Document loader integrations | LangChain English

Document loaders provide a standard interface for reading data from different sources (such as Slack, Notion, or Google Drive) into LangChain's Document format. This ensures that data can be handled consistently regardless of the source.

All document loaders implement the BaseLoader interface.

Warning

Community document loaders are user-contributed and unverified. LangChain does not review or endorse these integrations; use them at your own risk.

Interface

Each document loader may define its own parameters, but they share a common API:

load(): Loads all documents at once.
loadAndSplit(): Loads all documents at once and splits them into smaller documents.

import { OracleDocLoader } from "@oracle/langchain-oracledb";

const loader = new OracleDocLoader(,
  ...  // <-- Integration specific parameters here
);
const data = await loader.load();

By category

LangChain.js categorizes document loaders in two different ways:

File loaders, which load data into LangChain formats from your local filesystem.
Web loaders, which load data from remote sources.

File loaders

Info

If you'd like to contribute an integration, see Contributing integrations.

Common file types

Document Loader	Description	Package/API
`DirectoryLoader`	Load all files from a directory with custom loader mappings	Package
JSON	Load JSON files using JSON pointer to target specific keys	Package
`JSONLines`	Load data from JSONLines/JSONL files	Package
`Text`	Load plain text files	Package

Specialized file loaders

Document Loader	Description	Package/API
`MultiFileLoader`	Load data from multiple individual file paths	Package
`OracleDocLoader`	Ingest Oracle AI Vector Search tables or Oracle Text-supported files	Package

Web loaders

Cloud providers

Document Loader	Description	Web Support	Package/API
Google Cloud SQL for PostgreSQL	Load documents from Cloud SQL PostgreSQL databases	✅	Package

Audio & video

Document Loader	Description	Web Support	Package/API
`Soniox`	Transcribe multilingual audio files with optional translation using Soniox API	✅	API

Other

Document Loader	Description	Web Support	Package/API
`LangSmith`	Load datasets and traces from LangSmith	✅	API

All document loaders

Integration	Downloads
`Google cloud SQL for postgresql`
`Soniox`
`DirectoryLoader`	N/A
`JSON files`	N/A
`Jsonlines files -`	N/A
`LangSmithLoader`	N/A
`Multiple individual files -`	N/A
`OracleDocLoader`	N/A
`TextLoader`	N/A