Sweep: Add xml documentation for LangChain.Providers.Abstractions package where it was missing

src/Providers/Abstractions/src/Chat/ChatModel.cs

@@ -1,29 +1,42 @@
 // ReSharper disable once CheckNamespace
 namespace LangChain.Providers;
 
+/// <summary>
+/// Represents an abstract base class for chat models, providing common functionality and event handling.
+/// </summary>
+/// <param name="id">The unique identifier for the chat model.</param>
 public abstract class ChatModel(string id) : Model<ChatSettings>(id), IChatModel<ChatRequest, ChatResponse, ChatSettings>
 {
     #region Events
 
+    /// <summary>
+    /// Gets or sets the context length for the chat model.
+    /// </summary>
     public virtual int ContextLength { get; protected set; }
 
-    /// <inheritdoc cref="IChatModel.PartialResponseGenerated"/>
+    /// <summary>
+    /// Occurs when a partial response is generated.
+    /// </summary>
+    /// <inheritdoc/>
     public event EventHandler<string>? PartialResponseGenerated;
 
     protected void OnPartialResponseGenerated(string token)
     {
         PartialResponseGenerated?.Invoke(this, token);
     }
 
-    /// <inheritdoc cref="IChatModel.CompletedResponseGenerated"/>
+    /// <inheritdoc/>
     public event EventHandler<string>? CompletedResponseGenerated;
 
     protected void OnCompletedResponseGenerated(string token)
     {
         CompletedResponseGenerated?.Invoke(this, token);
     }
 
-    /// <inheritdoc cref="IChatModel.PromptSent"/>
+    /// <summary>
+    /// Occurs when a prompt is sent to the chat model.
+    /// </summary>
+    /// <inheritdoc/>
     public event EventHandler<string>? PromptSent;
 
 
@@ -34,6 +47,7 @@ protected void OnPromptSent(string prompt)
 
     #endregion
 
+    /// <inheritdoc/>
     public abstract Task<ChatResponse> GenerateAsync(
         ChatRequest request,
         ChatSettings? settings = null,

src/Providers/Abstractions/src/Chat/IChatModel.cs

@@ -6,34 +6,51 @@
 public interface IChatModel : IModel<ChatSettings>
 {
     /// <summary>
-    /// Max input tokens for the model.
+    /// Gets the maximum number of input tokens the model can handle.
+    /// This property defines the upper limit of tokens that can be processed in a single request.
+    /// Implementations should ensure that requests do not exceed this limit.
     /// </summary>
     public int ContextLength { get; }
 
+    /// <summary>
+    /// Occurs when a partial response is generated.
+    /// </summary>
+    event EventHandler<string>? PartialResponseGenerated;
+
+    /// <summary>
+    /// Occurs when a completed response is generated.
+    /// </summary>
+    event EventHandler<string>? CompletedResponseGenerated;
+
+    /// <summary>
+    /// Occurs when a prompt is sent to the chat model.
+    /// </summary>
+    event EventHandler<string>? PromptSent;
+
 
     /// <summary>
     /// Occurs when token generated in streaming mode.
     /// </summary>
     event EventHandler<string>? PartialResponseGenerated;
 
     /// <summary>
     /// Occurs when completed response generated.
     /// </summary>
     event EventHandler<string>? CompletedResponseGenerated;
 
     /// <summary>
     /// Occurs before prompt is sent to the model.
     /// </summary>
     event EventHandler<string>? PromptSent;
 
 
     /// <summary>
-    /// Run the LLM on the given prompt and input.
+    /// Asynchronously generates a chat response based on the provided request and settings.
     /// </summary>
-    /// <param name="request"></param>
-    /// <param name="settings"></param>
-    /// <param name="cancellationToken"></param>
-    /// <returns></returns>
+    /// <param name="request">The chat request containing the prompt and any additional information required for generating a response.</param>
+    /// <param name="settings">Optional chat settings to customize the response generation process. If null, default settings are used.</param>
+    /// <param name="cancellationToken">A cancellation token that can be used to cancel the operation.</param>
+    /// <returns>A task that represents the asynchronous operation, containing the chat response.</returns>
     public Task<ChatResponse> GenerateAsync(
         ChatRequest request,
         ChatSettings? settings = null,

src/Providers/Abstractions/src/Common/IModel.cs

@@ -1,5 +1,9 @@
 namespace LangChain.Providers;
 
+/// <summary>
+/// Represents the base interface for models in the LangChain framework. It defines essential properties and methods that all models must implement, including a unique identifier (Id) and usage tracking.
+/// Implementing classes are expected to provide specific functionalities and data structures relevant to their domain while adhering to this common structure.
+/// </summary>
 /// <summary>
 /// Defines a common model properties.
 /// </summary>

src/Providers/Abstractions/src/Embedding/IEmbeddingModel.cs

@@ -3,21 +3,22 @@ namespace LangChain.Providers;
 
 /// <summary>
 /// Interface for embedding models.
+/// Provides functionality to create embeddings from input data using specific settings.
 /// </summary>
 public interface IEmbeddingModel : IModel<EmbeddingSettings>
 {
     /// <summary>
-    /// 
+    /// Gets the maximum length of input that the embedding model can process.
     /// </summary>
     public int MaximumInputLength { get; }
 
     /// <summary>
-    /// 
+    /// Asynchronously creates embeddings based on the provided request and settings.
     /// </summary>
-    /// <param name="request"></param>
-    /// <param name="settings"></param>
-    /// <param name="cancellationToken"></param>
-    /// <returns></returns>
+    /// <param name="request">The embedding request containing the input data for which embeddings are to be generated.</param>
+    /// <param name="settings">Optional embedding settings to customize the embedding generation process. If null, default settings are used.</param>
+    /// <param name="cancellationToken">A cancellation token that can be used to cancel the operation.</param>
+    /// <returns>A task that represents the asynchronous operation, resulting in an EmbeddingResponse object.</returns>
     Task<EmbeddingResponse> CreateEmbeddingsAsync(
         EmbeddingRequest request,
         EmbeddingSettings? settings = null,

src/Providers/Abstractions/src/ImageToText/IImageToTextModel.cs

@@ -2,17 +2,17 @@
 namespace LangChain.Providers;
 
 /// <summary>
-/// Defines a large language model that can be used for image to text generation.
+/// Defines a large language model interface for converting images to text. This interface outlines the contract for models that can interpret visual content and generate corresponding textual descriptions.
 /// </summary>
 public interface IImageToTextModel : IModel<ImageToTextSettings>
 {
     /// <summary>
     /// Run the LLM on the given image.
     /// </summary>
-    /// <param name="request"></param>
-    /// <param name="settings"></param>
-    /// <param name="cancellationToken"></param>
-    /// <returns></returns>
+    /// <param name="request">The image to text request containing the image and any additional information required for text generation.</param>
+    /// <param name="settings">Optional settings to customize the text generation process. If null, default settings are used.</param>
+    /// <param name="cancellationToken">A cancellation token that can be used to cancel the operation.</param>
+    /// <returns>A task that represents the asynchronous operation, resulting in an ImageToTextResponse object containing the generated text.</returns>
     public Task<ImageToTextResponse> GenerateTextFromImageAsync(
         ImageToTextRequest request,
         ImageToTextSettings? settings = null,

src/Providers/Abstractions/src/Moderation/IModerationModel.cs

@@ -1,22 +1,22 @@
 namespace LangChain.Providers;
 
 /// <summary>
-/// 
+/// Defines the interface for models that perform content moderation. Implementations of this interface should provide mechanisms to assess if given input text violates content policies.
 /// </summary>
 public interface IModerationModel : IModel
 {
     /// <summary>
-    /// 
+    /// Gets the recommended size of text chunks for moderation checks. This size is optimal for the model to accurately assess content for policy violations.
     /// </summary>
     public int RecommendedModerationChunkSize { get; }
 
     /// <summary>
-    /// Given a input text, returns true if the model classifies it as violating provider content policy.
+    /// Asynchronously checks if the given input text violates content policies.
     /// </summary>
-    /// <param name="request"></param>
-    /// <param name="settings"></param>
-    /// <param name="cancellationToken"></param>
-    /// <returns></returns>
+    /// <param name="request">The moderation request containing the text to be checked.</param>
+    /// <param name="settings">Optional moderation settings to customize the check process. If null, default settings are used.</param>
+    /// <param name="cancellationToken">A cancellation token that can be used to cancel the operation.</param>
+    /// <returns>A task that represents the asynchronous operation, resulting in a ModerationResponse indicating if a violation was found.</returns>
     public Task<ModerationResponse> CheckViolationAsync(
         ModerationRequest request,
         ModerationSettings? settings = null,

src/Providers/Abstractions/src/SpeechToText/ISpeechToTextModel.cs

@@ -1,17 +1,17 @@
 namespace LangChain.Providers;
 
 /// <summary>
-/// 
+/// Defines the interface for models that convert speech to text. Implementations of this interface should provide mechanisms to transcribe spoken language into textual form.
 /// </summary>
 public interface ISpeechToTextModel : IModel<SpeechToTextSettings>
 {
     /// <summary>
-    /// Transcribes audio to text.
+    /// Asynchronously transcribes audio to text based on the provided request and settings.
     /// </summary>
-    /// <param name="request"></param>
-    /// <param name="settings"></param>
-    /// <param name="cancellationToken"></param>
-    /// <returns></returns>
+    /// <param name="request">The speech to text request containing the audio data and any additional information required for transcription.</param>
+    /// <param name="settings">Optional settings to customize the transcription process. If null, default settings are used.</param>
+    /// <param name="cancellationToken">A cancellation token that can be used to cancel the operation.</param>
+    /// <returns>A task that represents the asynchronous operation, resulting in a SpeechToTextResponse object.</returns>
     public Task<SpeechToTextResponse> TranscribeAsync(
         SpeechToTextRequest request,
         SpeechToTextSettings? settings = default,

src/Providers/Abstractions/src/TextToImage/ITextToImageModel.cs

@@ -2,22 +2,22 @@
 namespace LangChain.Providers;
 
 /// <summary>
-/// 
+/// Defines the interface for models that generate images based on textual input. Implementations of this interface should provide mechanisms to interpret text and produce corresponding visual content.
 /// </summary>
 public interface ITextToImageModel : IModel<TextToImageSettings>
 {
     /// <summary>
-    /// Occurs before prompt is sent to the model.
+    /// Occurs before a prompt is sent to the model, indicating the initiation of the image generation process based on the provided text.
     /// </summary>
     event EventHandler<string>? PromptSent;
 
     /// <summary>
-    /// 
+    /// Asynchronously generates an image based on the provided text request and settings.
     /// </summary>
-    /// <param name="request"></param>
-    /// <param name="settings"></param>
-    /// <param name="cancellationToken"></param>
-    /// <returns></returns>
+    /// <param name="request">The text to image request containing the text and any additional information required for image generation.</param>
+    /// <param name="settings">Optional settings to customize the image generation process. If null, default settings are used.</param>
+    /// <param name="cancellationToken">A cancellation token that can be used to cancel the operation.</param>
+    /// <returns>A task that represents the asynchronous operation, resulting in a TextToImageResponse object containing the generated image.</returns>
     public Task<TextToImageResponse> GenerateImageAsync(
         TextToImageRequest request,
         TextToImageSettings? settings = default,

src/Providers/Abstractions/src/TextToSpeech/ITextToSpeechModel.cs

@@ -2,17 +2,17 @@
 namespace LangChain.Providers;
 
 /// <summary>
-/// 
+/// Defines the interface for models that convert text to speech. Implementations of this interface should provide mechanisms to generate speech from textual input.
 /// </summary>
 public interface ITextToSpeechModel : IModel
 {
     /// <summary>
-    /// 
+    /// Asynchronously generates speech from the provided text request using specified settings.
     /// </summary>
-    /// <param name="request"></param>
-    /// <param name="settings"></param>
-    /// <param name="cancellationToken"></param>
-    /// <returns></returns>
+    /// <param name="request">The text to speech request containing the text to be converted into speech.</param>
+    /// <param name="settings">Optional settings to customize the speech generation process. If null, default settings are used.</param>
+    /// <param name="cancellationToken">A cancellation token that can be used to cancel the operation.</param>
+    /// <returns>A task that represents the asynchronous operation, resulting in a TextToSpeechResponse object.</returns>
     Task<TextToSpeechResponse> GenerateSpeechAsync(
         TextToSpeechRequest request,
         TextToSpeechSettings? settings = default,