first initial 2

app.py

@@ -1,106 +1,77 @@
-# app.py
 import gradio as gr
 from transformers import pipeline
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
 import torch
-import spacy
 
 # Load the zero-shot classification model
-model_name = "MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli"
-classifier = pipeline("zero-shot-classification", model=model_name)
-
-# Load spaCy for brand name extraction
-nlp = spacy.load("en_core_web_sm")
-
-def extract_brand_names(text):
-    doc = nlp(text)
-    # Look for organization names and proper nouns that might be brands
-    potential_brands = []
-    for ent in doc.ents:
-        if ent.label_ in ["ORG", "PRODUCT"]:
-            potential_brands.append((ent.text, 0.9))  # High confidence for named entities
-    
-    # Also check for proper nouns that might be brands
-    for token in doc:
-        if token.pos_ == "PROPN" and token.text not in [brand[0] for brand in potential_brands]:
-            potential_brands.append((token.text, 0.7))  # Lower confidence for proper nouns
-    
-    return potential_brands
+try:
+    model_name = "MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli"
+    classifier = pipeline("zero-shot-classification", 
+                        model=model_name, 
+                        device=0 if torch.cuda.is_available() else -1)
+except Exception as e:
+    print(f"Error loading main model: {e}")
+    # Fallback to a lighter model if the first one fails
+    model_name = "facebook/bart-large-mnli"
+    classifier = pipeline("zero-shot-classification", model=model_name)
 
 def classify_product(ad_text):
     if not ad_text.strip():
         return "Please enter some ad text."
     
-    # Category classification
-    category_hypothesis = "This is an advertisement for a product in the category of"
-    candidate_categories = [
-        "Software", "Electronics", "Clothing", "Food & Beverage", 
-        "Healthcare", "Financial Services", "Entertainment",
-        "Home & Garden", "Automotive", "Education"
-    ]
-    
-    category_result = classifier(
-        ad_text,
-        candidate_labels=candidate_categories,
-        hypothesis_template=category_hypothesis,
-        multi_label=False
-    )
-    
-    # Product type classification
-    product_hypothesis = "This is specifically a"
-    # We'll let the model infer specific product types based on the text
-    product_result = classifier(
-        ad_text,
-        candidate_labels=[
-            "software application", "mobile app", "subscription service",
-            "physical product", "digital product", "professional service",
-            "consumer device", "platform", "tool"
-        ],
-        hypothesis_template=product_hypothesis,
-        multi_label=False
-    )
-    
-    # Brand extraction
-    brands = extract_brand_names(ad_text)
-    
-    # Format results
-    results = {
-        "Category": {
-            "classification": category_result["labels"][0],
-            "confidence": f"{category_result['scores'][0]:.2%}"
-        },
-        "Product Type": {
-            "classification": product_result["labels"][0],
-            "confidence": f"{product_result['scores'][0]:.2%}"
-        },
-        "Detected Brands": [
-            {"brand": brand, "confidence": f"{conf:.2%}"}
-            for brand, conf in brands
-        ] if brands else "No specific brand detected"
-    }
-    
-    # Format output string
-    output = f"""
+    try:
+        # Category classification
+        category_result = classifier(
+            ad_text,
+            candidate_labels=[
+                "Software", "Electronics", "Clothing", "Food & Beverage", 
+                "Healthcare", "Financial Services", "Entertainment",
+                "Home & Garden", "Automotive", "Education"
+            ],
+            hypothesis_template="This is an advertisement for a product in the category of",
+            multi_label=False
+        )
+        
+        # Product type classification
+        product_result = classifier(
+            ad_text,
+            candidate_labels=[
+                "software application", "mobile app", "subscription service",
+                "physical product", "digital product", "professional service",
+                "consumer device", "platform", "tool"
+            ],
+            hypothesis_template="This is specifically a",
+            multi_label=False
+        )
+        
+        # Format output string
+        output = f"""
 📊 Analysis Results:
 
-🏷️ Category: {results['Category']['classification']}
-   Confidence: {results['Category']['confidence']}
+🏷️ Category: {category_result['labels'][0]}
+   Confidence: {category_result['scores'][0]:.2%}
 
-📦 Product Type: {results['Product Type']['classification']}
-   Confidence: {results['Product Type']['confidence']}
-
-🏢 Brand Detection:"""
-    
-    if isinstance(results["Detected Brands"], list):
-        for brand_info in results["Detected Brands"]:
-            output += f"\n   • {brand_info['brand']} (Confidence: {brand_info['confidence']})"
-    else:
-        output += f"\n   {results['Detected Brands']}"
+📦 Product Type: {product_result['labels'][0]}
+   Confidence: {product_result['scores'][0]:.2%}
+"""
+        
+        # Additional product details from text
+        if any(brand_keyword in ad_text.lower() for brand_keyword in ['by', 'from', 'introducing', 'new']):
+            product_name_result = classifier(
+                ad_text,
+                candidate_labels=["contains brand name", "does not contain brand name"],
+                hypothesis_template="This text",
+                multi_label=False
+            )
+            if product_name_result['labels'][0] == "contains brand name":
+                output += "\n🏢 Brand Mention: Likely contains a brand name"
+        
+        return output
     
-    return output
+    except Exception as e:
+        return f"An error occurred: {str(e)}\nPlease try with different text or contact support."
 
 # Create Gradio interface
-iface = gr.Interface(
+demo = gr.Interface(
     fn=classify_product,
     inputs=gr.Textbox(
         lines=5,
@@ -109,10 +80,13 @@ iface = gr.Interface(
     ),
     outputs=gr.Textbox(label="Analysis Results"),
     title="AI Powered Product Identifier from Ad Text",
-    description="Paste your marketing ad text to identify the product category, type, and brand mentions.",
+    description="Paste your marketing ad text to identify the product category and type. Maximum 100 words.",
     examples=[
         ["Experience seamless productivity with our new CloudWork Pro subscription. This AI-powered workspace solution helps remote teams collaborate better with smart document sharing, real-time editing, and integrated chat features. Starting at $29/month."],
         ["Introducing the new iPhone 15 Pro with revolutionary A17 Pro chip. Capture stunning photos with our advanced 48MP camera system. Available in titanium finish with all-day battery life. Pre-order now at Apple stores nationwide."],
     ],
     theme=gr.themes.Soft()
-)
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -1,5 +1,3 @@
 gradio==4.7.1
 transformers==4.34.0
-torch==2.0.1
-spacy==3.7.2
-https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.0/en_core_web_sm-3.7.0.tar.gz
+torch==2.0.1