Update app.py

app.py

@@ -54,6 +54,16 @@ query_prompt = PromptTemplate(
 # Keyword Chain
 query_chain = query_prompt | llama3_json | JsonOutputParser()
 
+# Text Cleaning
+def clean_text(text):
+    # Remove links
+    text = re.sub(r'http\S+', '', text)
+    # Remove non-alphanumeric characters (but keep numbers)
+    text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
+    # Remove HTML tags
+    text = re.sub(r'<[^>]+>', '', text)
+    return text
+
 # Google Search and Firecrawl Setup
 def search_and_scrape(keyword):
     search_results = google_search.results(keyword, 1)
@@ -116,7 +126,7 @@ def fact_check_flow(user_question):
     # Join Results
     final_markdown = []
     for results in context_data:
-        final_markdown.append(results['markdown'])
+        final_markdown.append(clean_text(results['markdown']))
 
     final_markdown = ' '.join(final_markdown)