set up a Gradio interface for our phishing email detection model:

app.py

@@ -1,64 +1,53 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("cybersectony/phishing-email-detection-distilbert_v2.4.1")
+model = AutoModelForSequenceClassification.from_pretrained("cybersectony/phishing-email-detection-distilbert_v2.4.1")
+
+def predict_email(email_text):
+    # Preprocess and tokenize
+    inputs = tokenizer(
+        email_text,
+        return_tensors="pt",
+        truncation=True,
+        max_length=512
+    )
+    
+    # Get prediction
+    with torch.no_grad():
+        outputs = model(**inputs)
+        predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    
+    # Get probabilities for each class
+    probs = predictions[0].tolist()
+    
+    # Create labels dictionary
+    labels = {
+        "Legitimate Email": probs[0],
+        "Phishing URL": probs[1],
+        "Legitimate URL": probs[2],
+        "Phishing URL (Alt)": probs[3]
+    }
+    
+    # Determine the most likely classification
+    max_label = max(labels.items(), key=lambda x: x[1])
+    
+    # Format output
+    result = f"**Prediction**: {max_label[0]}\n**Confidence**: {max_label[1]:.4f}\n\n**All Probabilities**:\n"
+    for label, prob in labels.items():
+        result += f"{label}: {prob:.4f}\n"
+    return result
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=predict_email,
+    inputs=gr.Textbox(lines=5, placeholder="Enter the email text here..."),
+    outputs="text",
+    title="Phishing Email Detection",
+    description="Enter an email text to classify it as legitimate or phishing using a DistilBERT model."
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the interface
+iface.launch()