update

app.py

@@ -121,7 +121,6 @@ cleaned_chunks = preprocess_text(academic_tips_text)
 chunk_embeddings = create_embeddings(cleaned_chunks)
 #AI API being used
 client= InferenceClient("openai/gpt-oss-20b")
-response=""
 #defining role of AI and user
 
 def respond(message,history):
@@ -131,8 +130,8 @@ def respond(message,history):
 
     if history:
         messages.extend(history) #keep adding history 
-
-    messages.append({"role":"user", "content": message})
+        
+    messages.append({"role":"user","content": message})
 
     response=client.chat_completion(messages, max_tokens=100) #capping how many words the LLM is allowed to generate as a respond (100 words)