from langchain.chains import VectorDBQA
from langchain.llms import OpenAI

# Now we can load the persisted database from disk, and use it as normal. 
vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding)


from langchain.chains import ConversationalRetrievalChain
from langchain.memory import ConversationBufferMemory
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)

qa = ConversationalRetrievalChain.from_llm(
    OpenAI(temperature=0.8), 
    vectordb.as_retriever(search_kwargs={"k": 3}),
    memory=memory
)

from langchain_core.runnables import ConfigurableFieldSpec
from langchain_community.chat_message_histories import ChatMessageHistory
from langchain_core.chat_history import BaseChatMessageHistory
from langchain_core.runnables.history import RunnableWithMessageHistory
from langchain_openai.chat_models import ChatOpenAI
from langchain.schema.output_parser import StrOutputParser
from operator import itemgetter

llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0.7)


store = {}


def get_session_history(user_id: str, conversation_id: str) -> BaseChatMessageHistory:
    if (user_id, conversation_id) not in store:
        store[(user_id, conversation_id)] = ChatMessageHistory()
    return store[(user_id, conversation_id)]

with_message_history = RunnableWithMessageHistory(
    qa,
    get_session_history=get_session_history,
    input_messages_key="question",
    history_messages_key="",
    history_factory_config=[
        ConfigurableFieldSpec(
            id="user_id",
            annotation=str,
            name="User ID",
            description="Unique identifier for the user.",
            default="",
            is_shared=True,
        ),
        ConfigurableFieldSpec(
            id="conversation_id",
            annotation=str,
            name="Conversation ID",
            description="Unique identifier for the conversation.",
            default="",
            is_shared=True,
        ),
    ],
)


user_id = "user123"
conversation_id = "conv456"
question = "list of all candidates in resume?"

# Invoke the chain with the user's question and conversation context
response = with_message_history.invoke(
    { "question":question,},
     config={"configurable": {"user_id": user_id, "conversation_id": conversation_id}},
)
response

but while using this i am getting error that

TypeError Traceback (most recent call last)
in <cell line: 6>()
4
5 # Invoke the chain with the user’s question and conversation context
—-> 6 response = with_message_history.invoke(
7 { “question”:question,},
8 config={“configurable”: {“user_id”: user_id, “conversation_id”: conversation_id}},

17 frames
/usr/local/lib/python3.10/dist-packages/tiktoken/core.py in encode(self, text, allowed_special, disallowed_special)
114 if not isinstance(disallowed_special, frozenset):
115 disallowed_special = frozenset(disallowed_special)
–> 116 if match := _special_token_regex(disallowed_special).search(text):
117 raise_disallowed_special_token(match.group())
118

TypeError: expected string or buffer

can anyone help me out with this error that i am getting while running invoke in google collab i am not able to solve it