Update app.py

app.py

@@ -20,32 +20,45 @@ 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):
-        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)
+    print(f"Encode image type: {type(image)}")  # Debug print
     
-    # If image is a path string, open it
-    elif isinstance(image, str):
-        image = Image.open(image)
+    try:
+        # If image is a tuple (as sometimes provided by Gradio), take the first element
+        if isinstance(image, tuple):
+            print(f"Image is tuple with length: {len(image)}")  # Debug print
+            if len(image) > 0 and image[0] is not None:
+                if isinstance(image[0], np.ndarray):
+                    image = Image.fromarray(image[0])
+                else:
+                    image = image[0]
+            else:
+                raise ValueError("Invalid image tuple provided")
 
-    # Ensure image is in PIL Image format
-    if not isinstance(image, Image.Image):
-        raise ValueError("Input must be a PIL Image, numpy array, or valid image path")
+        # 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)
 
-    # Convert image to RGB if it's in RGBA mode
-    if image.mode == 'RGBA':
-        image = image.convert('RGB')
+        print(f"Image type after conversion: {type(image)}")  # Debug print
 
-    buffered = io.BytesIO()
-    image.save(buffered, format="PNG")
-    return base64.b64encode(buffered.getvalue()).decode('utf-8')
+        # Ensure image is in PIL Image format
+        if not isinstance(image, Image.Image):
+            raise ValueError(f"Input must be a PIL Image, numpy array, or valid image path. Got {type(image)}")
+
+        # 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")
+        return base64.b64encode(buffered.getvalue()).decode('utf-8')
+    except Exception as e:
+        print(f"Encode error details: {str(e)}")  # Debug print
+        raise
+        
 
 def analyze_image(image):
     client = OpenAI(api_key=OPENAI_API_KEY)
@@ -244,14 +257,21 @@ def process_and_analyze(image):
     if image is None:
         return None, "Please upload an image first."
 
+    print(f"Initial image type: {type(image)}")  # Debug print
+
     if OPENAI_API_KEY is None:
         return None, "OpenAI API key not found in environment variables."
 
     try:
         # Convert the image to PIL format if needed
         if isinstance(image, tuple):
+            print(f"Image is tuple, length: {len(image)}")  # Debug print
             if len(image) > 0 and image[0] is not None:
-                image = Image.fromarray(image[0])
+                if isinstance(image[0], np.ndarray):
+                    image = Image.fromarray(image[0])
+                else:
+                    print(f"First element type: {type(image[0])}")  # Debug print
+                    image = image[0]
             else:
                 return None, "Invalid image format provided"
         elif isinstance(image, np.ndarray):
@@ -259,15 +279,19 @@ def process_and_analyze(image):
         elif isinstance(image, str):
             image = Image.open(image)
         
+        print(f"Image type after conversion: {type(image)}")  # Debug print
+
         if not isinstance(image, Image.Image):
-            return None, "Invalid image format"
+            return None, f"Invalid image format: {type(image)}"
 
         # Ensure image is in RGB mode
         if image.mode != 'RGB':
             image = image.convert('RGB')
 
         # Analyze image
+        print("Starting GPT analysis...")  # Debug print
         gpt_response = analyze_image(image)
+        print(f"GPT response: {gpt_response}")  # Debug print
         
         try:
             response_data = json.loads(gpt_response)
@@ -277,8 +301,11 @@ def process_and_analyze(image):
         if not all(key in response_data for key in ["label", "element", "rating"]):
             return None, "Error: Missing required fields in analysis response"
 
+        print(f"Response data: {response_data}")  # Debug print
+
         if response_data["label"].lower() == "surprising" and response_data["element"].lower() != "na":
             try:
+                print("Starting image detection...")  # Debug print
                 result_buf = process_image_detection(image, response_data["element"], response_data["rating"])
                 result_image = Image.open(result_buf)
                 analysis_text = (
@@ -288,6 +315,7 @@ def process_and_analyze(image):
                 )
                 return result_image, analysis_text
             except Exception as detection_error:
+                print(f"Detection error details: {str(detection_error)}")  # Debug print
                 return None, f"Error in image detection processing: {str(detection_error)}"
         else:
             return image, "Not Surprising"
@@ -296,10 +324,7 @@ def process_and_analyze(image):
         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)
-        
+        print(detailed_error)  # Debug print
         return None, f"Error processing image: {error_msg}"