哪家企业网站做的好,如何建立手机论坛,企业邮箱正确的写法,专业网站制作公司是如何处理一个优秀网站的分类目录#xff1a;《自然语言处理从入门到应用》总目录 Cassandra聊天消息记录
Cassandra是一种分布式数据库#xff0c;非常适合存储大量数据#xff0c;是存储聊天消息历史的良好选择#xff0c;因为它易于扩展#xff0c;能够处理大量写入操作。
# List of contact…分类目录《自然语言处理从入门到应用》总目录 Cassandra聊天消息记录
Cassandra是一种分布式数据库非常适合存储大量数据是存储聊天消息历史的良好选择因为它易于扩展能够处理大量写入操作。
# List of contact points to try connecting to Cassandra cluster.
contact_points [cassandra]from langchain.memory import CassandraChatMessageHistorymessage_history CassandraChatMessageHistory(contact_pointscontact_points, session_idtest-session
)message_history.add_user_message(hi!)message_history.add_ai_message(whats up?)
message_history.messages
[HumanMessage(contenthi!, additional_kwargs{}, exampleFalse),
AIMessage(contentwhats up?, additional_kwargs{}, exampleFalse)]DynamoDB聊天消息记录
首先确保我们已经正确配置了AWS CLI并再确保我们已经安装了boto3。接下来创建我们将存储消息 DynamoDB表
import boto3# Get the service resource.
dynamodb boto3.resource(dynamodb)# Create the DynamoDB table.
table dynamodb.create_table(TableNameSessionTable,KeySchema[{AttributeName: SessionId,KeyType: HASH}],AttributeDefinitions[{AttributeName: SessionId,AttributeType: S}],BillingModePAY_PER_REQUEST,
)# Wait until the table exists.
table.meta.client.get_waiter(table_exists).wait(TableNameSessionTable)# Print out some data about the table.
print(table.item_count)输出
0DynamoDBChatMessageHistory
from langchain.memory.chat_message_histories import DynamoDBChatMessageHistoryhistory DynamoDBChatMessageHistory(table_nameSessionTable, session_id0)
history.add_user_message(hi!)
history.add_ai_message(whats up?)
history.messages输出
[HumanMessage(contenthi!, additional_kwargs{}, exampleFalse),
AIMessage(contentwhats up?, additional_kwargs{}, exampleFalse)]使用自定义端点URL的DynamoDBChatMessageHistory
有时候在连接到AWS端点时指定URL非常有用比如在本地使用Localstack进行开发。对于这种情况我们可以通过构造函数中的endpoint_url参数来指定URL。
from langchain.memory.chat_message_histories import DynamoDBChatMessageHistoryhistory DynamoDBChatMessageHistory(table_nameSessionTable, session_id0, endpoint_urlhttp://localhost.localstack.cloud:4566)Agent with DynamoDB Memory
from langchain.agents import Tool
from langchain.memory import ConversationBufferMemory
from langchain.chat_models import ChatOpenAI
from langchain.agents import initialize_agent
from langchain.agents import AgentType
from langchain.utilities import PythonREPL
from getpass import getpassmessage_history DynamoDBChatMessageHistory(table_nameSessionTable, session_id1)
memory ConversationBufferMemory(memory_keychat_history, chat_memorymessage_history, return_messagesTrue)
python_repl PythonREPL()# You can create the tool to pass to an agent
tools [Tool(namepython_repl,descriptionA Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with print(...).,funcpython_repl.run
)]
llmChatOpenAI(temperature0)
agent_chain initialize_agent(tools, llm, agentAgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION, verboseTrue, memorymemory)
agent_chain.run(inputHello!)日志输出 Entering new AgentExecutor chain...
{action: Final Answer,action_input: Hello! How can I assist you today?
} Finished chain.输出
Hello! How can I assist you today?输入
agent_chain.run(inputWho owns Twitter?)日志输出 Entering new AgentExecutor chain...
{action: python_repl,action_input: import requests\nfrom bs4 import BeautifulSoup\n\nurl https://en.wikipedia.org/wiki/Twitter\nresponse requests.get(url)\nsoup BeautifulSoup(response.content, html.parser)\nowner soup.find(th, textOwner).find_next_sibling(td).text.strip()\nprint(owner)
}
Observation: X Corp. (2023–present)Twitter, Inc. (2006–2023)Thought:{action: Final Answer,action_input: X Corp. (2023–present)Twitter, Inc. (2006–2023)
} Finished chain.输出
X Corp. (2023–present)Twitter, Inc. (2006–2023)输入
agent_chain.run(inputMy name is Bob.)日志输出 Entering new AgentExecutor chain...
{action: Final Answer,action_input: Hello Bob! How can I assist you today?
} Finished chain.输出 Hello Bob! How can I assist you today?输入
agent_chain.run(inputWho am I?)日志输出 Entering new AgentExecutor chain...
{action: Final Answer,action_input: Your name is Bob.
} Finished chain.输出
Your name is Bob.Momento聊天消息记录
本节介绍如何使用Momento Cache来存储聊天消息记录我们会使用MomentoChatMessageHistory类。需要注意的是默认情况下如果不存在具有给定名称的缓存我们将创建一个新的缓存。我们需要获得一个Momento授权令牌才能使用这个类。这可以直接通过将其传递给momento.CacheClient实例化作为MomentoChatMessageHistory.from_client_params的命名参数auth_token或者可以将其设置为环境变量MOMENTO_AUTH_TOKEN。
from datetime import timedelta
from langchain.memory import MomentoChatMessageHistorysession_id foo
cache_name langchain
ttl timedelta(days1)
history MomentoChatMessageHistory.from_client_params(session_id, cache_name,ttl,
)history.add_user_message(hi!)history.add_ai_message(whats up?)
history.messages输出
[HumanMessage(contenthi!, additional_kwargs{}, exampleFalse),
AIMessage(contentwhats up?, additional_kwargs{}, exampleFalse)]MongoDB聊天消息记录
本节介绍如何使用MongoDB存储聊天消息记录。MongoDB是一个开放源代码的跨平台文档导向数据库程序。它被归类为NoSQL数据库程序使用类似JSON的文档并且支持可选的模式。MongoDB由MongoDB Inc.开发并在服务器端公共许可证SSPL下许可。
# Provide the connection string to connect to the MongoDB database
connection_string mongodb://mongo_user:password123mongo:27017
from langchain.memory import MongoDBChatMessageHistorymessage_history MongoDBChatMessageHistory(connection_stringconnection_string, session_idtest-session)message_history.add_user_message(hi!)message_history.add_ai_message(whats up?)
message_history.messages输出
[HumanMessage(contenthi!, additional_kwargs{}, exampleFalse),
AIMessage(contentwhats up?, additional_kwargs{}, exampleFalse)]Postgres聊天消息历史记录
本节介绍了如何使用 Postgres 来存储聊天消息历史记录。
from langchain.memory import PostgresChatMessageHistoryhistory PostgresChatMessageHistory(connection_stringpostgresql://postgres:mypasswordlocalhost/chat_history, session_idfoo)history.add_user_message(hi!)history.add_ai_message(whats up?)
history.messagesRedis聊天消息历史记录
本节介绍了如何使用Redis来存储聊天消息历史记录。
from langchain.memory import RedisChatMessageHistoryhistory RedisChatMessageHistory(foo)history.add_user_message(hi!)
history.add_ai_message(whats up?)
history.messages输出
[AIMessage(contentwhats up?, additional_kwargs{}),
HumanMessage(contenthi!, additional_kwargs{})]参考文献 [1] LangChain官方网站https://www.langchain.com/ [2] LangChain ️ 中文网跟着LangChain一起学LLM/GPT开发https://www.langchain.com.cn/ [3] LangChain中文网 - LangChain 是一个用于开发由语言模型驱动的应用程序的框架http://www.cnlangchain.com/
