Update app.py

app.py

@@ -1,25 +1,116 @@
 import gradio as gr
 import pandas as pd
 import tempfile
+import os
 from io import BytesIO
+import re
+import openai
 
 def process_woocommerce_data_in_memory(netcom_file):
     """
     Reads the uploaded NetCom CSV file in-memory, processes it to the WooCommerce format,
     and returns the resulting CSV as bytes, suitable for download.
     """
-    # Define the brand-to-logo mapping
+    # Define the brand-to-logo mapping with updated URLs
     brand_logo_map = {
-        "Amazon Web Services": "https://devthe.tech/wp-content/uploads/2025/02/aws.png",
-        "Cisco": "https://devthe.tech/wp-content/uploads/2025/02/cisco-e1738593292198-1.webp",
-        "Microsoft": "https://devthe.tech/wp-content/uploads/2025/01/Microsoft-e1737494120985-1.png"
+        "Amazon Web Services": "/wp-content/uploads/2025/04/aws.png",
+        "Cisco": "/wp-content/uploads/2025/04/cisco-e1738593292198-1.webp",
+        "Microsoft": "/wp-content/uploads/2025/04/Microsoft-e1737494120985-1.png",
+        "Google Cloud": "/wp-content/uploads/2025/04/Google_Cloud.png",
+        "EC Council": "/wp-content/uploads/2025/04/Ec_Council.png",
+        "ITIL": "/wp-content/uploads/2025/04/ITIL.webp",
+        "PMI": "/wp-content/uploads/2025/04/PMI.png",
+        "Comptia": "/wp-content/uploads/2025/04/Comptia.png",
+        "Autodesk": "/wp-content/uploads/2025/04/autodesk.png",
+        "ISC2": "/wp-content/uploads/2025/04/ISC2.png",
+        "AICerts": "/wp-content/uploads/2025/04/aicerts-logo-1.png"
     }
 
+    # Default prerequisite text for courses without prerequisites
+    default_prerequisite = "No specific prerequisites are required for this course. Basic computer literacy and familiarity with fundamental concepts in the subject area are recommended for the best learning experience."
+
     # 1. Read the uploaded CSV into a DataFrame
     netcom_df = pd.read_csv(netcom_file.name, encoding='latin1')
     netcom_df.columns = netcom_df.columns.str.strip()  # standardize column names
 
+    # Initialize OpenAI client
+    client = openai.OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+    
+    # Process descriptions in batches of 500
+    def process_text_with_ai(texts, instruction):
+        """Process text with GPT-4o-mini"""
+        if not texts:
+            return []
+            
+        results = []
+        batch_size = 500
+        
+        for i in range(0, len(texts), batch_size):
+            batch = texts[i:i+batch_size]
+            batch_prompts = [f"{instruction}\n\nText: {text}" for text in batch]
+            
+            batch_results = []
+            for prompt in batch_prompts:
+                response = client.chat.completions.create(
+                    model="gpt-4o-mini",
+                    messages=[{"role": "user", "content": prompt}],
+                    temperature=0
+                )
+                batch_results.append(response.choices[0].message.content)
+            
+            results.extend(batch_results)
+        
+        return results
+    
+    # Prepare descriptions for AI processing
+    descriptions = netcom_df['Decription'].fillna("").tolist()
+    objectives = netcom_df['Objectives'].fillna("").tolist()
+    prerequisites = netcom_df['RequiredPrerequisite'].fillna("").tolist()
+    agendas = netcom_df['Outline'].fillna("").tolist()
+    
+    # Process with AI
+    short_descriptions = process_text_with_ai(
+        descriptions, 
+        "Create a concise 250-character summary of this course description:"
+    )
+    
+    condensed_descriptions = process_text_with_ai(
+        descriptions, 
+        "Condense this description to maximum 750 characters in paragraph format, with clean formatting:"
+    )
+    
+    formatted_objectives = process_text_with_ai(
+        objectives, 
+        "Format these objectives into a bullet list format with clean formatting. Start each bullet with '• ':"
+    )
+    
+    formatted_prerequisites = []
+    for prereq in prerequisites:
+        if not prereq or pd.isna(prereq) or prereq.strip() == "":
+            formatted_prerequisites.append(default_prerequisite)
+        else:
+            formatted_prereq = process_text_with_ai(
+                [prereq], 
+                "Format these prerequisites into a bullet list format with clean formatting. Start each bullet with '• ':"
+            )[0]
+            formatted_prerequisites.append(formatted_prereq)
+    
+    formatted_agendas = process_text_with_ai(
+        agendas, 
+        "Format this agenda into a bullet list format with clean formatting. Start each bullet with '• ':"
+    )
+    
+    # Add processed text to dataframe
+    netcom_df['Short_Description'] = short_descriptions
+    netcom_df['Condensed_Description'] = condensed_descriptions
+    netcom_df['Formatted_Objectives'] = formatted_objectives
+    netcom_df['Formatted_Prerequisites'] = formatted_prerequisites
+    netcom_df['Formatted_Agenda'] = formatted_agendas
+
     # 2. Create aggregated dates and times for each Course ID
+    # Sort by Course ID and date first
+    netcom_df = netcom_df.sort_values(['Course ID', 'Course Start Date'])
+    
     date_agg = (
         netcom_df.groupby('Course ID')['Course Start Date']
         .apply(lambda x: ','.join(x.astype(str).unique()))
@@ -53,12 +144,10 @@ def process_woocommerce_data_in_memory(netcom_file):
         'Name': parent_products['Course Name'],
         'Published': 1,
         'Visibility in catalog': 'visible',
-        'Short description': parent_products['Decription'],
-        'Description': parent_products['Decription'],
+        'Short description': parent_products['Short_Description'],
+        'Description': parent_products['Condensed_Description'],
         'Tax status': 'taxable',
         'In stock?': 1,
-        'Stock': 1,
-        'Sold individually?': 1,
         'Regular price': parent_products['SRP Pricing'].replace('[\$,]', '', regex=True),
         'Categories': 'courses',
         'Images': parent_products['Vendor'].map(brand_logo_map).fillna(''),
@@ -76,13 +165,13 @@ def process_woocommerce_data_in_memory(netcom_file):
         'Attribute 3 value(s)': parent_products['Aggregated_Times'],
         'Attribute 3 visible': 'visible',
         'Attribute 3 global': 1,
-        'Meta: outline': parent_products['Outline'],
+        'Meta: outline': parent_products['Formatted_Agenda'],
         'Meta: days': parent_products['Duration'],
         'Meta: location': 'Virtual',
         'Meta: overview': parent_products['Target Audience'],
-        'Meta: objectives': parent_products['Objectives'],
-        'Meta: prerequisites': parent_products['RequiredPrerequisite'].fillna(''),
-        'Meta: agenda': parent_products['Outline']  # Agenda now copies the outline
+        'Meta: objectives': parent_products['Formatted_Objectives'],
+        'Meta: prerequisites': parent_products['Formatted_Prerequisites'],
+        'Meta: agenda': parent_products['Formatted_Agenda']
     })
 
     # 6. Create child (variation) products
@@ -92,12 +181,10 @@ def process_woocommerce_data_in_memory(netcom_file):
         'Name': netcom_df['Course Name'],
         'Published': 1,
         'Visibility in catalog': 'visible',
-        'Short description': netcom_df['Decription'],
-        'Description': netcom_df['Decription'],
+        'Short description': netcom_df['Short_Description'],
+        'Description': netcom_df['Condensed_Description'],
         'Tax status': 'taxable',
         'In stock?': 1,
-        'Stock': 1,
-        'Sold individually?': 1,
         'Regular price': netcom_df['SRP Pricing'].replace('[\$,]', '', regex=True),
         'Categories': 'courses',
         'Images': netcom_df['Vendor'].map(brand_logo_map).fillna(''),
@@ -117,23 +204,23 @@ def process_woocommerce_data_in_memory(netcom_file):
         ),
         'Attribute 3 visible': 'visible',
         'Attribute 3 global': 1,
-        'Meta: outline': netcom_df['Outline'],
+        'Meta: outline': netcom_df['Formatted_Agenda'],
         'Meta: days': netcom_df['Duration'],
         'Meta: location': 'Virtual',
         'Meta: overview': netcom_df['Target Audience'],
-        'Meta: objectives': netcom_df['Objectives'],
-        'Meta: prerequisites': netcom_df['RequiredPrerequisite'].fillna(''),
-        'Meta: agenda': netcom_df['Outline']  # Agenda now copies the outline
+        'Meta: objectives': netcom_df['Formatted_Objectives'],
+        'Meta: prerequisites': netcom_df['Formatted_Prerequisites'],
+        'Meta: agenda': netcom_df['Formatted_Agenda']
     })
 
     # 7. Combine parent + child
     woo_final_df = pd.concat([woo_parent_df, woo_child_df], ignore_index=True)
 
-    # 8. Desired column order
+    # 8. Desired column order (removed Stock and Sold individually?)
     column_order = [
         'Type', 'SKU', 'Name', 'Published', 'Visibility in catalog',
         'Short description', 'Description', 'Tax status', 'In stock?',
-        'Stock', 'Sold individually?', 'Regular price', 'Categories', 'Images',
+        'Regular price', 'Categories', 'Images',
         'Parent', 'Brands', 'Attribute 1 name', 'Attribute 1 value(s)', 'Attribute 1 visible',
         'Attribute 1 global', 'Attribute 2 name', 'Attribute 2 value(s)', 'Attribute 2 visible',
         'Attribute 2 global', 'Attribute 3 name', 'Attribute 3 value(s)', 'Attribute 3 visible',
@@ -174,4 +261,5 @@ app = gr.Interface(
 )
 
 if __name__ == "__main__":
+    openai_api_key = os.getenv("OPENAI_API_KEY")
     app.launch()