ConversationSummaryBufferMemory

O ConversationSummaryBufferMemory é um componente de um sistema que mantém um registro das interações recentes em memória. Em vez de simplesmente descartar interações antigas, ele as compila em um resumo e usa ambas, as interações originais e o resumo. Diferente de outras implementações, ele usa a quantidade de tokens, ao invés do número de interações, para determinar quando descartar interações.

Ou seja, o ConversationSummaryBufferMemorycombina duas ideias de tipos de memória, que são: ConversationSummaryMemory e ConversationKGMemory. Ele mantém um buffer de interações recentes na memória, mas em vez de apenas liberar completamente as interações antigas, ele as compila em um resumo e usa ambos. Porém, ao contrário da implementação ConversationKGMemory, ele usa o comprimento do token em vez do número de interações para determinar quando liberar as interações.

Vamos primeiro ver como usar:

from langchain.memory import ConversationSummaryBufferMemory
from langchain.llms import OpenAI
llm = OpenAI()

memory = ConversationSummaryBufferMemory(llm=llm, max_token_limit=10)
memory.save_context({"input": "hi"}, {"output": "whats up"})
memory.save_context({"input": "not much you"}, {"output": "not much"})

memory.load_memory_variables({})

{'history': 'System: \nThe human says "hi", and the AI responds with "whats up".\nHuman: 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 = ConversationSummaryBufferMemory(llm=llm, max_token_limit=10, return_messages=True)
memory.save_context({"input": "hi"}, {"output": "whats up"})
memory.save_context({"input": "not much you"}, {"output": "not much"})

Também podemos utilizar o predict_new_summarymétodo diretamente.

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

'\nThe human and AI state that they are not doing much.'

Usando em uma chain

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

from langchain.chains import ConversationChain
conversation_with_summary = ConversationChain(
    llm=llm, 
    # We set a very low max_token_limit for the purposes of testing.
    memory=ConversationSummaryBufferMemory(llm=OpenAI(), max_token_limit=40),
    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 learning about the latest advances in artificial intelligence. What about you?"

conversation_with_summary.predict(input="Just working on writing some documentation!")

> 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 spending some time learning about the latest developments in AI technology. How about you?
Human: Just working on writing some documentation!
AI:

> Finished chain.

' That sounds like a great use of your time. Do you have experience with writing documentation?'

# We can see here that there is a summary of the conversation and then some previous interactions
conversation_with_summary.predict(input="For LangChain! Have you heard of 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:
System: 
The human asked the AI what it was up to and the AI responded that it was learning about the latest developments in AI technology.
Human: Just working on writing some documentation!
AI:  That sounds like a great use of your time. Do you have experience with writing documentation?
Human: For LangChain! Have you heard of it?
AI:

> Finished chain.

" No, I haven't heard of LangChain. Can you tell me more about it?"

# We can see here that the summary and the buffer are updated
conversation_with_summary.predict(input="Haha nope, although a lot of people confuse it for that")

> 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:
System: 
The human asked the AI what it was up to and the AI responded that it was learning about the latest developments in AI technology. The human then mentioned they were writing documentation, to which the AI responded that it sounded like a great use of their time and asked if they had experience with writing documentation.
Human: For LangChain! Have you heard of it?
AI:  No, I haven't heard of LangChain. Can you tell me more about it?
Human: Haha nope, although a lot of people confuse it for that
AI:

> Finished chain.

' Oh, okay. What is LangChain?'