Conversation memory with OPENAI_MULTI_FUNCTIONS agent

[liamgwallace]

Is it possible to get memory with the OPENAI_MULTI_FUNCTIONS agent? I tried the same way as other agents but it doesnt work for me. Is this currently possible?

func_llm= ChatOpenAI(temperature=0.2, openai_api_key=OPENAI_API_KEY, model="gpt-3.5-turbo-0613")
func_memory = ConversationBufferMemory(memory_key="chat_history")
func_agent = AgentType.OPENAI_MULTI_FUNCTIONS
agent = initialize_agent(tools = tools, llm = func_llm, agent=func_agent , verbose=verbose, memory=func_memory)

while True:
    query = input(f"\nquestion?\n")
    # Run the agent
    response = agent.run(query)
    print(f"\n{response}")

[dosubot[bot]]

Answer generated by a 🤖

Answer

I found related issues that might be helpful. I did my best to summarize the solutions, but I recommend looking at the related issues yourself.

Open Issues

Chatbot memory integration

No solution found.

---

This response is meant to be useful, save you time, and share context. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

[liamgwallace]

this is not quite the right answer. I am looking for examples where people have implemented chat history with the OPENAI_MULTI_FUNCTIONS agent.

[liamgwallace]

ah found it here I needed some kwargs

from langchain.prompts import MessagesPlaceholder
from langchain.memory import ConversationBufferMemory

agent_kwargs = {
    "extra_prompt_messages": [MessagesPlaceholder(variable_name="memory")],
}
memory = ConversationBufferMemory(memory_key="memory", return_messages=True)

agent = initialize_agent(
    tools,
    llm,
    agent=AgentType.OPENAI_FUNCTIONS,
    verbose=True,
    agent_kwargs=agent_kwargs,
    memory=memory,
)

agent.run("hi")