Firestore 聊天记录

为了在聊天会话之间实现更长期的持久性，您可以将默认的内存中 chatHistory 替换为 firestore，该 chatHistory 支持聊天记录类，例如 BufferMemory。

设置

首先，在您的项目中安装 Firebase admin 包

npm

npm install firebase-admin

Yarn

yarn add firebase-admin

pnpm

pnpm add firebase-admin

提示

有关安装集成包的通用说明，请参阅此部分。

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

访问您的 Firebase 项目中的项目设置页面，然后选择服务帐户选项卡。

在服务帐户选项卡内，单击Firebase Admin SDK部分内的生成新的私钥按钮，以下载包含您的服务帐户凭据的 JSON 文件。

使用下载的 JSON 文件，将 projectId、privateKey 和 clientEmail 传递到 FirestoreChatMessageHistory 类的 config 对象，如下所示

import { FirestoreChatMessageHistory } from "@langchain/community/stores/message/firestore";
import admin from "firebase-admin";

const messageHistory = new FirestoreChatMessageHistory({
  collections: ["chats"],
  docs: ["user-id"],
  sessionId: "user-id",
  userId: "a@example.com",
  config: {
    projectId: "YOUR-PROJECT-ID",
    credential: admin.credential.cert({
      projectId: "YOUR-PROJECT-ID",
      privateKey:
        "-----BEGIN PRIVATE KEY-----\nCHANGE-ME\n-----END PRIVATE KEY-----\n",
      clientEmail: "CHANGE-ME@CHANGE-ME-TOO.iam.gserviceaccount.com",
    }),
  },
});

在这里，collections 字段应与数据库中 collections 的名称和顺序匹配。docs 也是如此，它应该与数据库中 docs 的名称和顺序匹配。

使用方法

import { BufferMemory } from "langchain/memory";
import { FirestoreChatMessageHistory } from "@langchain/community/stores/message/firestore";
import { ChatOpenAI } from "@langchain/openai";
import { ConversationChain } from "langchain/chains";
import admin from "firebase-admin";

const memory = new BufferMemory({
  chatHistory: new FirestoreChatMessageHistory({
    collections: ["langchain"],
    docs: ["lc-example"],
    sessionId: "lc-example-id",
    userId: "a@example.com",
    config: {
      projectId: "YOUR-PROJECT-ID",
      credential: admin.credential.cert({
        projectId: "YOUR-PROJECT-ID",
        privateKey:
          "-----BEGIN PRIVATE KEY-----\nnCHANGE-ME\n-----END PRIVATE KEY-----\n",
        clientEmail: "CHANGE-ME@CHANGE-ME-TOO.iam.gserviceaccount.com",
      }),
    },
  }),
});

const model = new ChatOpenAI();
const chain = new ConversationChain({ llm: model, memory });

const res1 = await chain.invoke({ input: "Hi! I'm Jim." });
console.log({ res1 });
/*
{ res1: { text: "Hello Jim! It's nice to meet you. My name is AI. How may 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 Jim." } }
*/

API 参考

• BufferMemory 来自 langchain/memory
• FirestoreChatMessageHistory 来自 @langchain/community/stores/message/firestore
• ChatOpenAI 来自 @langchain/openai
• ConversationChain 来自 langchain/chains

嵌套集合

FirestoreChatMessageHistory 类支持嵌套集合和动态集合/文档名称。

下面的示例展示了如何从具有以下结构的数据库添加和检索消息

/chats/{chat-id}/bots/{bot-id}/messages/{message-id}

import { BufferMemory } from "langchain/memory";
import { FirestoreChatMessageHistory } from "@langchain/community/stores/message/firestore";
import { ChatOpenAI } from "@langchain/openai";
import { ConversationChain } from "langchain/chains";
import admin from "firebase-admin";

const memory = new BufferMemory({
  chatHistory: new FirestoreChatMessageHistory({
    collections: ["chats", "bots"],
    docs: ["chat-id", "bot-id"],
    sessionId: "user-id",
    userId: "a@example.com",
    config: {
      projectId: "YOUR-PROJECT-ID",
      credential: admin.credential.cert({
        projectId: "YOUR-PROJECT-ID",
        privateKey:
          "-----BEGIN PRIVATE KEY-----\nnCHANGE-ME\n-----END PRIVATE KEY-----\n",
        clientEmail: "CHANGE-ME@CHANGE-ME-TOO.iam.gserviceaccount.com",
      }),
    },
  }),
});

const model = new ChatOpenAI();
const chain = new ConversationChain({ llm: model, memory });

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

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

/*
{ res2: { response: 'You just said that your name is Jim.' } }
*/

API 参考

• BufferMemory 来自 langchain/memory
• FirestoreChatMessageHistory 来自 @langchain/community/stores/message/firestore
• ChatOpenAI 来自 @langchain/openai
• ConversationChain 来自 langchain/chains

Firestore 规则

如果您的集合名称是“chathistory”，您可以按如下方式配置 Firestore 规则。

      match /chathistory/{sessionId} {
       allow read: if request.auth.uid == resource.data.createdBy;
       allow write: if request.auth.uid == request.resource.data.createdBy;
             }
             match /chathistory/{sessionId}/messages/{messageId} {
       allow read: if request.auth.uid == resource.data.createdBy;
       allow write: if request.auth.uid == request.resource.data.createdBy;
            }