Skip to main content

Cassandra 聊天记忆

为了在聊天会话中实现更长期的持久化，您可以将默认的内存中 chatHistory（为 BufferMemory 等聊天记忆类提供支持）替换为 Cassandra 集群。

准备工作​

首先，安装 Cassandra Node.js 驱动程序：

:::提示 请参阅安装集成包的一般说明部分。 :::

npm install cassandra-driver @langchain/openai @langchain/community @langchain/core

根据您的数据库提供商不同，连接数据库的具体方式也会有所不同。我们将创建一个 configConnection 文档，该文档将用于向量存储配置的一部分。

Apache Cassandra®​

const configConnection = {
  contactPoints: ['h1', 'h2'],
  localDataCenter: 'datacenter1',
  credentials: {
    username: <...> as string,
    password: <...> as string,
  },
};

Astra DB​

Astra DB 是一个云原生的 Cassandra 即服务（Cassandra-as-a-Service）平台。

  1. 创建一个 Astra DB 账户。
  2. 创建一个 启用向量功能的数据库。
  3. 为您的数据库创建一个 Token。
const configConnection = {
  serviceProviderArgs: {
    astra: {
      token: <...> as string,
      endpoint: <...> as string,
    },
  },
};

除了使用 endpoint: 属性，您也可以提供 datacenterID: 属性，以及可选的 regionName: 属性。

使用方法​

import { BufferMemory } from "langchain/memory";
import { CassandraChatMessageHistory } from "@langchain/community/stores/message/cassandra";
import { ChatOpenAI } from "@langchain/openai";
import { ConversationChain } from "langchain/chains";

// The example below uses Astra DB, but you can use any Cassandra connection
const configConnection = {
  serviceProviderArgs: {
    astra: {
      token: "<your Astra Token>" as string,
      endpoint: "<your Astra Endpoint>" as string,
    },
  },
};

const memory = new BufferMemory({
  chatHistory: new CassandraChatMessageHistory({
    ...configConnection,
    keyspace: "langchain",
    table: "message_history",
    sessionId: "<some unique session identifier>",
  }),
});

const model = new ChatOpenAI({
  model: "gpt-4o-mini",
});
const chain = new ConversationChain({ llm: model, memory });

const res1 = await chain.invoke({ input: "Hi! I'm Jonathan." });
console.log({ res1 });
/*
{
  res1: {
    text: "Hello Jonathan! How can I assist you today?"
  }
}
*/

const res2 = await chain.invoke({ input: "What did I just say my name was?" });
console.log({ res2 });

/*
{
  res1: {
    text: "You said your name was Jonathan."
  }
}
*/

API Reference:

Was this page helpful?


You can also leave detailed feedback on GitHub.