@ragfoundry/adapter-loader-text

📄 Text and Markdown loader. Load .txt, .md and .markdown files from a directory or a single file.

A DocumentLoader adapter for RAGFoundry — typed retrieval-augmented generation for TypeScript.

💡 New to RAGFoundry? This page is for adding one specific provider to an app you're already building. Starting a project from scratch is faster with the scaffolder — it asks a few questions and wires everything (including this adapter, if you pick it) for you:

npm create @ragfoundry my-app

→ @ragfoundry/create

📦 Install

npm install @ragfoundry/core @ragfoundry/adapter-loader-text

🚀 Usage

Works with both import and require — this package ships both builds.

ESM:

import { createRAG } from "@ragfoundry/core"
import "@ragfoundry/adapter-loader-text"

const rag = createRAG({
  loader: { provider: "text", extensions: [".md"], recursive: true },
  // ...the rest of your config
})

CommonJS:

const { createRAG } = require("@ragfoundry/core")
require("@ragfoundry/adapter-loader-text")

const rag = createRAG({
  loader: { provider: "text", extensions: [".md"], recursive: true },
  // ...the rest of your config
})

⚠️ The import/require is what registers "text" at runtime — remove it and createRAG throws Unknown adapter "text", even though the provider name is still typed correctly. In TypeScript it's also what makes the loader block above autocomplete and type-check.

⚙️ Options

| Option | Type | Required | Default | |---|---|---|---| | extensions | string[] | no | [".txt", ".md", ".markdown"] | | recursive | boolean | no | true | | encoding | BufferEncoding | no | utf8 |

📝 Document ids are paths relative to the source root with forward slashes, so chunk ids stay stable across machines. A file named directly is loaded whatever its extension — the filter applies to directory walks.

🔗 See also

• @ragfoundry/core — the pipelines, types, and every export explained
• @ragfoundry/create — npm create @ragfoundry, scaffold a whole project

📄 License

MIT