Azure Cosmos DB Mongo vCore Chat Message History

AzureCosmosDBMongoChatMessageHistory 使用 Azure Cosmos DB Mongo vCore 来存储聊天消息历史记录。为了在聊天会话中实现更长期的持久性，您可以替换默认的内存中 chatHistory，它支持聊天记忆类，如 BufferMemory。如果您没有 Azure 帐户，您可以创建一个免费帐户以开始使用。

安装设置

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，了解有关安装集成包的通用说明。

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 mongo vCore 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。

一旦您的实例运行起来，请确保您拥有连接字符串。

用法

import { ChatOpenAI } from "@langchain/openai";
import {
  AzureCosmosDBMongoChatMessageHistory,
  AzureCosmosDBMongoChatHistoryDBConfig,
} 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 dbcfg: AzureCosmosDBMongoChatHistoryDBConfig = {
  connectionString: process.env.AZURE_COSMOSDB_MONGODB_CONNECTION_STRING,
  databaseName: "langchain",
  collectionName: "chathistory",
};

const chainWithHistory = new RunnableWithMessageHistory({
  runnable: chain,
  inputMessagesKey: "input",
  historyMessagesKey: "chat_history",
  getMessageHistory: async (sessionId) => {
    const chatHistory = new AzureCosmosDBMongoChatMessageHistory(
      dbcfg,
      sessionId,
      "user-id"
    );
    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 AzureCosmosDBMongoChatMessageHistory;

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

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

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

API 参考

• ChatOpenAI from @langchain/openai
• AzureCosmosDBMongoChatMessageHistory from @langchain/azure-cosmosdb
• AzureCosmosDBMongoChatHistoryDBConfig from @langchain/azure-cosmosdb
• RunnableWithMessageHistory from @langchain/core/runnables
• StringOutputParser from @langchain/core/output_parsers
• ChatPromptTemplate from @langchain/core/prompts
• MessagesPlaceholder from @langchain/core/prompts