This example goes over how to load data from multiple file paths. The second argument is a map of file extensions to loader factories. Each file will be passed to the matching loader, and the resulting documents will be concatenated together. Example files: 
src/document_loaders/example_data/example/
├── example.txt
└── example.csv

src/document_loaders/example_data/example2/
├── example.json
└── example.jsonl
Example code: 
import { MultiFileLoader } from "langchain/document_loaders/fs/multi_file";
import {
  JSONLoader,
  JSONLinesLoader,
} from "langchain/document_loaders/fs/json";
import { TextLoader } from "langchain/document_loaders/fs/text";
import { CSVLoader } from "langchain/document_loaders/fs/csv";

const loader = new MultiFileLoader(
  [
    "src/document_loaders/example_data/example/example.txt",
    "src/document_loaders/example_data/example/example.csv",
    "src/document_loaders/example_data/example2/example.json",
    "src/document_loaders/example_data/example2/example.jsonl",
  ],
  {
    ".json": (path) => new JSONLoader(path, "/texts"),
    ".jsonl": (path) => new JSONLinesLoader(path, "/html"),
    ".txt": (path) => new TextLoader(path),
    ".csv": (path) => new CSVLoader(path, "text"),
  }
);
const docs = await loader.load();
console.log({ docs });