Update app.py

app.py

@@ -15,7 +15,7 @@ DB_NAME = "db.sqlite3"
 USERNAME = "aixbi"
 PASSWORD = "aixbi@123"
 MAX_SENTENCES_CHECK = 10
-LOGO_PATH = "aixbi.jpg"  # Place your logo here
+LOGO_PATH = "aixbi.jpg"  # Place your logo file here
 
 # -----------------------------
 # DB INIT
@@ -40,43 +40,51 @@ init_db()
 # MODEL LOADING
 # -----------------------------
 embedder = SentenceTransformer('all-MiniLM-L6-v2')
-tokenizer = AutoTokenizer.from_pretrained("roberta-base-openai-detector")
-model = AutoModelForSequenceClassification.from_pretrained("roberta-base-openai-detector")
+tokenizer = AutoTokenizer.from_pretrained("hello-simpleai/chatgpt-detector-roberta")
+model = AutoModelForSequenceClassification.from_pretrained("hello-simpleai/chatgpt-detector-roberta")
 
 # -----------------------------
-# SAFE TEXT EXTRACTION
+# FILE HANDLING
 # -----------------------------
 def extract_text(file_obj):
-    try:
-        # Save to temp path for compatibility with Hugging Face Spaces
-        with tempfile.NamedTemporaryFile(delete=False) as tmp:
-            shutil.copyfile(file_obj.name, tmp.name)
-            tmp_path = tmp.name
+    """Extracts text safely from PDF/DOCX/TXT"""
+    if file_obj is None:
+        return None
+
+    name = file_obj.name
+    ext = os.path.splitext(name)[1].lower()
 
-        if tmp_path.endswith(".pdf"):
+    # Copy to temp file preserving extension
+    with tempfile.NamedTemporaryFile(delete=False, suffix=ext) as tmp:
+        shutil.copy(file_obj.name, tmp.name)
+        tmp_path = tmp.name
+
+    try:
+        if ext == ".pdf":
             with pdfplumber.open(tmp_path) as pdf:
                 text = " ".join(page.extract_text() or "" for page in pdf.pages)
-                return text.strip() if text else None
-        elif tmp_path.endswith(".docx"):
+        elif ext == ".docx":
             doc = docx.Document(tmp_path)
-            text = " ".join([p.text for p in doc.paragraphs])
-            return text.strip() if text else None
-        elif tmp_path.endswith(".txt"):
+            text = " ".join(p.text for p in doc.paragraphs)
+        elif ext == ".txt":
             with open(tmp_path, "r", encoding="utf-8", errors="ignore") as f:
                 text = f.read()
-            return text.strip() if text else None
         else:
             return None
-    except Exception as e:
-        print("Read error:", e)
+    except:
         return None
 
+    return text.strip() if text else None
+
+# -----------------------------
+# AI & PLAGIARISM DETECTION
+# -----------------------------
 def detect_ai_text(text):
     inputs = tokenizer(text[:512], return_tensors="pt", truncation=True)
     with torch.no_grad():
         outputs = model(**inputs)
     score = torch.softmax(outputs.logits, dim=1)[0][1].item()
-    return score * 100  # Return % probability
+    return score  # probability of AI-generated
 
 def live_plagiarism_check(sentences):
     ddgs = DDGS()
@@ -93,6 +101,9 @@ def live_plagiarism_check(sentences):
     score = (plagiarism_hits / len(samples)) * 100 if samples else 0
     return score, suspicious_sentences
 
+# -----------------------------
+# DB OPS
+# -----------------------------
 def save_result(student_id, student_name, ai_score, plagiarism_score):
     conn = sqlite3.connect(DB_NAME)
     c = conn.cursor()
@@ -108,7 +119,7 @@ def load_results():
     return df
 
 # -----------------------------
-# PDF REPORT WITH LOGO & COLORS
+# PDF REPORT
 # -----------------------------
 class HighlightPDF(FPDF):
     def add_highlighted_sentence(self, sentence, color):
@@ -120,9 +131,9 @@ def generate_pdf_report(student_name, student_id, ai_score, plagiarism_score, su
     pdf = HighlightPDF()
     pdf.add_page()
 
-    # Add logo small on top-left
+    # Logo
     if os.path.exists(LOGO_PATH):
-        pdf.image(LOGO_PATH, 10, 8, 15, 15)
+        pdf.image(LOGO_PATH, 10, 8, 20, 20)
 
     pdf.set_font("Arial", style='B', size=14)
     pdf.cell(200, 10, txt="AIxBI - Ultimate Document Plagiarism Report", ln=True, align='C')
@@ -138,7 +149,7 @@ def generate_pdf_report(student_name, student_id, ai_score, plagiarism_score, su
     pdf.multi_cell(0, 10, txt="Suspicious Sentences Detected:")
     if suspicious_sentences:
         for s in suspicious_sentences:
-            pdf.add_highlighted_sentence(f"- {s}", (255, 200, 200))  # Red for suspicious
+            pdf.add_highlighted_sentence(f"- {s}", (255, 200, 200))  # Red
     else:
         pdf.multi_cell(0, 10, "None detected.")
     pdf.ln(10)
@@ -149,9 +160,9 @@ def generate_pdf_report(student_name, student_id, ai_score, plagiarism_score, su
 
     pdf.multi_cell(0, 10, txt="Recommendations for Student:")
     recommendations = """1. Rewrite detected sentences in your own words.
-2. Add citations for any copied or referenced material.
-3. Avoid using AI content directly—use as guidance, not verbatim.
-4. Use plagiarism tools and proofread before submission."""
+2. Add citations for copied/referenced material.
+3. Avoid direct AI-generated content.
+4. Proofread and recheck plagiarism before submission."""
     pdf.multi_cell(0, 10, recommendations)
 
     pdf.output(output_path)
@@ -175,12 +186,19 @@ def analyze(student_name, student_id, file_obj):
 
     sentences = [s.strip() for s in text.split(". ") if len(s) > 30]
 
-    ai_score = detect_ai_text(text)
+    # AI Detection
+    ai_score = detect_ai_text(text) * 100
+
+    # Live plagiarism
     plagiarism_score, suspicious_sentences = live_plagiarism_check(sentences)
+
+    # Pick sample excerpt
     sample_text = suspicious_sentences[0] if suspicious_sentences else text[:200]
 
+    # Save to DB
     save_result(student_id, student_name, ai_score, plagiarism_score)
 
+    # Generate PDF
     output_pdf = f"{student_id}_report.pdf"
     generate_pdf_report(student_name, student_id, ai_score, plagiarism_score, suspicious_sentences, sample_text, output_pdf)
 
@@ -194,12 +212,13 @@ def show_dashboard():
 # -----------------------------
 # GRADIO UI (LIGHT THEME)
 # -----------------------------
-with gr.Blocks(theme="default", css="body { background-color: #f9f9f9; }") as demo:
+with gr.Blocks(theme="default") as demo:
     with gr.Row():
         if os.path.exists(LOGO_PATH):
-            gr.Image(LOGO_PATH, elem_id="logo", show_label=False, height=50, width=50)
+            gr.Image(LOGO_PATH, elem_id="logo", show_label=False, scale=0.2)
         gr.Markdown("## **AIxBI - Ultimate Document Plagiarism Software**\n#### Professional Thesis & AI Content Detector", elem_id="title")
 
+    # Login
     login_box = gr.Group(visible=True)
     with login_box:
         user = gr.Textbox(label="Username")
@@ -207,6 +226,7 @@ with gr.Blocks(theme="default", css="body { background-color: #f9f9f9; }") as de
         login_btn = gr.Button("Login", variant="primary")
         login_msg = gr.Markdown("")
     
+    # Main App
     app_box = gr.Group(visible=False)
     with app_box:
         with gr.Tab("Check Thesis"):