ConversationBufferMemory

Ricardo Reis
2 min readMay 23, 2023

Este notebook mostra como usar arquivos ConversationBufferMemory. Esta memória permite o armazenamento de mensagens e depois extrai as mensagens em uma variável.

Podemos primeiro extraí-lo como uma string.

from langchain.memory import ConversationBufferMemory
memory = ConversationBufferMemory()
memory.save_context({"input": "hi"}, {"ouput": "whats up"})
memory.load_memory_variables({})
{'history': 'Human: hi\nAI: whats up'}

Também podemos obter o histórico como uma lista de mensagens (isso é útil se você estiver usando isso com um modelo de bate-papo).

memory = ConversationBufferMemory(return_messages=True)
memory.save_context({"input": "hi"}, {"ouput": "whats up"})
memory.load_memory_variables({})
{'history': [HumanMessage(content='hi', additional_kwargs={}),
AIMessage(content='whats up', additional_kwargs={})]}

Usando em uma chain

Por fim, vamos dar uma olhada em como usar isso em uma cadeia (configuração verbose=Truepara que possamos ver o prompt).

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!")
> 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?"
conversation.predict(input="I'm doing well! Just having a conversation with an AI.")
> 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?"
conversation.predict(input="Tell me about yourself.")
> 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."

E é isso para começar! Existem muitos tipos diferentes de memória, confira nossos exemplos para vê-los todos

--

--