如何给 LLM Chain（大语言模型链）添加 Memeory（记忆）

本章介绍了如何将Memory类与LLMChain一起使用。在本指南的示例中，我们将添加 ConversationBufferMemory 类，当然也可以是任何其他 Memory（记忆）类。

from langchain.memory import ConversationBufferMemory
from langchain import OpenAI, LLMChain, PromptTemplate

最重要的一步是正确设置提示。在下面的提示中，我们有两个输入键：一个是实际输入的键，另一个是来自Memory类的输入的键。重要的是，我们确保PromptTemplate 中的键和ConversationBufferMemory 中的键匹配（chat_history）。

template = """You are a chatbot having a conversation with a human.

{chat_history}
Human: {human_input}
Chatbot:"""

prompt = PromptTemplate(
    input_variables=["chat_history", "human_input"], 
    template=template
)
memory = ConversationBufferMemory(memory_key="chat_history")

llm_chain = LLMChain(
    llm=OpenAI(), 
    prompt=prompt, 
    verbose=True, 
    memory=memory,
)

llm_chain.predict(human_input="Hi there my friend")

> Entering new LLMChain chain...
Prompt after formatting:
You are a chatbot having a conversation with a human.


Human: Hi there my friend
Chatbot:

> Finished LLMChain chain.

' Hi there, how are you doing today?'

llm_chain.predict(human_input="Not too bad - how are you?")

> Entering new LLMChain chain...
Prompt after formatting:
You are a chatbot having a conversation with a human.


Human: Hi there my friend
AI:  Hi there, how are you doing today?
Human: Not to bad - how are you?
Chatbot:

> Finished LLMChain chain.

" I'm doing great, thank you for asking!"