Update app.py

app.py

@@ -3,106 +3,55 @@ import torch
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
 import re
 
-# Load AI detection model
-MODEL_NAME = "roberta-base-openai-detector"
-tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
-model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME)
-
-# AI content detection function
-def detect_ai_content(text):
-    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
-    with torch.no_grad():
-        outputs = model(**inputs)
-    scores = torch.nn.functional.softmax(outputs.logits, dim=1)
-    return scores[0][1].item()  # AI probability
-
-# Writing style analysis
-def stylometry_analysis(text):
-    words = text.split()
-    avg_word_length = sum(len(word) for word in words) / len(words) if words else 0
-    complex_words_ratio = len([word for word in words if len(word) > 6]) / len(words) if words else 0
-    passive_voice_count = len(re.findall(r'\b(is|was|were|has been|have been|had been)\b \w+ed', text))
-    return avg_word_length, complex_words_ratio, passive_voice_count
-
-# Semantic similarity analysis
-def semantic_analysis(text):
-    keywords = ["AI", "generated", "neural network", "LLM", "GPT", "transformer"]
-    ai_patterns = sum([text.lower().count(keyword) for keyword in keywords])
-    return ai_patterns / len(text.split()) if text.split() else 0
-
-# Final AI Detection Logic
-def analyze_text(text):
-    ai_probability = detect_ai_content(text)
-    avg_word_length, complex_words_ratio, passive_voice_count = stylometry_analysis(text)
-    semantic_score = semantic_analysis(text)
-
-    is_ai_generated = (
-        ai_probability > 0.5 or 
-        complex_words_ratio > 0.4 or 
-        semantic_score > 0.2
-    )
-
-    result = "🟢 Human-Written" if not is_ai_generated else "🔴 AI-Generated"
-
-    return {
-        "Final Verdict": result,
-        "AI Probability": round(ai_probability, 2),
-        "Complex Words Ratio": round(complex_words_ratio, 2),
-        "Passive Voice Count": passive_voice_count,
-        "Semantic Score": round(semantic_score, 2)
-    }
-
-# Gradio UI
-def gradio_interface(text):
-    result = analyze_text(text)
-    return (
-        result["Final Verdict"],
-        f"{result['AI Probability']:.2f}",
-        f"{result['Complex Words Ratio']:.2f}",
-        str(result["Passive Voice Count"]),
-        f"{result['Semantic Score']:.2f}"
-    )
-
-# Create API Interface
-api_interface = gr.Interface(
-    fn=gradio_interface, 
-    inputs="text", 
-    outputs=["text", "text", "text", "text", "text"]
-)
-
-# Launch API
-api_interface.launch(server_name="0.0.0.0", server_port=7860)
-
-# Run UI
-demo = gr.Blocks()
-with demo:
-    gr.Markdown("# 🚀 Self-Learning AI Content Detector")
-    gr.Markdown("Detect AI-generated text and analyze writing patterns.")
-
-    with gr.Row():
-        text_input = gr.Textbox(label="Enter text to analyze:", lines=5)
-        analyze_button = gr.Button("🔍 Analyze")
-
-    with gr.Row():
-        final_verdict = gr.Textbox(label="Final Verdict", interactive=False)
-        ai_prob = gr.Textbox(label="AI Probability", interactive=False)
-        complex_ratio = gr.Textbox(label="Complex Words Ratio", interactive=False)
-        passive_voice = gr.Textbox(label="Passive Voice Count", interactive=False)
-        semantic_score = gr.Textbox(label="Semantic Score", interactive=False)
-
-    analyze_button.click(gradio_interface, inputs=[text_input], outputs=[final_verdict, ai_prob, complex_ratio, passive_voice, semantic_score])
-
-demo.launch()
-
-import gradio as gr
-
-def analyze_text(text):
-    return {"message": "API is working!", "input_text": text}
-
-api_interface = gr.Interface(
-    fn=analyze_text,
-    inputs="text",
-    outputs="json"
-)
-
-api_interface.launch(server_name="0.0.0.0", server_port=7860)
+# ... (आपका मौजूदा डिटेक्शन कोड यहाँ रहेगा) ...
+
+# ग्रेडियो इंटरफेस को एकीकृत करें
+def create_interface():
+    with gr.Blocks(title="AI Content Detector") as demo:
+        # UI भाग
+        gr.Markdown("# 🚀 Self-Learning AI Content Detector")
+        
+        with gr.Row():
+            input_text = gr.Textbox(label="Enter Text", lines=5)
+            analyze_btn = gr.Button("Analyze")
+        
+        with gr.Row():
+            final_verdict = gr.Textbox(label="Final Verdict")
+            ai_prob = gr.Number(label="AI Probability")
+            complex_ratio = gr.Number(label="Complex Words Ratio")
+            passive_voice = gr.Number(label="Passive Voice Count")
+            semantic_score = gr.Number(label="Semantic Score")
+        
+        # API भाग
+        gr.Markdown("## API Documentation")
+        gr.HTML("""
+            <div>
+                <h3>API Usage:</h3>
+                <p>POST to /api/analyze with JSON payload:</p>
+                <pre>
+{
+    "text": "Your text here"
+}
+                </pre>
+            </div>
+        """)
+        
+        # इवेंट हैंडलिंग
+        analyze_btn.click(
+            fn=analyze_text,
+            inputs=input_text,
+            outputs=[final_verdict, ai_prob, complex_ratio, passive_voice, semantic_score],
+            api_name="analyze"  # API एंडपॉइंट नाम
+        )
+    
+    return demo
+
+# मुख्य एप्लिकेशन
+if __name__ == "__main__":
+    demo = create_interface()
+    demo.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=False,
+        enable_api=True  # API एक्टिवेट करें
+    )