Langchain 的 Conversation buffer memory

This notebook shows how to use it ConversationBufferMemory. This memory allows messages to be stored and then extracted into variables.

We can first extract it as a string.

sample code,

from langchain.memory import ConversationBufferMemory

memory = ConversationBufferMemory()
memory.save_context({"input": "hi"}, {"output": "whats up"})

memory = ConversationBufferMemory()
memory.save_context({"input": "hi"}, {"output": "whats up"})

memory.load_memory_variables({})

output result,

    {'history': 'Human: hi\nAI: whats up'}

We can also get the history as a list of messages (very useful if you use it with the chat model).

sample code,

memory = ConversationBufferMemory(return_messages=True)
memory.save_context({"input": "hi"}, {"output": "whats up"})

memory.load_memory_variables({})

output result,

    {'history': [HumanMessage(content='hi', additional_kwargs={}),
      AIMessage(content='whats up', additional_kwargs={})]}

Using in a chain

Finally, let's look at using it in a chain (set verbose=True so we can see the prompt).

sample code,

from langchain.llms import OpenAI
from langchain.chains import ConversationChain


llm = OpenAI(temperature=0)
conversation = ConversationChain(
    llm=llm, 
    verbose=True, 
    memory=ConversationBufferMemory()
)

conversation.predict(input="Hi there!")

output result,

    
    
    > Entering new ConversationChain chain...
    Prompt after formatting:
    The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
    
    Current conversation:
    
    Human: Hi there!
    AI:
    
    > Finished chain.





    " Hi there! It's nice to meet you. How can I help you today?"

sample code,

conversation.predict(input="I'm doing well! Just having a conversation with an AI.")

output result,

    
    
    > Entering new ConversationChain chain...
    Prompt after formatting:
    The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
    
    Current conversation:
    Human: Hi there!
    AI:  Hi there! It's nice to meet you. How can I help you today?
    Human: I'm doing well! Just having a conversation with an AI.
    AI:
    
    > Finished chain.





    " That's great! It's always nice to have a conversation with someone new. What would you like to talk about?"

sample code,

conversation.predict(input="Tell me about yourself.")

output result,

    
    
    > Entering new ConversationChain chain...
    Prompt after formatting:
    The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
    
    Current conversation:
    Human: Hi there!
    AI:  Hi there! It's nice to meet you. How can I help you today?
    Human: I'm doing well! Just having a conversation with an AI.
    AI:  That's great! It's always nice to have a conversation with someone new. What would you like to talk about?
    Human: Tell me about yourself.
    AI:
    
    > Finished chain.





    " Sure! I'm an AI created to help people with their everyday tasks. I'm programmed to understand natural language and provide helpful information. I'm also constantly learning and updating my knowledge base so I can provide more accurate and helpful answers."

end!