Update app.py

app.py

@@ -3,52 +3,63 @@ import os
 import gradio as gr
 from dotenv import load_dotenv
 import io
-from PIL import Image
 
 # Load environment variables (where your OpenAI key will be stored)
 load_dotenv()
 
-# Load the OpenAI API key from environment variables
-openai.api_key = os.getenv("OPENAI_API_KEY")
+# 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 and generate marketing personas + scoring
+# Function to analyze the ad image using GPT-4o-mini's multimodal capabilities
 def analyze_ad(image):
-    # Convert the PIL image to bytes
+    # 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()
 
-    # Simulate extracting creative copy from the image using OCR (optical character recognition) 
-    # In actual production, you'd integrate an OCR API here to extract text
-    # For simplicity, we'll use placeholder text
-    ad_copy = "Placeholder for ad copy extracted from the 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 copy appealing to the intended demographic?
+    # 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:
+    
+    1. Relevance to Target Audience: Is the ad appealing to the intended demographic?
     2. Emotional Engagement: Does the ad evoke the right emotional response?
-    3. Brand Consistency: Does the copy align with the brand’s voice and values?
-    4. Creativity: How unique or innovative is the language or approach?
+    3. Brand Consistency: Does the ad align with the brand’s voice and values?
+    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.
     """
 
-    # Use the OpenAI API to generate the persona and scores using gpt-4o-mini model
+    # Send the image to GPT-4o-mini for multimodal processing
     response = openai.ChatCompletion.create(
-        model="gpt-4o-mini",  # Use the gpt-4o-mini model as requested
+        model="gpt-4o-mini",  # Use the multimodal GPT-4o-mini model
         messages=[
-            {"role": "system", "content": "You are a marketing expert."},
+            {"role": "system", "content": "You are a marketing expert analyzing an advertisement."},
             {"role": "user", "content": prompt}
         ],
-        max_tokens=300,
         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
     )
 
-    # Extract the response text
+    # Extract the response text from the API output
     result = response['choices'][0]['message']['content']
 
     # Return the result for display
@@ -56,18 +67,18 @@ def analyze_ad(image):
 
 # Function to process the image and run the analysis
 def upload_and_analyze(image):
-    # No need to open the image, as it is already a PIL image
+    # Pass the uploaded image to the analyze_ad function
     result = analyze_ad(image)
     
     return result
 
-# Updated Gradio interface for Hugging Face deployment
+# Gradio interface for Hugging Face deployment
 iface = gr.Interface(
     fn=upload_and_analyze,
     inputs=gr.Image(type="pil", label="Upload Advertisement Image"),  # Use type="pil" for the image input
     outputs=gr.Textbox(label="Marketing Persona and Ad Analysis"),
     title="Advertisement Persona and Scoring Analyzer",
-    description="Upload an advertisement image, and the app will generate marketing personas and evaluate the ad copy based on Relevance, Emotional Engagement, Brand Consistency, Creativity, and Persuasiveness."
+    description="Upload an advertisement image, and the app will generate marketing personas and evaluate the ad based on Relevance, Emotional Engagement, Brand Consistency, Creativity, and Persuasiveness."
 )
 
 # Launch the app