Skip to main content

Class: MarkdownLoader

Defined in: packages/agentos/src/memory/ingestion/MarkdownLoader.ts:114

Document loader for Markdown (.md) and MDX (.mdx) files.

Front-matter handling​

YAML front-matter delimited by --- is parsed via gray-matter. All key-value pairs are merged into DocumentMetadata as-is, with a handful of well-known keys (title, author, createdAt, modifiedAt, language) mapped to the corresponding typed metadata fields.

Title extraction fallback​

When the front-matter does not contain a title field the loader searches the document body for the first level-1 ATX heading (# Title) and uses that as the title.

Returned content​

The content field in the returned LoadedDocument contains the Markdown body without the front-matter block.

Implements​

Example​

const loader = new MarkdownLoader();
const doc = await loader.load('/docs/architecture.md');
console.log(doc.metadata.title); // from front-matter or first # heading

Implements​

Constructors​

Constructor​

new MarkdownLoader(): MarkdownLoader

Returns​

MarkdownLoader

Properties​

supportedExtensions​

readonly supportedExtensions: string[]

Defined in: packages/agentos/src/memory/ingestion/MarkdownLoader.ts:116

File extensions this loader handles, each with a leading dot.

Used by LoaderRegistry to route file paths to the correct loader.

Example​

['.md', '.mdx']

Implementation of​

IDocumentLoader.supportedExtensions

Methods​

canLoad()​

canLoad(source): boolean

Defined in: packages/agentos/src/memory/ingestion/MarkdownLoader.ts:123

Returns true when this loader is capable of handling source.

For string sources the check is purely extension-based. For Buffer sources the loader may inspect magic bytes when relevant.

Parameters​

source​

Absolute file path or raw bytes.

string | Buffer

Returns​

boolean

Implementation of​

IDocumentLoader.canLoad

load()​

load(source, _options?): Promise<LoadedDocument>

Defined in: packages/agentos/src/memory/ingestion/MarkdownLoader.ts:137

Parses source and returns a normalised LoadedDocument.

When source is a string the loader treats it as an absolute (or resolvable) file path and reads the file from disk. When source is a Buffer the loader parses the bytes directly and derives as much metadata as possible from the buffer content alone.

Parameters​

source​

Absolute file path OR raw document bytes.

string | Buffer

_options?​

LoadOptions

Optional hints such as a format override.

Returns​

Promise<LoadedDocument>

A promise resolving to the fully-populated LoadedDocument.

Throws​

When the file cannot be read or the format is not parsable.

Implementation of​

IDocumentLoader.load