how-to-create-index.md)
 + [Learn more about vector queries](vector-search-how-to-query.md)
-
++ [Azure Cognitive Search and LangChain: A Seamless Integration for Enhanced Vector Search Capabilities](https://techcommunity.microsoft.com/t5/azure-ai-services-blog/azure-cognitive-search-and-langchain-a-seamless-integration-for/ba-p/3901448)