Update app.py

app.py

@@ -2,56 +2,84 @@ import streamlit as st
 from transformers import pipeline
 from PyPDF2 import PdfReader
 import docx
+import plotly.graph_objects as go
 
 # Page setup
 st.set_page_config(layout="wide")
 st.title("📄 AI Content Analyzer")
-st.markdown("Upload PDF/Word files to detect AI-generated text")
+st.markdown("Upload PDF/Word files (Max 1000 words analysis)")
+
+# Constants
+MAX_WORDS = 1000  # Word limit
+WORD_LIMIT_WARNING = 1500  # Warning threshold
 
-# Load AI detection model
 @st.cache_resource
 def load_model():
     return pipeline("text-classification", model="roberta-base-openai-detector")
 
 detector = load_model()
 
+def count_words(text):
+    return len(text.split())
+
+def create_gauge(score):
+    fig = go.Figure(go.Indicator(
+        mode = "gauge+number",
+        value = score,
+        domain = {'x': [0, 1], 'y': [0, 1]},
+        title = {'text': "AI Probability", 'font': {'size': 20}},
+        gauge = {
+            'axis': {'range': [None, 100], 'tickwidth': 1},
+            'bar': {'color': "darkblue"},
+            'steps': [
+                {'range': [0, 50], 'color': 'green'},
+                {'range': [50, 75], 'color': 'yellow'},
+                {'range': [75, 100], 'color': 'red'}]
+        }))
+    st.plotly_chart(fig, use_container_width=True)
+
 # File uploader
-uploaded_file = st.file_uploader("Upload file (PDF or Word)", type=["pdf", "docx", "txt"])
+uploaded_file = st.file_uploader("Choose file", type=["pdf", "docx", "txt"])
 
 if uploaded_file:
     # Extract text
     text = ""
     if uploaded_file.name.endswith(".pdf"):
         reader = PdfReader(uploaded_file)
-        text = "".join([page.extract_text() or "" for page in reader.pages])
+        text = " ".join([page.extract_text() or "" for page in reader.pages])
     elif uploaded_file.name.endswith(".docx"):
         doc = docx.Document(uploaded_file)
-        text = "\n".join([para.text for para in doc.paragraphs])
+        text = " ".join([para.text for para in doc.paragraphs])
     else:
         text = uploaded_file.read().decode("utf-8")
 
-    # Analyze on button click
-    if st.button("Analyze Content"):
-        if len(text) < 5000:
-            st.warning("Not enough text to analyze!")
+    word_count = count_words(text)
+    
+    if word_count > WORD_LIMIT_WARNING:
+        st.warning(f"⚠️ File has {word_count} words (Analyzing first {MAX_WORDS} words only)")
+    
+    if st.button("Analyze"):
+        if word_count < 50:
+            st.error("❌ Not enough text (min 50 words required)")
         else:
-            result = detector(text[:5000])  # First 5000 chars for speed
-            ai_prob = result[0]['score'] * 100 if result[0]['label'] == 'FAKE' else 100 - (result[0]['score'] * 100)
+            # Process first 1000 words
+            processed_text = " ".join(text.split()[:MAX_WORDS])
+            
+            # Analysis
+            result = detector(processed_text)
+            ai_prob = result[0]['score']*100 if result[0]['label']=='FAKE' else 100-result[0]['score']*100
             
-            # Display results
-            st.subheader("Analysis Results")
+            # Results
+            st.subheader("Results")
+            create_gauge(ai_prob)
             
-            # AI Probability Meter
-            st.metric("AI Content Probability", f"{ai_prob:.2f}%")
-            st.progress(int(ai_prob))
+            col1, col2 = st.columns(2)
+            with col1:
+                st.metric("Words Analyzed", f"{min(word_count, MAX_WORDS)}/{word_count}")
+            with col2:
+                st.metric("AI Probability", f"{ai_prob:.1f}%")
             
-            # File details
-            st.markdown(f"""
-            - **File:** `{uploaded_file.name}`
-            - **Text Length:** {len(text)} characters
-            - **AI Probability:** {ai_prob:.2f}%
-            """)
-
-            # Text preview
-            with st.expander("View extracted text"):
-                st.text(text[:1000] + "...")  # First 1000 chars
+            with st.expander("View analysis details"):
+                st.write(f"**File:** {uploaded_file.name}")
+                st.write(f"**Model:** roberta-base-openai-detector")
+                st.text_area("Sample text", processed_text[:500]+"...", height=150)