Add multimodal message support with content type enumeration and sub-content models

app/MindWork AI Studio/Provider/OpenAI/ContentType.cs

@@ -0,0 +1,34 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Content types for OpenAI API interactions when using multimodal messages.
+/// </summary>
+public enum ContentType
+{
+    /// <summary>
+    /// Default type for user prompts in multimodal messages. This type is supported across all providers.
+    /// </summary>
+    TEXT,
+    
+    /// <summary>
+    /// Right now only supported by OpenAI and it's responses API. Even other providers that support multimodal messages
+    /// and the responses API do not support this type. They use TEXT instead.
+    /// </summary>
+    INPUT_TEXT,
+    
+    /// <summary>
+    /// Right now only supported by OpenAI and it's responses API. Even other providers that support multimodal messages
+    /// and the responses API do not support this type. They use IMAGE_URL instead.
+    /// </summary>
+    INPUT_IMAGE,
+    
+    /// <summary>
+    /// Right now only supported by OpenAI (responses & chat completion API), Google (chat completions API), and Mistral (chat completions API).
+    /// </summary>
+    INPUT_AUDIO,
+    
+    /// <summary>
+    /// Default type for images in multimodal messages. This type is supported across all providers.
+    /// </summary>
+    IMAGE_URL,
+}

app/MindWork AI Studio/Provider/OpenAI/ISubContent.cs

@@ -0,0 +1,12 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Contract for sub-content in multimodal messages.
+/// </summary>
+public interface ISubContent
+{
+    /// <summary>
+    /// The type of the sub-content.
+    /// </summary>
+    public ContentType Type { get; init; }
+}

app/MindWork AI Studio/Provider/OpenAI/MultimodalMessage.cs

@@ -0,0 +1,13 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// A multimodal chat message model that can contain various types of content.
+/// </summary>
+/// <param name="Content">The list of sub-contents in the message.</param>
+/// <param name="Role">The role of the message.</param>
+public record MultimodalMessage(List<ISubContent> Content, string Role) : IMessage<List<ISubContent>>
+{
+    public MultimodalMessage() : this([], string.Empty)
+    {
+    }
+}

app/MindWork AI Studio/Provider/OpenAI/SubContentImageUrl.cs

@@ -0,0 +1,11 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Image sub-content for multimodal messages.
+/// </summary>
+public record SubContentImageUrl(ContentType Type, string ImageUrl) : ISubContent
+{
+    public SubContentImageUrl() : this(ContentType.IMAGE_URL, string.Empty)
+    {
+    }
+}

app/MindWork AI Studio/Provider/OpenAI/SubContentInputImage.cs

@@ -0,0 +1,14 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Image input sub-content for multimodal messages.
+/// </summary>
+/// <remarks>
+/// Right now, this is used only by OpenAI in its responses API.
+/// </remarks>
+public record SubContentInputImage(ContentType Type, string ImageUrl) : ISubContent
+{
+    public SubContentInputImage() : this(ContentType.INPUT_IMAGE, string.Empty)
+    {
+    }
+}

app/MindWork AI Studio/Provider/OpenAI/SubContentInputText.cs

@@ -0,0 +1,14 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Text input sub-content for multimodal messages.
+/// </summary>
+/// <remarks>
+/// Right now, this is used only by OpenAI in its responses API.
+/// </remarks>
+public record SubContentInputText(ContentType Type, string Text) : ISubContent
+{
+    public SubContentInputText() : this(ContentType.INPUT_TEXT, string.Empty)
+    {
+    }
+}

app/MindWork AI Studio/Provider/OpenAI/SubContentText.cs

@@ -0,0 +1,11 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Text sub-content for multimodal messages.
+/// </summary>
+public record SubContentText(ContentType Type, string Text) : ISubContent
+{
+    public SubContentText() : this(ContentType.TEXT, string.Empty)
+    {
+    }
+}