Update tools.py

tools.py

@@ -59,7 +59,26 @@ def use_vision_model(question: str, images: List[Image.Image]) -> str:
         }
     ]
 
-    output = image_model(messages).content
+    # Get the response and properly extract the content as a string
+    response = image_model(messages)
+    
+    # Handle different response formats
+    if hasattr(response, 'content'):
+        output = response.content
+        # If content is a list, extract text from it
+        if isinstance(output, list):
+            text_parts = []
+            for item in output:
+                if isinstance(item, dict) and 'text' in item:
+                    text_parts.append(item['text'])
+                elif isinstance(item, str):
+                    text_parts.append(item)
+            output = ' '.join(text_parts) if text_parts else str(output)
+        elif not isinstance(output, str):
+            output = str(output)
+    else:
+        output = str(response)
+    
     print(f'Model returned: {output}')
     return output
 
@@ -327,5 +346,5 @@ def transcribe_audio(audio_file_path: str) -> str:
     """
     model_size: str = "small"
     model = whisper.load_model(model_size)
-    result = model.transcribe(audio_file_path)
+    result = model.transcribe(audio_path)
     return result['text']