Azure Cosmos DB NoSQL 聊天消息历史

AzureCosmosDBNoSQLChatMessageHistory 使用 Cosmos DB 存储聊天消息历史记录。对于跨聊天会话的长期持久性，您可以替换默认的内存中 chatHistory，后者支持聊天内存类，例如 BufferMemory。如果您没有 Azure 帐户，可以创建一个免费帐户以开始使用。

设置

您首先需要安装 @langchain/azure-cosmosdb 包

npm

npm install @langchain/azure-cosmosdb @langchain/core

Yarn

yarn add @langchain/azure-cosmosdb @langchain/core

pnpm

pnpm add @langchain/azure-cosmosdb @langchain/core

提示

请参阅此部分，了解有关安装集成软件包的常规说明。

npm

npm install @langchain/openai @langchain/community @langchain/core

Yarn

yarn add @langchain/openai @langchain/community @langchain/core

pnpm

pnpm add @langchain/openai @langchain/community @langchain/core

您还需要运行 Azure Cosmos DB for NoSQL 实例。您可以按照本指南在 Azure 门户上部署免费版本，无需任何费用。

实例运行后，请确保您拥有连接字符串。如果您使用托管标识，则需要拥有终结点。您可以在 Azure 门户的实例的“设置/密钥”部分中找到它们。

信息

当使用 Azure 托管标识和基于角色的访问控制时，您必须确保已预先创建数据库和容器。RBAC 不提供创建数据库和容器的权限。您可以在 Azure Cosmos DB 文档中获取有关权限模型的更多信息。

用法

import { ChatOpenAI } from "@langchain/openai";
import { AzureCosmsosDBNoSQLChatMessageHistory } from "@langchain/azure-cosmosdb";
import { RunnableWithMessageHistory } from "@langchain/core/runnables";
import { StringOutputParser } from "@langchain/core/output_parsers";
import {
  ChatPromptTemplate,
  MessagesPlaceholder,
} from "@langchain/core/prompts";

const model = new ChatOpenAI({
  model: "gpt-3.5-turbo",
  temperature: 0,
});

const prompt = ChatPromptTemplate.fromMessages([
  [
    "system",
    "You are a helpful assistant. Answer all questions to the best of your ability.",
  ],
  new MessagesPlaceholder("chat_history"),
  ["human", "{input}"],
]);

const chain = prompt.pipe(model).pipe(new StringOutputParser());

const chainWithHistory = new RunnableWithMessageHistory({
  runnable: chain,
  inputMessagesKey: "input",
  historyMessagesKey: "chat_history",
  getMessageHistory: async (sessionId) => {
    const chatHistory = new AzureCosmsosDBNoSQLChatMessageHistory({
      sessionId,
      userId: "user-id",
      databaseName: "DATABASE_NAME",
      containerName: "CONTAINER_NAME",
    });
    return chatHistory;
  },
});

const res1 = await chainWithHistory.invoke(
  { input: "Hi! I'm Jim." },
  { configurable: { sessionId: "langchain-test-session" } }
);
console.log({ res1 });
/*
 { res1: 'Hi Jim! How can I assist you today?' }
 */

const res2 = await chainWithHistory.invoke(
  { input: "What did I just say my name was?" },
  { configurable: { sessionId: "langchain-test-session" } }
);
console.log({ res2 });
/*
 { res2: { response: 'You said your name was Jim.' } 
 */

// Give this session a title
const chatHistory = (await chainWithHistory.getMessageHistory(
  "langchain-test-session"
)) as AzureCosmsosDBNoSQLChatMessageHistory;

await chatHistory.setContext({ title: "Introducing Jim" });

// List all session for the user
const sessions = await chatHistory.getAllSessions();

console.log(sessions);
/*
 [
  { sessionId: 'langchain-test-session', context: { title: "Introducing Jim"  } }
 ]
 */

API 参考

• ChatOpenAI 来自 @langchain/openai
• AzureCosmsosDBNoSQLChatMessageHistory 来自 @langchain/azure-cosmosdb
• RunnableWithMessageHistory 来自 @langchain/core/runnables
• StringOutputParser 来自 @langchain/core/output_parsers
• ChatPromptTemplate 来自 @langchain/core/prompts
• MessagesPlaceholder 来自 @langchain/core/prompts