跳至主要内容

BM25

BM25,也称为 Okapi BM25,是一种在信息检索系统中使用的排序函数,用于估计文档与给定搜索查询的相关性。

您可以将其用作检索管道的一部分,作为后处理步骤,在从其他来源检索初始文档集之后重新排序文档。

设置

BM25Retriever@langchain/community 导出。 您需要像这样安装它

yarn add @langchain/community @langchain/core

此检索器使用 此实现 的 Okapi BM25 中的代码。

用法

您现在可以使用先前检索到的文档创建一个新的检索器

import { BM25Retriever } from "@langchain/community/retrievers/bm25";

const retriever = BM25Retriever.fromDocuments(
[
{ pageContent: "Buildings are made out of brick", metadata: {} },
{ pageContent: "Buildings are made out of wood", metadata: {} },
{ pageContent: "Buildings are made out of stone", metadata: {} },
{ pageContent: "Cars are made out of metal", metadata: {} },
{ pageContent: "Cars are made out of plastic", metadata: {} },
{ pageContent: "mitochondria is the powerhouse of the cell", metadata: {} },
{ pageContent: "mitochondria is made of lipids", metadata: {} },
],
{ k: 4 }
);

// Will return the 4 documents reranked by the BM25 algorithm
await retriever.invoke("mitochondria");
[
{ pageContent: 'mitochondria is made of lipids', metadata: {} },
{
pageContent: 'mitochondria is the powerhouse of the cell',
metadata: {}
},
{ pageContent: 'Buildings are made out of brick', metadata: {} },
{ pageContent: 'Buildings are made out of wood', metadata: {} }
]

此页面是否有帮助?


您也可以留下详细的反馈 在 GitHub 上.