Update app.py

app.py

@@ -3,6 +3,7 @@ import streamlit as st
 import requests
 import feedparser
 import datetime
+from fuzzywuzzy import fuzz
 from dotenv import load_dotenv
 from duckduckgo_search import DDGS
 
@@ -34,6 +35,23 @@ def call_llm(messages, model="deepseek/deepseek-chat-v3-0324:free", max_tokens=2
         raise RuntimeError(f"Invalid response: {result}")
     return result["choices"][0]["message"]["content"]
 
+def check_plagiarism(text, query, threshold=70):
+    web_results = search_duckduckgo(query, max_results=5)
+    plagiarized_snippets = []
+
+    for result in web_results:
+        snippet = result.get("snippet", "")
+        similarity = fuzz.token_set_ratio(text, snippet)
+        if similarity >= threshold:
+            plagiarized_snippets.append({
+                "title": result["title"],
+                "url": result["url"],
+                "snippet": snippet,
+                "similarity": similarity
+            })
+
+    return plagiarized_snippets
+
 # --- Source Utilities ---
 def get_arxiv_papers(query, max_results=3):
     from urllib.parse import quote_plus
@@ -161,6 +179,17 @@ if st.button("Run Research Agent"):
             st.session_state.chat_history.append({"role": "user", "content": topic})
             st.session_state.chat_history.append({"role": "assistant", "content": response})
             st.markdown(response)
+            # Check for plagiarism (optional feature)
+plagiarism_hits = check_plagiarism(response, topic)
+
+if plagiarism_hits:
+    st.warning("⚠️ Potential overlap with existing web content detected.")
+    st.subheader("🕵️ Plagiarism Check Results")
+    for hit in plagiarism_hits:
+        st.markdown(f"**{hit['title']}** - [{hit['url']}]({hit['url']})")
+        st.markdown(f"> _Similarity: {hit['similarity']}%_\n\n{hit['snippet']}")
+else:
+    st.success("✅ No significant overlaps found. Content appears original.")
         except Exception as e:
             st.error(f"Failed: {e}")