agent的memory如何添加？我尝试了许多方法，始终报错variable chat_history should be a list of base messages

[zhaoyuchen1128]

Checked other resources

• [X] I added a very descriptive title to this issue.
• [X] I searched the LangChain documentation with the integrated search.
• [X] I used the GitHub search to find a similar question and didn't find it.
• [X] I am sure that this is a bug in LangChain rather than my code.
• [X] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

memory = ConversationBufferMemory(memory_key="chat_history") chat_history=[] if co.count_documents(query) != 0:

    for i in range(0, len(co.find(query)[0]["content"]), 1):
        if i % 2 == 0:

           chat_history.append(HumanMessage(content=co.find(query)[0]["content"][i]))

        else:
           chat_history.append(AIMessage(content=co.find(query)[0]["content"][i]))

memory.chat_memory=chat_history
llm = OLLAMA(model=language_model)
print(memory.chat_memory)

tools = load_tools(["google-serper"], llm=llm)

agent = initialize_agent(tools, llm, agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION, verbose=True,memory=memory)
xx=agent.run(content)

Error Message and Stack Trace (if applicable)

ValueError: variable chat_history should be a list of base messages

Description

我就是想将memory加载到agent中，加载到conversationchain时都没问题

System Info

windows latest

[zhaoyuchen1128]

memory如果什么都不操作也报同样的错误

[mackong]

@zhaoyuchen1128 please provide complete example code.