feat(providers): Add vision and document processing capabilities to providers

ts/abstract.classes.multimodal.ts

@@ -62,4 +62,25 @@ export abstract class MultiModalModel {
    * @throws Error if the provider doesn't support audio generation
    */
   public abstract audio(optionsArg: { message: string }): Promise<NodeJS.ReadableStream>;
+
+  /**
+   * Vision-language processing
+   * @param optionsArg Options containing the image and prompt for analysis
+   * @returns Promise resolving to the model's description or analysis of the image
+   * @throws Error if the provider doesn't support vision tasks
+   */
+  public abstract vision(optionsArg: { image: Buffer; prompt: string }): Promise<string>;
+
+  /**
+   * Document analysis and processing
+   * @param optionsArg Options containing system message, user message, PDF documents, and message history
+   * @returns Promise resolving to the model's analysis of the documents
+   * @throws Error if the provider doesn't support document processing
+   */
+  public abstract document(optionsArg: {
+    systemMessage: string;
+    userMessage: string;
+    pdfDocuments: Uint8Array[];
+    messageHistory: ChatMessage[];
+  }): Promise<{ message: any }>;
 }