ConversationBufferWindowMemory

ConversationBufferWindowMemorymantém uma lista das interações da conversa ao longo do tempo. Ele usa apenas as últimas K interações. Isso pode ser útil para manter uma janela deslizante das interações mais recentes, para que o buffer não fique muito grande

Vamos primeiro explorar a funcionalidade básica desse tipo de memória.

from langchain.memory import ConversationBufferWindowMemory

memory = ConversationBufferWindowMemory( k=1)
memory.save_context({"input": "hi"}, {"ouput": "whats up"})
memory.save_context({"input": "not much you"}, {"ouput": "not much"})

memory.load_memory_variables({})

{'history': 'Human: not much you\nAI: not much'}

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 = ConversationBufferWindowMemory( k=1, return_messages=True)
memory.save_context({"input": "hi"}, {"ouput": "whats up"})
memory.save_context({"input": "not much you"}, {"ouput": "not much"})

memory.load_memory_variables({})

{'history': [HumanMessage(content='not much you', additional_kwargs={}),
  AIMessage(content='not much', additional_kwargs={})]}

Usando em uma chain

Vamos percorrer um exemplo, configurando novamente verbose=Truepara que possamos ver o prompt.

from langchain.llms import OpenAI
from langchain.chains import ConversationChain
conversation_with_summary = ConversationChain(
    llm=OpenAI(temperature=0), 
    # We set a low k=2, to only keep the last 2 interactions in memory
    memory=ConversationBufferWindowMemory(k=2), 
    verbose=True
)
conversation_with_summary.predict(input="Hi, what's up?")

> 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, what's up?
AI:
> Finished chain.

" Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?"

conversation_with_summary.predict(input="What's their issues?")

> 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, what's up?
AI:  Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?
Human: What's their issues?
AI:
> Finished chain.

" The customer is having trouble connecting to their Wi-Fi network. I'm helping them troubleshoot the issue and get them connected."

conversation_with_summary.predict(input="Is it going well?")

> 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, what's up?
AI:  Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?
Human: What's their issues?
AI:  The customer is having trouble connecting to their Wi-Fi network. I'm helping them troubleshoot the issue and get them connected.
Human: Is it going well?
AI:
> Finished chain.

" Yes, it's going well so far. We've already identified the problem and are now working on a solution."

# Notice here that the first interaction does not appear.
conversation_with_summary.predict(input="What's the solution?")

> 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: What's their issues?
AI:  The customer is having trouble connecting to their Wi-Fi network. I'm helping them troubleshoot the issue and get them connected.
Human: Is it going well?
AI:  Yes, it's going well so far. We've already identified the problem and are now working on a solution.
Human: What's the solution?
AI:
> Finished chain.

" The solution is to reset the router and reconfigure the settings. We're currently in the process of doing that."