[ERR_PACKAGE_PATH_NOT_EXPORTED]: Package subpath './dist/document_loaders/web/cheerio' is not defined by "exports" in \node_modules\@langchain\community\package.json

[LaiYu111]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

import "cheerio"
import "pdf-parse";
import {CheerioWebBaseLoader} from "@langchain/community/dist/document_loaders/web/cheerio";
// import {PDFLoader} from "@langchain/community/dist/document_loaders/fs/pdf";

// const loader = new PDFLoader("./1.pdf")

const loader = new CheerioWebBaseLoader(
  "https://lilianweng.github.io/posts/2023-06-23-agent/"
);

const docs = await loader.load()

Description

I am using nest.js and trying to write a service. I tried to load the PDF file and a web source, but an error occurred.

(Cheerio)
[ERR_PACKAGE_PATH_NOT_EXPORTED]: Package subpath './dist/document_loaders/web/cheerio' is not defined by "exports" in ..\node_modules@langchain\community\package.json

(PDFLoader)
r [ERR_PACKAGE_PATH_NOT_EXPORTED]: Package subpath './dist/document_loaders/fs/pdf' is not defined by "exports" in \node_modules@langchain\community\package.json

System Info

node.js: 20.9.0
Platform: Windows
"langchain": "^0.2.11",
"pdf-parse": "^1.1.1",
"cheerio": "^1.0.0-rc.12",

[dosubot[bot]]

Hey @LaiYu111! I'm here to help you with your bug, answer your questions, and guide you on becoming a contributor. Let's take a look at the issue together.

To resolve the errors related to Cheerio and PDFLoader, you need to import the modules correctly without using the dist subpath. Here is how you can adjust your imports:

For Cheerio, use the following import path:

import { CheerioWebBaseLoader } from "@langchain/community/document_loaders/web/cheerio";

const loader = new CheerioWebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/");
const docs = await loader.load();
console.log({ docs });

For PDFLoader, use the following import path:

import { PDFLoader } from "@langchain/community/document_loaders/fs/pdf";

const pdfLoader = new PDFLoader("./1.pdf");
const pdfDocs = await pdfLoader.load();
console.log({ pdfDocs });

Make sure you have installed all necessary dependencies:

yarn add cheerio @langchain/community

By following these steps, you should be able to resolve the errors related to Cheerio and PDFLoader in your Nest.js service ^[1][2].

To continue talking to Dosu, mention @dosu.