Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from transformers import pipeline, AutoTokenizer | |
| from PyPDF2 import PdfReader | |
| import docx | |
| import plotly.graph_objects as go | |
| # Page configuration | |
| st.set_page_config(layout="wide") | |
| st.title("📄 AI Content Analyzer") | |
| st.markdown("Upload PDF/Word files to detect AI-generated content") | |
| # Constants | |
| MAX_WORDS = 1000 # Maximum words to analyze | |
| WARNING_THRESHOLD = 1200 # Warning threshold for large files | |
| # Load AI detection model | |
| def load_model(): | |
| model_name = "roberta-base-openai-detector" | |
| tokenizer = AutoTokenizer.from_pretrained(model_name) | |
| return pipeline("text-classification", model=model_name, tokenizer=tokenizer) | |
| 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 Content 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"]) | |
| 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]) | |
| else: | |
| doc = docx.Document(uploaded_file) | |
| text = " ".join([para.text for para in doc.paragraphs]) | |
| word_count = count_words(text) | |
| # Word limit warning | |
| if word_count > WARNING_THRESHOLD: | |
| st.warning(f"⚠️ File contains {word_count} words (Analyzing first {MAX_WORDS} words only)") | |
| if st.button("Analyze Content"): | |
| if word_count < 50: | |
| st.error("❌ Insufficient text for analysis (minimum 50 words required)") | |
| else: | |
| # Process first 1000 words | |
| processed_text = " ".join(text.split()[:MAX_WORDS]) | |
| # Perform 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") | |
| create_gauge(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}%") | |
| with st.expander("View Text Sample"): | |
| st.text(processed_text[:1000] + ("..." if word_count>1000 else "")) |