Create Gradio interface for EcommerceClassifier

app.py

@@ -0,0 +1,51 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Load the EcommerceClassifier model
+model_name = "Maverick98/EcommerceClassifier"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+# Define classification function
+def classify_product(product_text):
+    inputs = tokenizer(product_text, return_tensors="pt", truncation=True, max_length=512)
+    outputs = model(**inputs)
+    predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    
+    # Get the predicted class and confidence
+    predicted_class = torch.argmax(predictions, dim=-1).item()
+    confidence = predictions[0][predicted_class].item()
+    
+    # Map class index to label (adjust based on model's classes)
+    class_labels = model.config.id2label
+    predicted_label = class_labels.get(predicted_class, f"Class {predicted_class}")
+    
+    # Return all probabilities for each class
+    results = {class_labels.get(i, f"Class {i}"): predictions[0][i].item() 
+               for i in range(len(predictions[0]))}
+    
+    return results
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=classify_product,
+    inputs=gr.Textbox(
+        label="Product Description",
+        placeholder="Enter product title or description...",
+        lines=5
+    ),
+    outputs=gr.Label(label="Classification Results", num_top_classes=10),
+    title="🛍️ E-Commerce Product Classifier",
+    description="Fast and accurate e-commerce product classification powered by EcommerceClassifier. Enter a product title or description to classify it into the appropriate category.",
+    examples=[
+        ["Women's Cotton T-Shirt - Casual Summer Wear"],
+        ["Wireless Bluetooth Headphones with Noise Cancellation"],
+        ["Organic Green Tea - 100 Tea Bags"],
+        ["Leather Office Chair with Lumbar Support"],
+    ],
+    theme="soft"
+)
+
+if __name__ == "__main__":
+    demo.launch()