跳至主要内容

Vectara

本指南将帮助您开始使用这种由 Vectara 向量存储 支持的检索器。有关所有功能和配置的详细文档，请访问 API 参考。

概述​

一个 自查询检索器 通过动态生成基于某些输入查询的元数据过滤器来检索文档。这使得检索器能够在获取结果时除了纯粹的语义相似性之外，还考虑底层文档元数据。

它使用一个称为 Translator 的模块，该模块根据有关元数据字段和给定向量存储支持的查询语言的信息生成过滤器。

集成细节​

支持向量存储自托管云服务包Py 支持
VectaraStore❌✅@langchain/community✅

设置​

按照 此处 文档设置 Vectara 实例。设置以下环境变量

process.env.VECTARA_CUSTOMER_ID = "your_customer_id";
process.env.VECTARA_CORPUS_ID = "your_corpus_id";
process.env.VECTARA_API_KEY = "your-vectara-api-key";

如果您想从各个查询中获取自动跟踪，还可以通过取消以下注释来设置您的 LangSmith API 密钥

// process.env.LANGSMITH_API_KEY = "<YOUR API KEY HERE>";
// process.env.LANGSMITH_TRACING = "true";

安装​

向量存储位于 @langchain/community 包中。您还需要安装 langchain 包来导入主要的 SelfQueryRetriever 类。

提示

有关安装集成包的常规说明，请参阅 此部分。

yarn add @langchain/community langchain @langchain/core

实例化​

首先，使用包含元数据的某些文档初始化您的 Vectara 向量存储

import { VectaraStore } from "@langchain/community/vectorstores/vectara";
import { Document } from "@langchain/core/documents";
import type { AttributeInfo } from "langchain/chains/query_constructor";

// Vectara provides embeddings
import { FakeEmbeddings } from "@langchain/core/utils/testing";

/**
 * First, we create a bunch of documents. You can load your own documents here instead.
 * Each document has a pageContent and a metadata field. Make sure your metadata matches the AttributeInfo below.
 */
const docs = [
  new Document({
    pageContent:
      "A bunch of scientists bring back dinosaurs and mayhem breaks loose",
    metadata: { year: 1993, rating: 7.7, genre: "science fiction" },
  }),
  new Document({
    pageContent:
      "Leo DiCaprio gets lost in a dream within a dream within a dream within a ...",
    metadata: { year: 2010, director: "Christopher Nolan", rating: 8.2 },
  }),
  new Document({
    pageContent:
      "A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea",
    metadata: { year: 2006, director: "Satoshi Kon", rating: 8.6 },
  }),
  new Document({
    pageContent:
      "A bunch of normal-sized women are supremely wholesome and some men pine after them",
    metadata: { year: 2019, director: "Greta Gerwig", rating: 8.3 },
  }),
  new Document({
    pageContent: "Toys come alive and have a blast doing so",
    metadata: { year: 1995, genre: "animated" },
  }),
  new Document({
    pageContent: "Three men walk into the Zone, three men walk out of the Zone",
    metadata: {
      year: 1979,
      director: "Andrei Tarkovsky",
      genre: "science fiction",
      rating: 9.9,
    },
  }),
];

/**
 * Next, we define the attributes we want to be able to query on.
 * in this case, we want to be able to query on the genre, year, director, rating, and length of the movie.
 * We also provide a description of each attribute and the type of the attribute.
 * This is used to generate the query prompts.
 */
const attributeInfo: AttributeInfo[] = [
  {
    name: "genre",
    description: "The genre of the movie",
    type: "string or array of strings",
  },
  {
    name: "year",
    description: "The year the movie was released",
    type: "number",
  },
  {
    name: "director",
    description: "The director of the movie",
    type: "string",
  },
  {
    name: "rating",
    description: "The rating of the movie (1-10)",
    type: "number",
  },
  {
    name: "length",
    description: "The length of the movie in minutes",
    type: "number",
  },
];

/**
 * Next, we instantiate a vector store. This is where we store the embeddings of the documents.
 * We also need to provide an embeddings object. This is used to embed the documents.
 */
// Vectara provides embeddings
const embeddings = new FakeEmbeddings();
const vectorStore = await VectaraStore.fromDocuments(docs, embeddings, {
  customerId: Number(process.env.VECTARA_CUSTOMER_ID),
  corpusId: Number(process.env.VECTARA_CORPUS_ID),
  apiKey: String(process.env.VECTARA_API_KEY),
});

现在我们可以实例化我们的检索器

选择您的聊天模型

安装依赖项

提示

请参阅 有关安装集成包的常规说明，请参阅此部分.

yarn add @langchain/openai

添加环境变量

OPENAI_API_KEY=your-api-key

实例化模型

import { ChatOpenAI } from "@langchain/openai";

const llm = new ChatOpenAI({
  model: "gpt-4o-mini",
  temperature: 0
});
import { SelfQueryRetriever } from "langchain/retrievers/self_query";
import { VectaraTranslator } from "@langchain/community/structured_query/vectara";

const selfQueryRetriever = SelfQueryRetriever.fromLLM({
  llm: llm,
  vectorStore: vectorStore,
  /** A short summary of what the document contents represent. */
  documentContents: "Brief summary of a movie",
  attributeInfo: attributeInfo,
  structuredQueryTranslator: new VectaraTranslator(),
});

用法​

现在，问一个需要一些关于文档元数据的知识才能回答的问题。您可以看到检索器将生成正确的结果

await selfQueryRetriever.invoke("Which movies are rated higher than 8.5?");
[
  Document {
    pageContent: 'A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea',
    metadata: { year: 2006, rating: 8.6, director: 'Satoshi Kon' },
    id: undefined
  },
  Document {
    pageContent: 'Three men walk into the Zone, three men walk out of the Zone',
    metadata: {
      year: 1979,
      genre: 'science fiction',
      rating: 9.9,
      director: 'Andrei Tarkovsky'
    },
    id: undefined
  }
]

在链中使用​

与其他检索器一样，Vectara 自查询检索器可以通过 链 集成到 LLM 应用程序中。

请注意，由于它们的返回答案可能严重依赖于文档元数据，因此我们以不同的格式对检索到的文档进行格式化，以包括该信息。

import { ChatPromptTemplate } from "@langchain/core/prompts";
import {
  RunnablePassthrough,
  RunnableSequence,
} from "@langchain/core/runnables";
import { StringOutputParser } from "@langchain/core/output_parsers";

import type { Document } from "@langchain/core/documents";

const prompt = ChatPromptTemplate.fromTemplate(`
Answer the question based only on the context provided.

Context: {context}

Question: {question}`);

const formatDocs = (docs: Document[]) => {
  return docs.map((doc) => JSON.stringify(doc)).join("\n\n");
};

// See https://js.langchain.ac.cn/docs/tutorials/rag
const ragChain = RunnableSequence.from([
  {
    context: selfQueryRetriever.pipe(formatDocs),
    question: new RunnablePassthrough(),
  },
  prompt,
  llm,
  new StringOutputParser(),
]);
await ragChain.invoke("Which movies are rated higher than 8.5?");
The movies rated higher than 8.5 are:

1. The movie directed by Satoshi Kon in 2006, which has a rating of 8.6.
2. The movie directed by Andrei Tarkovsky in 1979, which has a rating of 9.9.

默认搜索参数​

您还可以将 searchParams 字段传递到上述方法中，该字段提供除任何生成的查询之外还应用的默认过滤器。

有关如何构建元数据过滤器的更多信息，请参阅 官方文档。

const selfQueryRetrieverWithDefaultParams = SelfQueryRetriever.fromLLM({
  llm,
  vectorStore,
  documentContents: "Brief summary of a movie",
  attributeInfo,
  /**
   * We need to use a translator that translates the queries into a
   * filter format that the vector store can understand. LangChain provides one here.
   */
  structuredQueryTranslator: new VectaraTranslator(),
  searchParams: {
    filter: {
      filter: "( doc.genre = 'science fiction' ) and ( doc.rating > 8.5 )",
    },
    mergeFiltersOperator: "and",
  },
});

API 参考​

有关所有 Vectara 自查询检索器功能和配置的详细文档，请访问 API 参考。

此页面是否有用？


您也可以留下详细的反馈 在 GitHub 上.