如何向pandas工具包代理添加会话记忆？

Question

我想添加一个ConversationBufferMemory，pandas_dataframe_agent但到目前为止我还没有成功。

• 我尝试通过 construcor: 添加内存，create_pandas_dataframe_agent(llm, df, verbose=True, memory=memory)这不会破坏代码，但不会导致代理记住我之前的问题。
• 我还尝试通过这段代码将内存添加到代理中：pd_agent.agent.llm_chain.memory = memory。这导致了ValueError: One input key expected got ['input', 'agent_scratchpad']

这是我到目前为止的代码（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

Answer 1

在该版本中0.0.202，我发现将内存添加到 pandas_agent 的唯一方法是这样的（您还需要更改prompt.py文件 - 操作方法写在代码下面）：

We want to create two diffrent models - one for generating code and the second one for the context
llm_code = ChatOpenAI(temperature=0, model_name="gpt-4-0613") #gpt-3.5-turbo-16k-0613
llm_context = ChatOpenAI(temperature=0.5, model_name="gpt-4") #gpt-3.5-turbo

chat_history_buffer = ConversationBufferWindowMemory(
    k=5,
    memory_key="chat_history_buffer",
    input_key="input"
    )

chat_history_summary = ConversationSummaryMemory(
    llm=llm_context, 
    memory_key="chat_history_summary",
    input_key="input"
    )

chat_history_KG = ConversationKGMemory(
    llm=llm_context, 
    memory_key="chat_history_KG",
    input_key="input",
    )

memory = CombinedMemory(memories=[chat_history_buffer, chat_history_summary, chat_history_KG])

pd_agent = create_pandas_dataframe_agent(
    llm_code, 
    df, 
    verbose=True, 
    agent_executor_kwargs={"memory": memory},
    input_variables=['df_head', 'input', 'agent_scratchpad', 'chat_history_buffer', 'chat_history_summary', 'chat_history_KG']
    )

首先，为要使用的每种内存类型指定memory_key. 这memory_key需要传递到input_variables.

您还需要将内存对象传递到 pandas_agent 中，如下所示：

agent_executor_kwargs={"memory": memory}

很重要！！！

您需要更改prompt.py位于的文件../langchain/agents/agent_toolkits/pandas/prompt.py以考虑您添加的新内存。

您唯一需要改变的是PREFIX。这是对我有用的改变：

PREFIX = """
You are working with a pandas dataframe in Python. The name of the dataframe is `df`.
You should use the tools below to answer the question posed of you:

Summary of the whole conversation:
{chat_history_summary}

Last few messages between you and user:
{chat_history_buffer}

Entities that the conversation is about:
{chat_history_KG}
"""