如何将会话记忆添加到pandas工具箱代理中?

我想添加一个 ConversationBufferMemory 到 pandas_dataframe_agent 但到目前为止,我没有成功。

• 我试着通过constructor添加记忆: create_pandas_dataframe_agent(llm, df, verbose=True, memory=memory) 这并没有破坏代码,但也没有让代理记住我之前的问题。
• 此外,我还试图通过以下代码片段将内存添加到代理中: pd_agent.agent.llm_chain.memory = memory 。这导致 ValueError: One input key expected got ['input', 'agent_scratchpad']

这是我迄今为止的代码(不起作用):

llm = ChatOpenAI(temperature=0, model_name="gpt-4-0613")

memory = ConversationBufferMemory()

pd_agent = create_pandas_dataframe_agent(llm, df, verbose=True, memory=memory)
#pd_agent.agent.llm_chain.memory = memory #Or if I use this approach the code breaks when calling the .run() methods

pd_agent.run("Look into the data in step 12. Are there any weird patterns? What can we say about this part of the dataset.")
pd_agent.run("What was my previouse question?") #Agent doesn't rember