支持向量存储

VectorStoreRetrieverMemory将记忆存储在向量存储中，并在每次调用时查询前K个最"显著"的文档。

与大多数其他记忆类不同的是，它不明确跟踪交互的顺序。

在这种情况下，"文档"是先前对话片段。这对于提及AI在对话中早些时候被告知的相关信息可能是有用的。

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

初始化向量存储

根据您选择的存储方式，这一步可能会有所不同。请参考相关的向量存储文档以获取更多详细信息。

import faiss

from langchain.docstore import InMemoryDocstore
from langchain.vectorstores import FAISS

embedding_size = 1536 # OpenAIEmbeddings的维度
index = faiss.IndexFlatL2(embedding_size)
embedding_fn = OpenAIEmbeddings().embed_query
vectorstore = FAISS(embedding_fn, index, InMemoryDocstore({}), {})

创建VectorStoreRetrieverMemory

从任何向量存储检索器实例化内存对象。

# 在实际使用中，您可以将`k`设置得更高，但我们使用k=1来展示向量查找仍然返回语义相关的信息
retriever = vectorstore.as_retriever(search_kwargs=dict(k=1))
memory = VectorStoreRetrieverMemory(retriever=retriever)

# 当添加到代理程序时，内存对象可以保存来自对话或使用工具的相关信息
memory.save_context({"input": "我最喜欢的食物是比萨饼"}, {"output": "知道了"})
memory.save_context({"input": "我最喜欢的运动是足球"}, {"output": "..."})
memory.save_context({"input": "我不喜欢凯尔特人队"}, {"output": "好的"})

# 注意，返回的第一个结果是与1099相关的记忆，与其他文件相比，语言模型认为它与1099更有语义相关性，尽管它们都包含数字。
print(memory.load_memory_variables({"prompt": "我应该看什么运动？"})["history"])

    input: 我最喜欢的运动是足球
    output: ...

在链式结构中使用

让我们通过一个示例进行演示，再次设置verbose=True以便查看提示信息。

llm = OpenAI(temperature=0) # 可以是任何有效的LLM
_DEFAULT_TEMPLATE = """以下是人类和AI之间友好的对话。AI健谈并从其上下文中提供了许多具体细节。如果AI不知道问题的答案，它会真诚地说自己不知道。

先前对话的相关部分：
{history}

（如果不相关，您无需使用这些信息）

当前对话：
人类：{input}
AI:"""
PROMPT = PromptTemplate(
    input_variables=["history", "input"], template=_DEFAULT_TEMPLATE
)
conversation_with_summary = ConversationChain(
    llm=llm, 
    prompt=PROMPT,
    # 出于测试目的，我们将max_token_limit设置得非常低。
    memory=memory,
    verbose=True
)
conversation_with_summary.predict(input="Hi, 我叫Perry，有什么新鲜事？")

    
    
    > 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: that's 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.





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

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

    
    
    > 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.





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

# Even though the language model is stateless, since relevant 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")

    
    
    > 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: that's 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.





    ' You said your favorite food is pizza.'

# 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?")

    
    
    > 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.





    ' Your name is Perry.'