feat(provider.anthropic): Add support for vision and document processing in Anthropic provider

readme.md

@@ -26,7 +26,7 @@ This command installs the package and adds it to your project's dependencies.
 
 ### Anthropic
 - Models: Claude-3-opus-20240229
-- Features: Chat, Streaming
+- Features: Chat, Streaming, Vision, Document Processing
 - Configuration:
   ```typescript
   anthropicToken: 'your-anthropic-token'
@@ -148,7 +148,7 @@ const audioStream = await smartAi.openaiProvider.audio({
 
 ### Document Processing
 
-For providers that support document processing (OpenAI and Ollama):
+For providers that support document processing (OpenAI, Ollama, and Anthropic):
 
 ```typescript
 // Using OpenAI
@@ -166,6 +166,14 @@ const analysis = await smartAi.ollamaProvider.document({
   messageHistory: [],
   pdfDocuments: [pdfBuffer] // Uint8Array of PDF content
 });
+
+// Using Anthropic with Claude 3
+const anthropicAnalysis = await smartAi.anthropicProvider.document({
+  systemMessage: 'You are a document analysis assistant',
+  userMessage: 'Please analyze this document and extract key information',
+  messageHistory: [],
+  pdfDocuments: [pdfBuffer] // Uint8Array of PDF content
+});
 ```
 
 Both providers will:
@@ -175,7 +183,7 @@ Both providers will:
 
 ### Vision Processing
 
-For providers that support vision tasks (OpenAI and Ollama):
+For providers that support vision tasks (OpenAI, Ollama, and Anthropic):
 
 ```typescript
 // Using OpenAI's GPT-4 Vision
@@ -189,6 +197,12 @@ const analysis = await smartAi.ollamaProvider.vision({
   image: imageBuffer,
   prompt: 'Analyze this image in detail'
 });
+
+// Using Anthropic's Claude 3
+const anthropicAnalysis = await smartAi.anthropicProvider.vision({
+  image: imageBuffer,
+  prompt: 'Please analyze this image and describe what you see'
+});
 ```
 
 ## Error Handling