Update app.py

app.py

@@ -3,6 +3,8 @@ import os
 import gradio as gr
 from dotenv import load_dotenv
 import io
+from PIL import Image
+import pytesseract  # Import Tesseract OCR
 
 # Load environment variables (where your OpenAI key will be stored)
 load_dotenv()
@@ -10,17 +12,17 @@ load_dotenv()
 # Load the OpenAI API key from environment variables and strip any trailing newlines or spaces
 openai.api_key = os.getenv("OPENAI_API_KEY").strip()
 
-# Function to analyze the ad image using GPT-4o-mini's multimodal capabilities
+# Function to analyze the ad and generate marketing personas + scoring
 def analyze_ad(image):
-    # Convert the PIL image to bytes (as required for API input)
-    image_bytes = io.BytesIO()
-    image.save(image_bytes, format='PNG')
-    image_bytes = image_bytes.getvalue()
+    # Extract text from the image using Tesseract OCR
+    ad_copy = pytesseract.image_to_string(image)
 
-    # Multimodal request: Image input to GPT-4o-mini (image + text analysis)
-    prompt = """
-    Analyze the following ad image. Extract the ad copy text from the image and generate a marketing persona. 
-    Then, provide a score (out of 10) for each of the following:
+    if not ad_copy.strip():  # Check if OCR extracted any text
+        return "No text was detected in the image. Please upload a clearer ad image."
+
+    # Prompt for the marketing persona and scoring rubric
+    prompt = f"""
+    Analyze the following ad copy and generate a marketing persona. Then, provide a score (out of 10) for each of the following:
     
     1. Relevance to Target Audience: Is the ad appealing to the intended demographic?
     2. Emotional Engagement: Does the ad evoke the right emotional response?
@@ -28,35 +30,20 @@ def analyze_ad(image):
     4. Creativity: How unique or innovative is the ad's design and text approach?
     5. Persuasiveness: Does the ad motivate action, such as clicking or purchasing?
     
+    Ad Copy: {ad_copy}
+    
     Provide the persona description and the scores in table form with a final score.
     """
 
-    # Send the image to GPT-4o-mini for multimodal processing
+    # Send the prompt to GPT-4o-mini for analysis
     response = openai.ChatCompletion.create(
-        model="gpt-4o-mini",  # Use the multimodal GPT-4o-mini model
+        model="gpt-4o-mini",  # Use the gpt-4o-mini model as requested
         messages=[
             {"role": "system", "content": "You are a marketing expert analyzing an advertisement."},
             {"role": "user", "content": prompt}
         ],
         temperature=0.7,
-        max_tokens=400,
-        functions=[
-            {
-                "name": "analyze_image",
-                "description": "Analyze an image to extract text and generate marketing insights",
-                "parameters": {
-                    "type": "image",
-                    "properties": {
-                        "image": {
-                            "type": "string",
-                            "description": "The input image for analysis"
-                        }
-                    },
-                    "required": ["image"]
-                }
-            }
-        ],
-        function_call={"name": "analyze_image", "arguments": {"image": image_bytes}}  # Sending the image as input
+        max_tokens=400
     )
 
     # Extract the response text from the API output