Update app.py

app.py

@@ -22,15 +22,26 @@ OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
 def encode_image_to_base64(image):
     # If image is a tuple (as sometimes provided by Gradio), take the first element
     if isinstance(image, tuple):
-        image = image[0]
+        if len(image) > 0 and image[0] is not None:
+            image = image[0]
+        else:
+            raise ValueError("Invalid image tuple provided")
 
     # If image is a numpy array, convert to PIL Image
     if isinstance(image, np.ndarray):
         image = Image.fromarray(image)
+    
+    # If image is a path string, open it
+    elif isinstance(image, str):
+        image = Image.open(image)
 
     # Ensure image is in PIL Image format
     if not isinstance(image, Image.Image):
-        raise ValueError("Input must be a PIL Image, numpy array, or tuple containing an image")
+        raise ValueError("Input must be a PIL Image, numpy array, or valid image path")
+
+    # Convert image to RGB if it's in RGBA mode
+    if image.mode == 'RGBA':
+        image = image.convert('RGB')
 
     buffered = io.BytesIO()
     image.save(buffered, format="PNG")
@@ -218,32 +229,59 @@ def process_and_analyze(image):
         return None, "OpenAI API key not found in environment variables."
 
     try:
-        # Handle different input types
+        # Convert the image to PIL format if needed
         if isinstance(image, tuple):
-            image = image[0]  # Take the first element if it's a tuple
-        if isinstance(image, np.ndarray):
+            if len(image) > 0 and image[0] is not None:
+                image = Image.fromarray(image[0])
+            else:
+                return None, "Invalid image format provided"
+        elif isinstance(image, np.ndarray):
             image = Image.fromarray(image)
+        elif isinstance(image, str):
+            image = Image.open(image)
+        
         if not isinstance(image, Image.Image):
-            raise ValueError("Invalid image format")
+            return None, "Invalid image format"
 
-        # Resize the image by 2x
-        image = image.resize((image.size[0] * 2, image.size[1] * 2), Image.Resampling.LANCZOS)
+        # Ensure image is in RGB mode
+        if image.mode != 'RGB':
+            image = image.convert('RGB')
 
         # Analyze image
         gpt_response = analyze_image(image)
-        response_data = json.loads(gpt_response)
+        
+        try:
+            response_data = json.loads(gpt_response)
+        except json.JSONDecodeError:
+            return None, "Error: Invalid response format from GPT"
+
+        if not all(key in response_data for key in ["label", "element", "rating"]):
+            return None, "Error: Missing required fields in analysis response"
 
         if response_data["label"].lower() == "surprising" and response_data["element"].lower() != "na":
-            result_buf = process_image_detection(image, response_data["element"], response_data["rating"])
-            result_image = Image.open(result_buf)
-            analysis_text = f"Label: {response_data['label']}\nElement: {response_data['element']}\nRating: {response_data['rating']}/5"
-            return result_image, analysis_text
+            try:
+                result_buf = process_image_detection(image, response_data["element"], response_data["rating"])
+                result_image = Image.open(result_buf)
+                analysis_text = (
+                    f"Label: {response_data['label']}\n"
+                    f"Element: {response_data['element']}\n"
+                    f"Rating: {response_data['rating']}/5"
+                )
+                return result_image, analysis_text
+            except Exception as detection_error:
+                return None, f"Error in image detection processing: {str(detection_error)}"
         else:
             return image, "Not Surprising"
 
     except Exception as e:
-        return None, f"Error processing image: {str(e)}"
-
+        error_type = type(e).__name__
+        error_msg = str(e)
+        detailed_error = f"Error ({error_type}): {error_msg}"
+        
+        # Log the error (you might want to add proper logging)
+        print(detailed_error)
+        
+        return None, f"Error processing image: {error_msg}"
 
 
 # Create Gradio interface