Update ChatEngine.py

ChatEngine.py

@@ -1,24 +1,20 @@
 from llama_index.llms.huggingface import HuggingFaceLLM
 from llama_index.core.base.llms.types import ChatMessage, MessageRole
-from configs import *
+
 class ChatEngine:
-    def __init__(self, llm, retriever, model_name=MODEL_NAME, context_window=CONTEXT_WINDOW, temperature=TEMPERATURE):
+    def __init__(self, retriever):
         """
         Initializes the ChatEngine with a retriever and a language model.
 
         Args:
             retriever (HybridRetriever): An instance of a retriever to fetch relevant documents.
-            model_name (str): The name of the language model to be used.
-            context_window (int, optional): The maximum context window size for the language model. Defaults to 32000.
-            temperature (float, optional): The temperature setting for the language model. Defaults to 0.
         """
 
         self.retriever = retriever
 
-        self.llm = llm
         self.chat_history = []
 
-    def ask_question(self, question):
+    def ask_question(self, question, llm):
         """
         Asks a question to the language model, using the retriever to fetch relevant documents.
 
@@ -38,12 +34,6 @@ class ChatEngine:
         
         self.chat_history.append(ChatMessage(role=MessageRole.ASSISTANT, content=f"Document: {document}"))
 
-        response = self.llm.chat(self.chat_history)
-        response_content = response.content if hasattr(response, 'content') else str(response)
-
-        if response_content.lower().startswith("assistant:"):
-            response_content = response_content[len("assistant:"):].strip()
-            
-        self.chat_history.append(ChatMessage(role=MessageRole.ASSISTANT, content=response_content))
-        
+        response = llm.chat(self.chat_history)
+     
         return response.message.content