分類目錄：《自然語言處理從入門到應用》總目錄

---

對話令牌緩沖存儲器ConversationTokenBufferMemory

ConversationTokenBufferMemory在內存中保留了最近的一些對話交互，并使用標記長度來確定何時刷新交互，而不是交互數量。

from langchain.memory import ConversationTokenBufferMemory
from langchain.llms import OpenAI
llm = OpenAI()
memory = ConversationTokenBufferMemory(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({})

輸出：

{‘history’: ‘Human: not much you\nAI: not much’}

我們還可以將歷史記錄作為消息列表獲取，如果我們正在使用聊天模型，將非常有用：

memory = ConversationTokenBufferMemory(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"})

在鏈式模型中的應用

讓我們通過一個例子來演示如何在鏈式模型中使用它，同樣設置verbose=True，以便我們可以看到提示信息。

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=ConversationTokenBufferMemory(llm=OpenAI(), max_token_limit=60),verbose=True
)
conversation_with_summary.predict(input="Hi, what's up?")

日志輸出：

> 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.

輸出：

" Hi there! I'm doing great, just enjoying the day. How about you?"

輸入：

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

日志輸出：

> 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, just enjoying the day. How about you?
Human: Just working on writing some documentation!
AI:> Finished chain.

輸出：

    ' Sounds like a productive day! What kind of documentation are you writing?'

輸入：

conversation_with_summary.predict(input="For LangChain! Have you heard of it?")

日志輸出：

> 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, just enjoying the day. How about you?
Human: Just working on writing some documentation!
AI:  Sounds like a productive day! What kind of documentation are you writing?
Human: For LangChain! Have you heard of it?
AI:> Finished chain.

輸出：

    " Yes, I have heard of LangChain! It is a decentralized language-learning platform that connects native speakers and learners in real time. Is that the documentation you're writing about?"

輸入：

# 我們可以看到這里緩沖區被更新了
conversation_with_summary.predict(input="Haha nope, although a lot of people confuse it for that")

日志輸出：

> 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: For LangChain! Have you heard of it?
AI:  Yes, I have heard of LangChain! It is a decentralized language-learning platform that connects native speakers and learners in real time. Is that the documentation you're writing about?
Human: Haha nope, although a lot of people confuse it for that
AI:> Finished chain.

輸出：

" Oh, I see. Is there another language learning platform you're referring to?"

基于向量存儲的記憶VectorStoreRetrieverMemory

VectorStoreRetrieverMemory將內存存儲在VectorDB中，并在每次調用時查詢最重要的前$K$個文檔。與大多數其他Memory類不同，它不明確跟蹤交互的順序。在這種情況下，“文檔”是先前的對話片段。這對于提及AI在對話中早些時候得知的相關信息非常有用。

from datetime import datetime
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.llms import OpenAI
from langchain.memory import VectorStoreRetrieverMemory
from langchain.chains import ConversationChain
from langchain.prompts import PromptTemplate

初始化VectorStore

根據我們選擇的存儲方式，此步驟可能會有所不同，我們可以查閱相關的VectorStore文檔以獲取更多詳細信息。

import faissfrom langchain.docstore import InMemoryDocstore
from langchain.vectorstores import FAISSembedding_size = 1536 # Dimensions of the OpenAIEmbeddings
index = faiss.IndexFlatL2(embedding_size)
embedding_fn = OpenAIEmbeddings().embed_query
vectorstore = FAISS(embedding_fn, index, InMemoryDocstore({}), {})

創建VectorStoreRetrieverMemory

記憶對象是從VectorStoreRetriever實例化的。

# In actual usage, you would set `k` to be a higher value, but we use k=1 to show that the vector lookup still returns the semantically relevant information
retriever = vectorstore.as_retriever(search_kwargs=dict(k=1))
memory = VectorStoreRetrieverMemory(retriever=retriever)# When added to an agent, the memory object can save pertinent information from conversations or used tools
memory.save_context({"input": "My favorite food is pizza"}, {"output": "thats good to know"})
memory.save_context({"input": "My favorite sport is soccer"}, {"output": "..."})
memory.save_context({"input": "I don't the Celtics"}, {"output": "ok"}) # 
# Notice the first result returned is the memory pertaining to tax help, which the language model deems more semantically relevant
# to a 1099 than the other documents, despite them both containing numbers.
print(memory.load_memory_variables({"prompt": "what sport should i watch?"})["history"])

輸出：

input: My favorite sport is soccer
output: ...

在對話鏈中使用

讓我們通過一個示例來演示，在此示例中我們繼續設置verbose=True以便查看提示。

llm = OpenAI(temperature=0) # Can be any valid LLM
_DEFAULT_TEMPLATE = """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.Relevant pieces of previous conversation:
{history}(You do not need to use these pieces of information if not relevant)Current conversation:
Human: {input}
AI:"""
PROMPT = PromptTemplate(input_variables=["history", "input"], template=_DEFAULT_TEMPLATE
)
conversation_with_summary = ConversationChain(llm=llm, prompt=PROMPT,# We set a very low max_token_limit for the purposes of testing.memory=memory,verbose=True
)
conversation_with_summary.predict(input="Hi, my name is Perry, what's up?")

日志輸出：

> 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.Relevant pieces of previous conversation:
input: My favorite food is pizza
output: thats good to know(You do not need to use these pieces of information if not relevant)Current conversation:
Human: Hi, my name is Perry, what's up?
AI:> Finished chain.

輸出：

" Hi Perry, I'm doing well. How about you?"

輸入：

# Here, the basketball related content is surfaced
conversation_with_summary.predict(input="what's my favorite sport?")

日志輸出：

> 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.Relevant pieces of previous conversation:
input: My favorite sport is soccer
output: ...(You do not need to use these pieces of information if not relevant)Current conversation:
Human: what's my favorite sport?
AI:> Finished chain.

輸出：

  ' You told me earlier that your favorite sport is soccer.'

輸入：

# Even though the language model is stateless, since relavent memory is fetched, it can "reason" about the time.
# Timestamping memories and data is useful in general to let the agent determine temporal relevance
conversation_with_summary.predict(input="Whats my favorite food")

日志輸出：

> 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.Relevant pieces of previous conversation:
input: My favorite food is pizza
output: thats good to know(You do not need to use these pieces of information if not relevant)Current conversation:
Human: Whats my favorite food
AI:> Finished chain.

輸出：

  ' You said your favorite food is pizza.'

輸入：

# The memories from the conversation are automatically stored,
# since this query best matches the introduction chat above,
# the agent is able to 'remember' the user's name.
conversation_with_summary.predict(input="What's my name?")

日志輸出：

> 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.Relevant pieces of previous conversation:
input: Hi, my name is Perry, what's up?
response:  Hi Perry, I'm doing well. How about you?(You do not need to use these pieces of information if not relevant)Current conversation:
Human: What's my name?
AI:> Finished chain.

輸出：

' Your name is Perry.'

參考文獻：
[1] LangChain官方網站：https://www.langchain.com/
[2] LangChain 🦜?🔗 中文網，跟著LangChain一起學LLM/GPT開發：https://www.langchain.com.cn/
[3] LangChain中文網 - LangChain 是一個用于開發由語言模型驅動的應用程序的框架：http://www.cnlangchain.com/