Update app.py

app.py

@@ -55,13 +55,13 @@ def preprocess_response(response: str) -> str:
     response = response.replace(" ,", ",")
     response = response.replace(" .", ".")
     response = " ".join(response.split())
-    if not any(word in response.lower() for word in ["sorry", "apologize", "empathy"]):
+    if not any(word in response.lower() for word in ["Capa Complaints"]):
         response = "I'm here to help. " + response
     return response
 
 def shorten_response(response: str) -> str:
     """Uses the Zephyr model to shorten and refine the response."""
-    messages = [{"role": "system", "content": "Greet, Shorten and refine this response in a supportive and empathetic manner."}, {"role": "user", "content": response}]
+    messages = [{"role": "system", "content": "Greet, Shorten and refine this response"}, {"role": "user", "content": response}]
     result = client.chat_completion(messages, max_tokens=512, temperature=0.5, top_p=0.9)
     return result.choices[0].message['content'].strip()
 
@@ -78,7 +78,7 @@ def respond(message: str, history: List[Tuple[str, str]]):
     messages.append({"role": "user", "content": message})
 
     # RAG - Retrieve relevant documents if the query suggests exercises or specific information
-    if any(keyword in message.lower() for keyword in ["exercise", "technique", "information", "guide", "help", "how to"]):
+    if any(keyword in message.lower() for keyword in ["exercise", "technique", "information", "guide", "help", "how to", "tell me", "find","which"]):
         retrieved_docs = app.search_documents(message)
         context = "\n".join(retrieved_docs)
         if context.strip():