Zep 开源

Zep 是一种用于 AI 助手应用程序的长期记忆服务。通过 Zep，您可以让 AI 助手回忆过去的对话，无论它们有多遥远，同时还能减少幻觉、延迟和成本。

对 Zep Cloud 感兴趣？请参阅Zep Cloud 安装指南

注意：ZepVectorStore 适用于 Documents，旨在用作 Retriever。它提供了与 Zep 的 ZepMemory 类不同的功能，后者旨在用于持久化、丰富和搜索用户的聊天历史记录。

Zep 的 VectorStore 有何优势？🤖🚀

Zep 使用 Zep 服务器本地的低延迟模型自动嵌入添加到 Zep 向量存储的文档。Zep TS/JS 客户端可在非 Node 边缘环境中使用。这两项功能以及 Zep 的聊天记忆功能使 Zep 成为构建延迟和性能至关重要的对话式 LLM 应用程序的理想选择。

支持的搜索类型

Zep 支持相似性搜索和最大边际相关性 (MMR) 搜索。MMR 搜索对于检索增强生成应用程序特别有用，因为它会重新排序结果以确保返回文档的多样性。

安装

请遵循Zep 开源快速入门指南来安装并开始使用 Zep。

用法

您需要 Zep API URL，并且可选地需要 API 密钥才能使用 Zep VectorStore。有关更多信息，请参阅Zep 文档。在下面的示例中，我们使用了 Zep 的自动嵌入功能，该功能使用低延迟嵌入模型自动在 Zep 服务器上嵌入文档。由于 LangChain 需要传入一个Embeddings实例，因此我们传入 FakeEmbeddings。 注意：如果您传入的Embeddings实例不是 FakeEmbeddings，则此实例将用于嵌入文档。您还必须将文档集合设置为 isAutoEmbedded === false。请参阅下面的 OpenAIEmbeddings 示例。

示例：从文档创建 ZepVectorStore 并查询

有关安装 LangChain 软件包的一般说明，请参阅此部分。

npm

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

import { ZepVectorStore } from "@langchain/community/vectorstores/zep";
import { FakeEmbeddings } from "@langchain/core/utils/testing";
import { TextLoader } from "@langchain/classic/document_loaders/fs/text";
import { randomUUID } from "crypto";

const loader = new TextLoader("src/document_loaders/example_data/example.txt");
const docs = await loader.load();
export const run = async () => {
  const collectionName = `collection${randomUUID().split("-")[0]}`;

  const zepConfig = {
    apiUrl: "https://:8000", // this should be the URL of your Zep implementation
    collectionName,
    embeddingDimensions: 1536, // this much match the width of the embeddings you're using
    isAutoEmbedded: true, // If true, the vector store will automatically embed documents when they are added
  };

  const embeddings = new FakeEmbeddings();

  const vectorStore = await ZepVectorStore.fromDocuments(
    docs,
    embeddings,
    zepConfig
  );

  // Wait for the documents to be embedded
  // eslint-disable-next-line no-constant-condition
  while (true) {
    const c = await vectorStore.client.document.getCollection(collectionName);
    console.log(
      `Embedding status: ${c.document_embedded_count}/${c.document_count} documents embedded`
    );
    // eslint-disable-next-line no-promise-executor-return
    await new Promise((resolve) => setTimeout(resolve, 1000));
    if (c.status === "ready") {
      break;
    }
  }

  const results = await vectorStore.similaritySearchWithScore("bar", 3);

  console.log("Similarity Results:");
  console.log(JSON.stringify(results));

  const results2 = await vectorStore.maxMarginalRelevanceSearch("bar", {
    k: 3,
  });

  console.log("MMR Results:");
  console.log(JSON.stringify(results2));
};

示例：使用元数据过滤器查询 ZepVectorStore

import { ZepVectorStore } from "@langchain/community/vectorstores/zep";
import { FakeEmbeddings } from "@langchain/core/utils/testing";
import { randomUUID } from "crypto";
import { Document } from "@langchain/core/documents";

const docs = [
  new Document({
    metadata: { album: "Led Zeppelin IV", year: 1971 },
    pageContent:
      "Stairway to Heaven is one of the most iconic songs by Led Zeppelin.",
  }),
  new Document({
    metadata: { album: "Led Zeppelin I", year: 1969 },
    pageContent:
      "Dazed and Confused was a standout track on Led Zeppelin's debut album.",
  }),
  new Document({
    metadata: { album: "Physical Graffiti", year: 1975 },
    pageContent:
      "Kashmir, from Physical Graffiti, showcases Led Zeppelin's unique blend of rock and world music.",
  }),
  new Document({
    metadata: { album: "Houses of the Holy", year: 1973 },
    pageContent:
      "The Rain Song is a beautiful, melancholic piece from Houses of the Holy.",
  }),
  new Document({
    metadata: { band: "Black Sabbath", album: "Paranoid", year: 1970 },
    pageContent:
      "Paranoid is Black Sabbath's second studio album and includes some of their most notable songs.",
  }),
  new Document({
    metadata: {
      band: "Iron Maiden",
      album: "The Number of the Beast",
      year: 1982,
    },
    pageContent:
      "The Number of the Beast is often considered Iron Maiden's best album.",
  }),
  new Document({
    metadata: { band: "Metallica", album: "Master of Puppets", year: 1986 },
    pageContent:
      "Master of Puppets is widely regarded as Metallica's finest work.",
  }),
  new Document({
    metadata: { band: "Megadeth", album: "Rust in Peace", year: 1990 },
    pageContent:
      "Rust in Peace is Megadeth's fourth studio album and features intricate guitar work.",
  }),
];

export const run = async () => {
  const collectionName = `collection${randomUUID().split("-")[0]}`;

  const zepConfig = {
    apiUrl: "https://:8000", // this should be the URL of your Zep implementation
    collectionName,
    embeddingDimensions: 1536, // this much match the width of the embeddings you're using
    isAutoEmbedded: true, // If true, the vector store will automatically embed documents when they are added
  };

  const embeddings = new FakeEmbeddings();

  const vectorStore = await ZepVectorStore.fromDocuments(
    docs,
    embeddings,
    zepConfig
  );

  // Wait for the documents to be embedded
  // eslint-disable-next-line no-constant-condition
  while (true) {
    const c = await vectorStore.client.document.getCollection(collectionName);
    console.log(
      `Embedding status: ${c.document_embedded_count}/${c.document_count} documents embedded`
    );
    // eslint-disable-next-line no-promise-executor-return
    await new Promise((resolve) => setTimeout(resolve, 1000));
    if (c.status === "ready") {
      break;
    }
  }

  vectorStore
    .similaritySearchWithScore("sad music", 3, {
      where: { jsonpath: "$[*] ? (@.year == 1973)" }, // We should see a single result: The Rain Song
    })
    .then((results) => {
      console.log(`\n\nSimilarity Results:\n${JSON.stringify(results)}`);
    })
    .catch((e) => {
      if (e.name === "NotFoundError") {
        console.log("No results found");
      } else {
        throw e;
      }
    });

  // We're not filtering here, but rather demonstrating MMR at work.
  // We could also add a filter to the MMR search, as we did with the similarity search above.
  vectorStore
    .maxMarginalRelevanceSearch("sad music", {
      k: 3,
    })
    .then((results) => {
      console.log(`\n\nMMR Results:\n${JSON.stringify(results)}`);
    })
    .catch((e) => {
      if (e.name === "NotFoundError") {
        console.log("No results found");
      } else {
        throw e;
      }
    });
};

示例：使用 LangChain Embedding 类，例如 `OpenAIEmbeddings`

import { ZepVectorStore } from "@langchain/community/vectorstores/zep";
import { OpenAIEmbeddings } from "@langchain/openai";
import { TextLoader } from "@langchain/classic/document_loaders/fs/text";
import { randomUUID } from "crypto";

const loader = new TextLoader("src/document_loaders/example_data/example.txt");
const docs = await loader.load();
export const run = async () => {
  const collectionName = `collection${randomUUID().split("-")[0]}`;

  const zepConfig = {
    apiUrl: "https://:8000", // this should be the URL of your Zep implementation
    collectionName,
    embeddingDimensions: 1536, // this much match the width of the embeddings you're using
    isAutoEmbedded: false, // set to false to disable auto-embedding
  };

  const embeddings = new OpenAIEmbeddings();

  const vectorStore = await ZepVectorStore.fromDocuments(
    docs,
    embeddings,
    zepConfig
  );

  const results = await vectorStore.similaritySearchWithScore("bar", 3);

  console.log("Similarity Results:");
  console.log(JSON.stringify(results));

  const results2 = await vectorStore.maxMarginalRelevanceSearch("bar", {
    k: 3,
  });

  console.log("MMR Results:");
  console.log(JSON.stringify(results2));
};

向量存储概念指南
向量存储操作指南

在 GitHub 上编辑此页面源文件。

以编程方式连接这些文档到 Claude、VSCode 等，通过 MCP 获取实时答案。

热门提供商

通用集成

RAG 集成

Zep 的 VectorStore 有何优势？🤖🚀

支持的搜索类型

安装

用法

示例：从文档创建 ZepVectorStore 并查询

示例：使用元数据过滤器查询 ZepVectorStore

示例：使用 LangChain Embedding 类，例如 `OpenAIEmbeddings`

热门提供商

通用集成

RAG 集成

​Zep 的 VectorStore 有何优势？🤖🚀

​支持的搜索类型

​安装

​用法

​示例：从文档创建 ZepVectorStore 并查询

​示例：使用元数据过滤器查询 ZepVectorStore

​示例：使用 LangChain Embedding 类，例如 OpenAIEmbeddings

​相关

Zep 的 VectorStore 有何优势？🤖🚀

支持的搜索类型

安装

用法

示例：从文档创建 ZepVectorStore 并查询

示例：使用元数据过滤器查询 ZepVectorStore

示例：使用 LangChain Embedding 类，例如 `OpenAIEmbeddings`

相关