记忆系统概述

// 使用指令的节点
const callModel = async (state: State, store: BaseStore) => {
    const namespace = ["agent_instructions"];
    const instructions = await store.get(namespace, "agent_a");
    // 应用程序逻辑
    const prompt = promptTemplate.format({
        instructions: instructions[0].value.instructions
    });
    // ...
};

// 更新指令的节点
const updateInstructions = async (state: State, store: BaseStore) => {
    const namespace = ["instructions"];
    const currentInstructions = await store.search(namespace);
    // 记忆逻辑
    const prompt = promptTemplate.format({
        instructions: currentInstructions[0].value.instructions,
        conversation: state.messages
    });
    const output = await llm.invoke(prompt);
    const newInstructions = output.new_instructions;
    await store.put(["agent_instructions"], "agent_a", {
        instructions: newInstructions
    });
    // ...
};

import { InMemoryStore } from "@langchain/langgraph";

const embed = (texts: string[]): number[][] => {
    // 替换为实际的嵌入函数或 LangChain 嵌入对象
    return texts.map(() => [1.0, 2.0]);
};

// InMemoryStore 将数据保存到内存字典中。生产环境中请使用数据库支持的存储。
const store = new InMemoryStore({ index: { embed, dims: 2 } });
const userId = "my-user";
const applicationContext = "chitchat";
const namespace = [userId, applicationContext];

await store.put(
    namespace,
    "a-memory",
    {
        rules: [
            "用户喜欢简短、直接的语言",
            "用户只使用英语和 TypeScript",
        ],
        "my-key": "my-value",
    }
);

// 通过 ID 获取 "记忆"
const item = await store.get(namespace, "a-memory");

// 在此命名空间内搜索 "记忆"，基于内容等价性进行过滤，按向量相似度排序
const items = await store.search(
    namespace,
    {
        filter: { "my-key": "my-value" },
        query: "language preferences"
    }
);