Update app.py

app.py

@@ -36,46 +36,38 @@ def encode_image_to_base64(image):
     image.save(buffered, format="PNG")
     return base64.b64encode(buffered.getvalue()).decode('utf-8')
 
-
 def analyze_image(image):
     client = OpenAI(api_key=OPENAI_API_KEY)
     base64_image = encode_image_to_base64(image)
 
-    # --- MINIMAL FIX START ---
-    # We build a Python list of dicts, then JSON-encode it:
-    prompt_list = [
-        {
-            "type": "text",
-            "text": """Your task is to determine if the image is surprising or not surprising.
-            if the image is surprising, determine which element, figure or object in the image is making the image surprising and write it only in one sentence with no more then 6 words, otherwise, write 'NA'.
-            Also rate how surprising the image is on a scale of 1-5, where 1 is not surprising at all and 5 is highly surprising.
-            Provide the response as a JSON with the following structure:
-            {
-                "label": "[surprising OR not surprising]",
-                "element": "[element]",
-                "rating": [1-5]
-            }"""
-        },
-        {
-            "type": "image_url",
-            "image_url": {
-                "url": f"data:image/jpeg;base64,{base64_image}"
-            }
-        }
-    ]
-
-    prompt_json = json.dumps(prompt_list)
-
     messages = [
         {
             "role": "user",
-            "content": prompt_json  # content must be a single string
+            "content": [
+                {
+                    "type": "text",
+                    "text": """Your task is to determine if the image is surprising or not surprising.    
+                    if the image is surprising, determine which element, figure or object in the image is making the image surprising and write it only in one sentence with no more then 6 words, otherwise, write 'NA'.    
+                    Also rate how surprising the image is on a scale of 1-5, where 1 is not surprising at all and 5 is highly surprising.
+                    Provide the response as a JSON with the following structure:    
+                    {
+                        "label": "[surprising OR not surprising]",
+                        "element": "[element]",
+                        "rating": [1-5]
+                    }"""
+                },
+                {
+                    "type": "image_url",
+                    "image_url": {
+                        "url": f"data:image/jpeg;base64,{base64_image}"
+                    }
+                }
+            ]
         }
     ]
-    # --- MINIMAL FIX END ---
 
     response = client.chat.completions.create(
-        model="gpt-4o-mini",  # or whichever model you have access to
+        model="gpt-4o-mini",
         messages=messages,
         max_tokens=100,
         temperature=0.1,
@@ -167,7 +159,7 @@ def process_image_detection(image, target_label, surprise_rating):
                 (box[0], box[1]),
                 box[2] - box[0],
                 box[3] - box[1],
-                linewidth=max(2, min(original_size) / 500),
+                linewidth=max(2, min(original_size) / 500),  # Scale line width with image size
                 edgecolor='red',
                 facecolor='none'
             )
@@ -196,6 +188,7 @@ def process_image_detection(image, target_label, surprise_rating):
 
     plt.axis('off')
 
+    # Save with high DPI
     buf = io.BytesIO()
     plt.savefig(buf,
                 format='png',
@@ -240,11 +233,7 @@ def process_and_analyze(image):
         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']}\n"
-                f"Element: {response_data['element']}\n"
-                f"Rating: {response_data['rating']}/5"
-            )
+            analysis_text = f"Label: {response_data['label']}\nElement: {response_data['element']}\nRating: {response_data['rating']}/5"
             return result_image, analysis_text
         else:
             return image, "Not Surprising"
@@ -253,6 +242,7 @@ def process_and_analyze(image):
         return None, f"Error processing image: {str(e)}"
 
 
+# Create Gradio interface
 def create_interface():
     with gr.Blocks() as demo:
         gr.Markdown("# Image Surprise Analysis")
@@ -277,4 +267,4 @@ def create_interface():
 
 if __name__ == "__main__":
     demo = create_interface()
-    demo.launch()
+    demo.launch()