Update chatbot.py

chatbot.py

@@ -2,6 +2,7 @@ import os
 import time
 import json
 from groq import Groq
+from transformers import AutoTokenizer
 from langchain_core.runnables import RunnablePassthrough 
 from langchain.memory import ConversationTokenBufferMemory
 from langchain_community.chat_models import ChatOpenAI
@@ -20,8 +21,19 @@ class Comsatsbot:
             "llama-3.1-70b-versatile",
             "llama3-70b-8192"
         ]
-        #self.memory = ConversationTokenBufferMemory(llm=self.llm, max_token_limit=3000)
-        self.memory = ConversationTokenBufferMemory(memory_key="chat_history",return_messages=True,max_token_limit=3000)
+         # self.memory = ConversationTokenBufferMemory(llm=self.llm, max_token_limit=3000)
+
+# Load LLaMA-compatible tokenizer
+        tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
+
+# Define a simple token counting function
+    def llama_token_count(text: str) -> int:
+        return len(tokenizer.encode(text, add_special_tokens=False))
+
+         # Use updated memory setup
+        self.memory = ConversationTokenBufferMemory(memory_key="chat_history", return_messages=True, max_token_limit=3000, tokenizer=llama_token_count)
+
+        
         self.chats_collection = chats_collection
         self.index_path = index_path
         self.hf = hf