LangChain学习之四种Memory模式使用

admin管理员组

文章数量:1130349

1. 学习背景

在LangChain for LLM应用程序开发中课程中，学习了LangChain框架扩展应用程序开发中语言模型的用例和功能的基本技能，遂做整理为后面的应用做准备。视频地址：基于LangChain的大语言模型应用开发+构建和评估。

2. 四种memory模式

本实验基于jupyternotebook进行。

2.1 ConversationBufferMemory

import warnings
warnings.filterwarnings('ignore')

from langchain.chat_models import ChatOpenAI
from langchain.chains import ConversationChain
from langchain.memory import ConversationBufferMemory


llm = ChatOpenAI(
    api_key = "XXXX",
    base_url = "XXXX",
    temperature=0.0
)

memory = ConversationBufferMemory()
conversation = ConversationChain(
    llm=llm, 
    memory = memory,
    verbose=True #设置为True可以看到模型的具体思考过程
)

conversation.predict(input="Hi, my name is Andrew")

输出如下：

> 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, my name is Andrew
AI:

> Finished chain.
"Hello Andrew! It's nice to meet you. My name is AI and I'm here to assist you with any questions or tasks you have. How can I help you today?"

继续测试

conversation.predict(input="What is 1+1?")

输出如下：

> 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, my name is Andrew
AI: Hello Andrew! It's nice to meet you. My name is AI and I'm here to assist you with any questions or tasks you have. How can I help you today?
Human: What is 1+1?
AI:

> Finished chain.
'1+1 equals 2. This is a basic mathematical operation that can be solved by adding the two numbers together. Is there anything else I can assist you with?'

再次输入之前的问题

conversation.predict(input="What is my name?")

输出如下：

> 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 ans

1. 学习背景

在LangChain for LLM应用程序开发中课程中，学习了LangChain框架扩展应用程序开发中语言模型的用例和功能的基本技能，遂做整理为后面的应用做准备。视频地址：基于LangChain的大语言模型应用开发+构建和评估。

2. 四种memory模式

本实验基于jupyternotebook进行。

2.1 ConversationBufferMemory

import warnings
warnings.filterwarnings('ignore')

from langchain.chat_models import ChatOpenAI
from langchain.chains import ConversationChain
from langchain.memory import ConversationBufferMemory


llm = ChatOpenAI(
    api_key = "XXXX",
    base_url = "XXXX",
    temperature=0.0
)

memory = ConversationBufferMemory()
conversation = ConversationChain(
    llm=llm, 
    memory = memory,
    verbose=True #设置为True可以看到模型的具体思考过程
)

conversation.predict(input="Hi, my name is Andrew")

输出如下：

> 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, my name is Andrew
AI:

> Finished chain.
"Hello Andrew! It's nice to meet you. My name is AI and I'm here to assist you with any questions or tasks you have. How can I help you today?"

继续测试

conversation.predict(input="What is 1+1?")

输出如下：

> 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, my name is Andrew
AI: Hello Andrew! It's nice to meet you. My name is AI and I'm here to assist you with any questions or tasks you have. How can I help you today?
Human: What is 1+1?
AI:

> Finished chain.
'1+1 equals 2. This is a basic mathematical operation that can be solved by adding the two numbers together. Is there anything else I can assist you with?'

再次输入之前的问题

conversation.predict(input="What is my name?")

输出如下：

> 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 ans

本文标签： 四种模式Langchainmemory