Add see also links to conceptual docs

src/Libraries/Microsoft.Extensions.AI.Abstractions/ChatCompletion/ChatOptions.cs

@@ -7,6 +7,7 @@
 namespace Microsoft.Extensions.AI;
 
 /// <summary>Represents the options for a chat request.</summary>
+/// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#provide-options">Provide options.</related>
 public class ChatOptions
 {
     /// <summary>Gets or sets an optional identifier used to associate a request with an existing conversation.</summary>
@@ -20,6 +21,7 @@ public string? ChatThreadId
     }
 
     /// <summary>Gets or sets an optional identifier used to associate a request with an existing conversation.</summary>
+    /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#stateless-vs-stateful-clients">Stateless vs. stateful clients.</related>
     public string? ConversationId { get; set; }
 
     /// <summary>Gets or sets the temperature for generating chat responses.</summary>
@@ -115,6 +117,7 @@ public string? ChatThreadId
     public ChatToolMode? ToolMode { get; set; }
 
     /// <summary>Gets or sets the list of tools to include with a chat request.</summary>
+    /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#tool-calling">Tool calling.</related>
     [JsonIgnore]
     public IList<AITool>? Tools { get; set; }
 

src/Libraries/Microsoft.Extensions.AI.Abstractions/ChatCompletion/ChatResponse.cs

@@ -92,6 +92,7 @@ public string? ChatThreadId
     /// or may not differ on every response, depending on whether the underlying provider uses a fixed ID for each conversation
     /// or updates it for each message.
     /// </remarks>
+    /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#stateless-vs-stateful-clients">Stateless vs. stateful clients.</related>
     public string? ConversationId { get; set; }
 
     /// <summary>Gets or sets the model ID used in the creation of the chat response.</summary>

src/Libraries/Microsoft.Extensions.AI.Abstractions/ChatCompletion/DelegatingChatClient.cs

@@ -16,6 +16,7 @@ namespace Microsoft.Extensions.AI;
 /// This is recommended as a base type when building clients that can be chained around an underlying <see cref="IChatClient"/>.
 /// The default implementation simply passes each call to the inner client instance.
 /// </remarks>
+/// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#custom-ichatclient-middleware">Custom IChatClient middleware.</related>
 public class DelegatingChatClient : IChatClient
 {
     /// <summary>

src/Libraries/Microsoft.Extensions.AI.Abstractions/ChatCompletion/IChatClient.cs

@@ -24,6 +24,7 @@ namespace Microsoft.Extensions.AI;
 /// </para>
 /// </remarks>
 /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/quickstarts/build-chat-app">Build an AI chat app with .NET.</related>
+/// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#the-ichatclient-interface">The IChatClient interface.</related>
 public interface IChatClient : IDisposable
 {
     /// <summary>Sends chat messages and returns the response.</summary>
@@ -32,6 +33,7 @@ public interface IChatClient : IDisposable
     /// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
     /// <returns>The response messages generated by the client.</returns>
     /// <exception cref="ArgumentNullException"><paramref name="messages"/> is <see langword="null"/>.</exception>
+    /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#request-a-chat-response">Request a chat response.</related>
     Task<ChatResponse> GetResponseAsync(
         IEnumerable<ChatMessage> messages,
         ChatOptions? options = null,
@@ -43,6 +45,7 @@ Task<ChatResponse> GetResponseAsync(
     /// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
     /// <returns>The response messages generated by the client.</returns>
     /// <exception cref="ArgumentNullException"><paramref name="messages"/> is <see langword="null"/>.</exception>
+    /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#request-a-streaming-chat-response">Request a streaming chat response.</related>
     IAsyncEnumerable<ChatResponseUpdate> GetStreamingResponseAsync(
         IEnumerable<ChatMessage> messages,
         ChatOptions? options = null,

src/Libraries/Microsoft.Extensions.AI.Abstractions/Embeddings/IEmbeddingGenerator{TInput,TEmbedding}.cs

@@ -24,6 +24,7 @@ namespace Microsoft.Extensions.AI;
 /// no <see cref="IEmbeddingGenerator{TInput, TEmbedding}"/> instances are used which might employ such mutation.
 /// </para>
 /// </remarks>
+/// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#the-iembeddinggenerator-interface">The IEmbeddingGenerator interface.</related>
 public interface IEmbeddingGenerator<in TInput, TEmbedding> : IEmbeddingGenerator
     where TEmbedding : Embedding
 {
@@ -33,6 +34,7 @@ public interface IEmbeddingGenerator<in TInput, TEmbedding> : IEmbeddingGenerato
     /// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
     /// <returns>The generated embeddings.</returns>
     /// <exception cref="ArgumentNullException"><paramref name="values"/> is <see langword="null"/>.</exception>
+    /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#create-embeddings">Create embeddings.</related>
     Task<GeneratedEmbeddings<TEmbedding>> GenerateAsync(
         IEnumerable<TInput> values,
         EmbeddingGenerationOptions? options = null,

src/Libraries/Microsoft.Extensions.AI/ChatCompletion/ChatClientBuilder.cs

@@ -66,6 +66,7 @@ public IChatClient Build(IServiceProvider? services = null)
     /// <param name="clientFactory">The client factory function.</param>
     /// <returns>The updated <see cref="ChatClientBuilder"/> instance.</returns>
     /// <exception cref="ArgumentNullException"><paramref name="clientFactory"/> is <see langword="null"/>.</exception>
+    /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#functionality-pipelines">Pipelines of functionality.</related>
     public ChatClientBuilder Use(Func<IChatClient, IChatClient> clientFactory)
     {
         _ = Throw.IfNull(clientFactory);
@@ -77,6 +78,7 @@ public ChatClientBuilder Use(Func<IChatClient, IChatClient> clientFactory)
     /// <param name="clientFactory">The client factory function.</param>
     /// <returns>The updated <see cref="ChatClientBuilder"/> instance.</returns>
     /// <exception cref="ArgumentNullException"><paramref name="clientFactory"/> is <see langword="null"/>.</exception>
+    /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#functionality-pipelines">Pipelines of functionality.</related>
     public ChatClientBuilder Use(Func<IChatClient, IServiceProvider, IChatClient> clientFactory)
     {
         _ = Throw.IfNull(clientFactory);
@@ -98,10 +100,11 @@ public ChatClientBuilder Use(Func<IChatClient, IServiceProvider, IChatClient> cl
     /// </param>
     /// <returns>The updated <see cref="ChatClientBuilder"/> instance.</returns>
     /// <remarks>
-    /// This overload may be used when the anonymous implementation needs to provide pre- and/or post-processing, but doesn't
+    /// This overload can be used when the anonymous implementation needs to provide pre-processing and/or post-processing, but doesn't
     /// need to interact with the results of the operation, which will come from the inner client.
     /// </remarks>
     /// <exception cref="ArgumentNullException"><paramref name="sharedFunc"/> is <see langword="null"/>.</exception>
+    /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#functionality-pipelines">Pipelines of functionality.</related>
     public ChatClientBuilder Use(Func<IEnumerable<ChatMessage>, ChatOptions?, Func<IEnumerable<ChatMessage>, ChatOptions?, CancellationToken, Task>, CancellationToken, Task> sharedFunc)
     {
         _ = Throw.IfNull(sharedFunc);
@@ -125,7 +128,7 @@ public ChatClientBuilder Use(Func<IEnumerable<ChatMessage>, ChatOptions?, Func<I
     /// </param>
     /// <returns>The updated <see cref="ChatClientBuilder"/> instance.</returns>
     /// <remarks>
-    /// One or both delegates may be provided. If both are provided, they will be used for their respective methods:
+    /// One or both delegates can be provided. If both are provided, they will be used for their respective methods:
     /// <paramref name="getResponseFunc"/> will provide the implementation of <see cref="IChatClient.GetResponseAsync"/>, and
     /// <paramref name="getStreamingResponseFunc"/> will provide the implementation of <see cref="IChatClient.GetStreamingResponseAsync"/>.
     /// If only one of the delegates is provided, it will be used for both methods. That means that if <paramref name="getResponseFunc"/>
@@ -135,6 +138,7 @@ public ChatClientBuilder Use(Func<IEnumerable<ChatMessage>, ChatOptions?, Func<I
     /// <see cref="IChatClient.GetResponseAsync"/> will be implemented by combining the updates from <paramref name="getStreamingResponseFunc"/>.
     /// </remarks>
     /// <exception cref="ArgumentNullException">Both <paramref name="getResponseFunc"/> and <paramref name="getStreamingResponseFunc"/> are <see langword="null"/>.</exception>
+    /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#functionality-pipelines">Pipelines of functionality.</related>
     public ChatClientBuilder Use(
         Func<IEnumerable<ChatMessage>, ChatOptions?, IChatClient, CancellationToken, Task<ChatResponse>>? getResponseFunc,
         Func<IEnumerable<ChatMessage>, ChatOptions?, IChatClient, CancellationToken, IAsyncEnumerable<ChatResponseUpdate>>? getStreamingResponseFunc)

src/Libraries/Microsoft.Extensions.AI/ChatCompletion/ChatClientStructuredOutputExtensions.cs

@@ -18,6 +18,7 @@ namespace Microsoft.Extensions.AI;
 /// <summary>
 /// Provides extension methods on <see cref="IChatClient"/> that simplify working with structured output.
 /// </summary>
+/// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/quickstarts/structured-output">Request a response with structured output.</related>
 public static class ChatClientStructuredOutputExtensions
 {
     private static readonly AIJsonSchemaCreateOptions _inferenceOptions = new()
@@ -33,9 +34,8 @@ public static class ChatClientStructuredOutputExtensions
     /// <param name="messages">The chat content to send.</param>
     /// <param name="options">The chat options to configure the request.</param>
     /// <param name="useJsonSchema">
-    /// Optionally specifies whether to set a JSON schema on the <see cref="ChatResponseFormat"/>.
-    /// This improves reliability if the underlying model supports native structured output with a schema, but may cause an error if the model does not support it.
-    /// If not specified, the default value is <see langword="true" />.
+    /// <see langword="true" /> to set a JSON schema on the <see cref="ChatResponseFormat"/>; otherwise, <see langword="false" />. The default is <see langword="true" />.
+    /// Using a JSON schema improves reliability if the underlying model supports native structured output with a schema, but might cause an error if the model does not support it.
     /// </param>
     /// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
     /// <returns>The response messages generated by the client.</returns>
@@ -53,14 +53,15 @@ public static Task<ChatResponse<T>> GetResponseAsync<T>(
     /// <param name="chatMessage">The text content for the chat message to send.</param>
     /// <param name="options">The chat options to configure the request.</param>
     /// <param name="useJsonSchema">
-    /// Optionally specifies whether to set a JSON schema on the <see cref="ChatResponseFormat"/>.
-    /// This improves reliability if the underlying model supports native structured output with a schema, but may cause an error if the model does not support it.
+    /// <see langword="true" /> to set a JSON schema on the <see cref="ChatResponseFormat"/>; otherwise, <see langword="false" />.
+    /// Using a JSON schema improves reliability if the underlying model supports native structured output with a schema, but might cause an error if the model does not support it.
     /// If not specified, the default value is determined by the implementation.
     /// If a specific value is required, it must be specified by the caller.
     /// </param>
     /// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
     /// <returns>The response messages generated by the client.</returns>
     /// <typeparam name="T">The type of structured output to request.</typeparam>
+    /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/quickstarts/structured-output">Request a response with structured output.</related>
     public static Task<ChatResponse<T>> GetResponseAsync<T>(
         this IChatClient chatClient,
         string chatMessage,
@@ -74,9 +75,8 @@ public static Task<ChatResponse<T>> GetResponseAsync<T>(
     /// <param name="chatMessage">The chat message to send.</param>
     /// <param name="options">The chat options to configure the request.</param>
     /// <param name="useJsonSchema">
-    /// Optionally specifies whether to set a JSON schema on the <see cref="ChatResponseFormat"/>.
-    /// This improves reliability if the underlying model supports native structured output with a schema, but may cause an error if the model does not support it.
-    /// If not specified, the default value is <see langword="true" />.
+    /// <see langword="true" /> to set a JSON schema on the <see cref="ChatResponseFormat"/>; otherwise, <see langword="false" />. The default is <see langword="true" />.
+    /// Using a JSON schema improves reliability if the underlying model supports native structured output with a schema, but might cause an error if the model does not support it.
     /// </param>
     /// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
     /// <returns>The response messages generated by the client.</returns>
@@ -95,9 +95,8 @@ public static Task<ChatResponse<T>> GetResponseAsync<T>(
     /// <param name="serializerOptions">The JSON serialization options to use.</param>
     /// <param name="options">The chat options to configure the request.</param>
     /// <param name="useJsonSchema">
-    /// Optionally specifies whether to set a JSON schema on the <see cref="ChatResponseFormat"/>.
-    /// This improves reliability if the underlying model supports native structured output with a schema, but may cause an error if the model does not support it.
-    /// If not specified, the default value is <see langword="true" />.
+    /// <see langword="true" /> to set a JSON schema on the <see cref="ChatResponseFormat"/>; otherwise, <see langword="false" />. The default is <see langword="true" />.
+    /// Using a JSON schema improves reliability if the underlying model supports native structured output with a schema, but might cause an error if the model does not support it.
     /// </param>
     /// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
     /// <returns>The response messages generated by the client.</returns>
@@ -117,9 +116,8 @@ public static Task<ChatResponse<T>> GetResponseAsync<T>(
     /// <param name="serializerOptions">The JSON serialization options to use.</param>
     /// <param name="options">The chat options to configure the request.</param>
     /// <param name="useJsonSchema">
-    /// Optionally specifies whether to set a JSON schema on the <see cref="ChatResponseFormat"/>.
-    /// This improves reliability if the underlying model supports native structured output with a schema, but may cause an error if the model does not support it.
-    /// If not specified, the default value is <see langword="true" />.
+    /// <see langword="true" /> to set a JSON schema on the <see cref="ChatResponseFormat"/>; otherwise, <see langword="false" />. The default is <see langword="true" />.
+    /// Using a JSON schema improves reliability if the underlying model supports native structured output with a schema, but might cause an error if the model does not support it.
     /// </param>
     /// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
     /// <returns>The response messages generated by the client.</returns>
@@ -139,16 +137,13 @@ public static Task<ChatResponse<T>> GetResponseAsync<T>(
     /// <param name="serializerOptions">The JSON serialization options to use.</param>
     /// <param name="options">The chat options to configure the request.</param>
     /// <param name="useJsonSchema">
-    /// Optionally specifies whether to set a JSON schema on the <see cref="ChatResponseFormat"/>.
-    /// This improves reliability if the underlying model supports native structured output with a schema, but may cause an error if the model does not support it.
-    /// If not specified, the default value is <see langword="true" />.
+    /// <see langword="true" /> to set a JSON schema on the <see cref="ChatResponseFormat"/>; otherwise, <see langword="false" />. The default is <see langword="true" />.
+    /// Using a JSON schema improves reliability if the underlying model supports native structured output with a schema, but might cause an error if the model does not support it.
     /// </param>
     /// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
     /// <returns>The response messages generated by the client.</returns>
     /// <typeparam name="T">The type of structured output to request.</typeparam>
-    /// <exception cref="ArgumentNullException"><paramref name="chatClient"/> is <see langword="null"/>.</exception>
-    /// <exception cref="ArgumentNullException"><paramref name="messages"/> is <see langword="null"/>.</exception>
-    /// <exception cref="ArgumentNullException"><paramref name="serializerOptions"/> is <see langword="null"/>.</exception>
+    /// <exception cref="ArgumentNullException"><paramref name="chatClient"/> or <paramref name="messages"/> or <paramref name="serializerOptions"/> is <see langword="null"/>.</exception>
     public static async Task<ChatResponse<T>> GetResponseAsync<T>(
         this IChatClient chatClient,
         IEnumerable<ChatMessage> messages,

src/Libraries/Microsoft.Extensions.AI/ChatCompletion/ConfigureOptionsChatClientBuilderExtensions.cs

@@ -27,6 +27,7 @@ public static class ConfigureOptionsChatClientBuilderExtensions
     /// <returns>The <paramref name="builder"/>.</returns>
     /// <exception cref="ArgumentNullException"><paramref name="builder"/> is <see langword="null"/>.</exception>
     /// <exception cref="ArgumentNullException"><paramref name="configure"/> is <see langword="null"/>.</exception>
+    /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#provide-options">Provide options.</related>
     public static ChatClientBuilder ConfigureOptions(
         this ChatClientBuilder builder, Action<ChatOptions> configure)
     {