Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -177,76 +177,90 @@ def main():
|
|
177 |
apply_theme(selected_theme)
|
178 |
|
179 |
# --- Title and Welcome ---
|
180 |
-
slider_value = st.slider("AI Plagiarism Detection Tool", min_value=0, max_value=100, value=50)
|
181 |
st.markdown("<h1 class='welcome-text'>Welcome to AI & Plagiarism Detection</h1>", unsafe_allow_html=True)
|
182 |
|
183 |
-
# ---
|
184 |
-
|
185 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
186 |
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
if uploaded_files:
|
191 |
-
for uploaded_file in uploaded_files:
|
192 |
-
file_size = len(uploaded_file.getvalue())
|
193 |
-
if file_size > 1000000000:
|
194 |
-
st.error(f"{uploaded_file.name}: File size exceeds the 1GB limit.")
|
195 |
-
continue
|
196 |
-
|
197 |
-
try:
|
198 |
-
if uploaded_file.type == "application/pdf":
|
199 |
-
raw_text = extract_text_from_pdf(uploaded_file)
|
200 |
-
elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
|
201 |
-
raw_text = extract_text_from_docx(uploaded_file)
|
202 |
-
else:
|
203 |
-
raw_text = None
|
204 |
-
st.error(f"{uploaded_file.name}: Unsupported file type")
|
205 |
continue
|
206 |
|
207 |
-
|
208 |
-
|
209 |
-
|
210 |
-
|
211 |
-
|
212 |
-
|
213 |
-
|
214 |
-
|
215 |
-
|
216 |
-
|
217 |
-
|
218 |
-
|
219 |
-
|
220 |
-
|
221 |
-
|
222 |
-
|
223 |
-
|
224 |
-
|
225 |
-
|
226 |
-
|
227 |
-
|
228 |
-
|
229 |
-
|
230 |
-
|
231 |
-
|
232 |
-
|
233 |
-
|
234 |
-
|
235 |
-
|
236 |
-
|
237 |
-
|
238 |
-
|
239 |
-
|
240 |
-
|
241 |
-
|
242 |
-
|
243 |
-
|
244 |
-
|
245 |
-
|
246 |
-
|
247 |
-
|
248 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
249 |
|
250 |
# --- Call Main ---
|
251 |
if __name__ == "__main__":
|
|
|
252 |
main()
|
|
|
177 |
apply_theme(selected_theme)
|
178 |
|
179 |
# --- Title and Welcome ---
|
|
|
180 |
st.markdown("<h1 class='welcome-text'>Welcome to AI & Plagiarism Detection</h1>", unsafe_allow_html=True)
|
181 |
|
182 |
+
# --- Tabs for File Upload and Text Input ---
|
183 |
+
tab1, tab2 = st.tabs(["Upload File", "Enter Text"])
|
184 |
+
|
185 |
+
with tab1:
|
186 |
+
uploaded_files = st.file_uploader("Upload files (PDF or DOCX)", type=["pdf", "docx"], accept_multiple_files=True)
|
187 |
+
if uploaded_files:
|
188 |
+
for uploaded_file in uploaded_files:
|
189 |
+
file_size = len(uploaded_file.getvalue())
|
190 |
+
if file_size > 1000000000:
|
191 |
+
st.error(f"{uploaded_file.name}: File size exceeds the 1GB limit.")
|
192 |
+
continue
|
193 |
+
|
194 |
+
try:
|
195 |
+
if uploaded_file.type == "application/pdf":
|
196 |
+
raw_text = extract_text_from_pdf(uploaded_file)
|
197 |
+
elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
|
198 |
+
raw_text = extract_text_from_docx(uploaded_file)
|
199 |
+
else:
|
200 |
+
raw_text = None
|
201 |
+
st.error(f"{uploaded_file.name}: Unsupported file type")
|
202 |
+
continue
|
203 |
|
204 |
+
except Exception as e:
|
205 |
+
st.error(f"Error processing {uploaded_file.name}: {e}")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
206 |
continue
|
207 |
|
208 |
+
if raw_text:
|
209 |
+
# Split text into manageable chunks
|
210 |
+
text_chunks = split_text_into_chunks(raw_text, tokenizer)
|
211 |
+
process_and_display(text_chunks, uploaded_file.name, ai_detection_model, tokenizer, plagiarism_model)
|
212 |
+
|
213 |
+
with tab2:
|
214 |
+
manual_text = st.text_area("Enter text here", "")
|
215 |
+
if manual_text:
|
216 |
+
text_chunks = split_text_into_chunks(manual_text, tokenizer)
|
217 |
+
process_and_display(text_chunks, "Manual Input", ai_detection_model, tokenizer, plagiarism_model)
|
218 |
+
|
219 |
+
# --- Helper function to process text and display results ---
|
220 |
+
def process_and_display(text_chunks, source_name, ai_detection_model, tokenizer, plagiarism_model):
|
221 |
+
# AI Detection
|
222 |
+
ai_percentage_avg = None
|
223 |
+
human_percentage = None
|
224 |
+
if ai_detection_model:
|
225 |
+
ai_percentages = detect_ai_content(text_chunks, ai_detection_model)
|
226 |
+
if ai_percentages:
|
227 |
+
ai_percentage_avg = sum(ai_percentages) / len(ai_percentages) * 100
|
228 |
+
human_percentage = 100 - ai_percentage_avg
|
229 |
+
|
230 |
+
# Plagiarism Check
|
231 |
+
plagiarism_percentage = None
|
232 |
+
if tokenizer and plagiarism_model:
|
233 |
+
plagiarism_percentage = plagiarism_check(text_chunks, tokenizer, plagiarism_model)
|
234 |
+
|
235 |
+
# --- Tiled Output ---
|
236 |
+
with st.container():
|
237 |
+
st.markdown(f"<div class='output-box'><h3>{source_name}</h3></div>", unsafe_allow_html=True)
|
238 |
+
|
239 |
+
col1, col2 = st.columns(2)
|
240 |
+
|
241 |
+
with col1:
|
242 |
+
st.markdown("<div class='output-box'><h4>AI Detection:</h4></div>", unsafe_allow_html=True)
|
243 |
+
if ai_percentage_avg is not None:
|
244 |
+
st.metric(label="AI Content", value=f"{ai_percentage_avg:.2f}%", delta="AI Generated")
|
245 |
+
st.metric(label="Human Written", value=f"{human_percentage:.2f}%", delta="Humanized Text")
|
246 |
+
else:
|
247 |
+
st.write("AI Detection not available")
|
248 |
+
|
249 |
+
with col2:
|
250 |
+
st.markdown("<div class='output-box'><h4>Plagiarism Detection:</h4></div>", unsafe_allow_html=True)
|
251 |
+
if plagiarism_percentage is not None:
|
252 |
+
st.metric(label="Plagiarism", value=f"{plagiarism_percentage:.2f}%", delta="Plagiarized" if plagiarism_percentage > 0 else "Original")
|
253 |
+
else:
|
254 |
+
st.write("Plagiarism Detection not available")
|
255 |
+
|
256 |
+
# --- Load models globally ---
|
257 |
+
@st.cache_resource
|
258 |
+
def load_models():
|
259 |
+
ai_detection_model = load_ai_detection_model()
|
260 |
+
tokenizer, plagiarism_model = load_plagiarism_model()
|
261 |
+
return ai_detection_model, tokenizer, plagiarism_model
|
262 |
|
263 |
# --- Call Main ---
|
264 |
if __name__ == "__main__":
|
265 |
+
ai_detection_model, tokenizer, plagiarism_model = load_models() # Load models
|
266 |
main()
|