Document Loaders

npm install @langchain/community

# For PDF loading
npm install pdf-parse

# For DOCX loading
npm install mammoth

# For web scraping
npm install cheerio

# For Puppeteer
npm install puppeteer

import { CSVLoader } from "@langchain/community/document_loaders/fs/csv";

const loader = new CSVLoader("path/to/file.csv");
const docs = await loader.load();

// Load specific column
const loader2 = new CSVLoader("path/to/file.csv", "content");
const docs2 = await loader2.load();

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

const loader = new PDFLoader("path/to/file.pdf");
const docs = await loader.load();

import { DocxLoader } from "@langchain/community/document_loaders/fs/docx";

const loader = new DocxLoader("path/to/file.docx");
const docs = await loader.load();

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

const loader = new CheerioWebBaseLoader("https://example.com");
const docs = await loader.load();

// With custom selector
const loader2 = new CheerioWebBaseLoader("https://example.com", {
  selector: ".article-content"
});

import { PuppeteerWebBaseLoader } from "@langchain/community/document_loaders/web/puppeteer";

const loader = new PuppeteerWebBaseLoader("https://example.com");
const docs = await loader.load();

import { S3Loader } from "@langchain/community/document_loaders/web/s3";

const loader = new S3Loader({
  bucket: "my-bucket",
  key: "path/to/file.txt",
  region: "us-east-1"
});
const docs = await loader.load();

import { GithubRepoLoader } from "@langchain/community/document_loaders/web/github";

const loader = new GithubRepoLoader(
  "langchain-ai/langchainjs",
  {
    branch: "main",
    recursive: true,
    unknown: "warn",
    maxConcurrency: 5
  }
);

import { CSVLoader } from "@langchain/community/document_loaders/fs/csv";

const loader = new CSVLoader("data.csv");
const docs = await loader.load();

console.log(docs[0].pageContent);
console.log(docs[0].metadata);

for await (const doc of loader.loadLazy()) {
  console.log(doc.pageContent);
}

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

class CustomLoader extends CheerioWebBaseLoader {
  async scrape() {
    const $ = await super.scrape();
    // Custom processing
    return $;
  }
}

interface Document {
  pageContent: string;  // The main text content
  metadata: Record<string, any>;  // Additional information
}