CODEWITHSUNDEEP
pythonlangchainlarge-language-modelpy-langchain
Jakub Szlaur
Jakub Szlaur

Reputation: 2132

How to add combination memory to an Agent with tools?

I want to create an Agent that will have 2 tools and a combined memory.

I have successfully created an example of combined memory: 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])

How do I now pass this memory to the agent? I tried via the memory = memory but without success.

Do I need to change the template somehow?

Upvotes: 1

Views: 629

Answers (1)

saifi
saifi

Reputation: 1

Implement the code in below given url and you will be good to go.

BUT, do tell in reply by testing it that if it works for your chatgpt llm ? , because I am using google's flan-t5-large llm and I am getting some weird loop when I enter my text prompt.

https://python.langchain.com/docs/modules/agents/how_to/sharedmemory_for_tools

Upvotes: 0

Related Questions