diff --git a/src/services/chatbot.py b/src/services/chatbot.py
index 4a2903a..212a5f5 100644
--- a/src/services/chatbot.py
+++ b/src/services/chatbot.py
@@ -1,5 +1,6 @@
 import os
 import json
+import re
 from openai import OpenAI
 from pydantic import BaseModel, Field
 from typing import List, Dict, Optional
@@ -79,10 +80,14 @@ class Chatbot:
         self.api_key = os.getenv("OPENAI_API_KEY")
         self.client = OpenAI(api_key=self.api_key)
         self.model = "gpt-4o-mini"
+        
+    def clean_text(self, text):
+        # Remove all surrogate characters
+        return re.sub(r'[\uD800-\uDFFF]', '', text)
 
     def _extract_text_from_docs(self, docs):
         """Extract text content from document objects."""
-        return [doc.page_content for doc in docs]
+        return [self.clean_text(doc.page_content) for doc in docs]
     # Existing methods...
 
     def validate_worker(self, question, docs) -> VisionMissionResponse: