Update app.py

app.py

@@ -5,75 +5,113 @@ import re
 import pandas as pd
 import gradio as gr
 
-MODEL_NAME = "dejanseo/ai-cop"
-
-# --- Load model ---
+# -----------------------------
+# STRONGEST MODEL
+# -----------------------------
+MODEL_NAME = "Hello-SimpleAI/HC3-Plus-OpenAI-Detector"
+
+# -----------------------------
+# LOAD MODEL
+# -----------------------------
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 dtype = torch.bfloat16 if (device.type=="cuda" and torch.cuda.is_bf16_supported()) else torch.float32
 model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME, torch_dtype=dtype)
 model.to(device).eval()
 
-def sent_tokenize(text):
-    return [s for s in re.split(r'(?<=[\.!?])\s+', text.strip()) if s]
 
-# --- Inference function ---
+# -----------------------------
+# PARAGRAPH TOKENIZER
+# -----------------------------
+def paragraph_split(text):
+    paragraphs = [p.strip() for p in text.split("\n") if p.strip()]
+    return paragraphs
+
+
+# -----------------------------
+# INFERENCE FUNCTION
+# -----------------------------
 def classify_text(text):
     if not text.strip():
         return "⚠️ Please enter some text.", None, None
 
-    sentences = sent_tokenize(text)
-    if not sentences:
-        return "⚠️ No sentences detected.", None, None
+    paragraphs = paragraph_split(text)
+    if not paragraphs:
+        return "⚠️ No paragraphs detected.", None, None
 
+    # Tokenize paragraphs
     inputs = tokenizer(
-        sentences,
+        paragraphs,
         return_tensors="pt",
         padding=True,
         truncation=True,
         max_length=model.config.max_position_embeddings
     ).to(device)
 
+    # Predict
     with torch.no_grad():
         logits = model(**inputs).logits
         probs = F.softmax(logits, dim=-1).cpu()
         preds = torch.argmax(probs, dim=-1).cpu()
 
+    # -----------------------------
+    # BUILD RESULTS
+    # -----------------------------
     results = []
-    highlighted_sentences = []
-    for i, s in enumerate(sentences):
-        p = preds[i].item()
-        conf = probs[i, p].item()
-        label = "AI" if p == 0 else "Human"
+    highlighted_paragraphs = []
+
+    for i, p in enumerate(paragraphs):
+        pred_label = preds[i].item()
+        confidence = probs[i, pred_label].item()
+
+        label = "AI" if pred_label == 0 else "Human"
+        conf_text = f"{confidence:.2f}"
 
-        results.append([s, label, f"{conf:.2f}"])
+        results.append([p, label, conf_text])
+
+        # Highlighting
         if label == "AI":
-            highlighted_sentences.append(f"<span style='color:red; font-weight:bold'>{s}</span>")
+            highlighted_paragraphs.append(
+                f"<p style='color:red; font-weight:bold; margin-bottom:10px'>{p}</p>"
+            )
         else:
-            highlighted_sentences.append(f"<span style='color:green; font-weight:bold'>{s}</span>")
+            highlighted_paragraphs.append(
+                f"<p style='color:green; font-weight:bold; margin-bottom:10px'>{p}</p>"
+            )
 
-    # Overall AI likelihood
+    # -----------------------------
+    # DOCUMENT LEVEL SCORE
+    # -----------------------------
     avg = torch.mean(probs, dim=0)
-    model_ai = avg[0].item() * 100
+    ai_likelihood = avg[0].item() * 100  # class 0 = AI
+
+    highlighted_html = "\n".join(highlighted_paragraphs)
+    df = pd.DataFrame(results, columns=["Paragraph", "Classification", "Confidence"])
 
-    highlighted_text = " ".join(highlighted_sentences)
-    df = pd.DataFrame(results, columns=["Sentence", "Classification", "Confidence"])
-    return f"⚖️ AI Likelihood: {model_ai:.1f}%", highlighted_text, df
+    return f"⚖️ Document AI Likelihood: {ai_likelihood:.1f}%", highlighted_html, df
 
-# --- Gradio Interface ---
+
+# -----------------------------
+# GRADIO INTERFACE
+# -----------------------------
 with gr.Blocks() as demo:
-    gr.Markdown("## 🧠 AI Article Detection by Writenix")
+    gr.Markdown("## 🧠 Writenix Advanced AI Detection (Paragraph-Level)")
 
     with gr.Row():
-        text_input = gr.Textbox(label="Enter text", lines=10, placeholder="Paste your text here…")
+        text_input = gr.Textbox(
+            label="Enter text",
+            lines=14,
+            placeholder="Paste your essay, article, or content here…"
+        )
 
-    classify_btn = gr.Button("Detect AI")
+    classify_btn = gr.Button("🚀 Detect AI")
 
     ai_score = gr.Label(label="Overall AI Likelihood")
     highlighted = gr.HTML()
-    table = gr.Dataframe(headers=["Sentence", "Classification", "Confidence"], wrap=True)
+    table = gr.Dataframe(headers=["Paragraph", "Classification", "Confidence"], wrap=True)
 
     classify_btn.click(classify_text, inputs=text_input, outputs=[ai_score, highlighted, table])
 
+
 if __name__ == "__main__":
     demo.launch()