Create plagrism.py

plagrism.py

@@ -0,0 +1,44 @@
+import streamlit as st
+import os
+import numpy as np
+import pandas as pd
+from sentence_transformers import SentenceTransformer, util
+
+# Load AI model (BERT)
+model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
+
+# Function to check plagiarism
+def check_plagiarism(text, stored_texts):
+    documents = stored_texts + [text]
+    embeddings = model.encode(documents, convert_to_tensor=True)
+    similarity_matrix = util.pytorch_cos_sim(embeddings[-1], embeddings[:-1])
+    
+    highest_similarity = np.max(similarity_matrix.numpy())
+    return highest_similarity * 100
+
+# Store past documents
+if not os.path.exists("database.csv"):
+    pd.DataFrame(columns=["text"]).to_csv("database.csv", index=False)
+
+def load_database():
+    df = pd.read_csv("database.csv")
+    return df["text"].tolist()
+
+def save_to_database(text):
+    df = pd.read_csv("database.csv")
+    new_df = pd.DataFrame({"text": [text]})
+    df = pd.concat([df, new_df], ignore_index=True)
+    df.to_csv("database.csv", index=False)
+
+# Streamlit UI
+st.title("Plagiarism Detection System using AI")
+input_text = st.text_area("Enter text to check for plagiarism")
+
+if st.button("Check Plagiarism"):
+    stored_texts = load_database()
+    similarity_score = check_plagiarism(input_text, stored_texts)
+    st.write(f"Plagiarism Score: {similarity_score:.2f}%")
+    
+    if similarity_score < 50:
+        save_to_database(input_text)
+        st.success("Text added to database for future reference.")