ConversationSummaryMemory

Agora vamos dar uma olhada no uso de um tipo de memória um pouco mais complexo — ConversationSummaryMemory. Esse tipo de memória cria um resumo da conversa até o momento. Isso pode ser útil para condensar as informações da conversa ao longo do tempo.

Fonte: https://python.langchain.com/en/latest/modules/memory/types/summary.html

Vamos primeiro explorar a funcionalidade básica desse tipo de memória.

O código a seguir ilustra o uso de um tipo de memória chamado ConversationSummaryMemory em uma cadeia de conversa (ou ConversationChain) usando uma biblioteca fictícia chamada langchain.

from langchain.memory import ConversationSummaryMemory, ChatMessageHistory
from langchain.llms import OpenAI

memory = ConversationSummaryMemory(llm=OpenAI(temperature=0))
memory.save_context({"input": "hi"}, {"ouput": "whats up"})

memory.load_memory_variables({})

{'history': '\nThe human greets the AI, to which the AI responds.'

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 = ConversationSummaryMemory(llm=OpenAI(temperature=0), return_messages=True)
memory.save_context({"input": "hi"}, {"ouput": "whats up"})

memory.load_memory_variables({})

{'history': [SystemMessage(content='\nThe human greets the AI, to which the AI responds.', additional_kwargs={})]}

Também podemos utilizar o predict_new_summarymétodo diretamente.

messages = memory.chat_memory.messages
previous_summary = ""
memory.predict_new_summary(messages, previous_summary)

'\nThe human greets the AI, to which the AI responds.'

Inicializando com mensagens

Se você tiver mensagens fora dessa classe, poderá inicializar facilmente a classe com ChatMessageHistory. Durante o carregamento, um resumo será calculado.

history = ChatMessageHistory()
history.add_user_message("hi")
history.add_ai_message("hi there!")

memory = ConversationSummaryMemory.from_messages(llm=OpenAI(temperature=0), chat_memory=history, return_messages=True)

memory.buffer

'\nThe human greets the AI, to which the AI responds with a friendly greeting.'

Usando em uma cadeia

Vamos percorrer um exemplo de como usar isso em uma cadeia, configurando novamente verbose=Truepara que possamos ver o prompt.

from langchain.llms import OpenAI
from langchain.chains import ConversationChain
llm = OpenAI(temperature=0)
conversation_with_summary = ConversationChain(
    llm=llm, 
    memory=ConversationSummaryMemory(llm=OpenAI()),
    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="Tell me more about it!")

> 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:
The human greeted the AI and asked how it was doing. The AI replied that it was doing great and was currently helping a customer with a technical issue.
Human: Tell me more about it!
AI:
> Finished chain.

" Sure! The customer is having trouble with their computer not connecting to the internet. I'm helping them troubleshoot the issue and figure out what the problem is. So far, we've tried resetting the router and checking the network settings, but the issue still persists. We're currently looking into other possible solutions."

conversation_with_summary.predict(input="Very cool -- what is the scope of the project?")

> 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:
The human greeted the AI and asked how it was doing. The AI replied that it was doing great and was currently helping a customer with a technical issue where their computer was not connecting to the internet. The AI was troubleshooting the issue and had already tried resetting the router and checking the network settings, but the issue still persisted and they were looking into other possible solutions.
Human: Very cool -- what is the scope of the project?
AI:
> Finished chain.

" The scope of the project is to troubleshoot the customer's computer issue and find a solution that will allow them to connect to the internet. We are currently exploring different possibilities and have already tried resetting the router and checking the network settings, but the issue still persists."