Skip to content

Class HTM::Loaders::MarkdownLoader

Inherits Object
Defined in lib/htm/loaders/markdown_loader.rb

Markdown file loader

Loads markdown files into HTM long-term memory with support for: * YAML frontmatter parsing (stored as metadata on first chunk) * Paragraph-based chunking * Re-sync on file changes (via mtime comparison) * Duplicate detection via content_hash

@example Load a single file 

loader = MarkdownLoader.new(htm)
result = loader.load_file('/path/to/doc.md')
# => { file_path: '/path/to/doc.md', chunks_created: 5, ... }

@example Load a directory 

results = loader.load_directory('/path/to/docs', pattern: '**/*.md')

Constants

FRONTMATTER_REGEX

Not documented.

MAX_FILE_SIZE

10 MB maximum file size

Public Instance Methods

initialize(htm_instance, chunk_size: nil, chunk_overlap: nil)

  • @param htm_instance [HTM] The HTM instance to use for storing nodes
  • @param chunk_size [Integer] Maximum characters per chunk (default: from config)
  • @param chunk_overlap [Integer] Character overlap between chunks (default: from config)
  • @return [MarkdownLoader] a new instance of MarkdownLoader

load_directory(path, pattern: '**/*.md', force: false)

Load all matching files from a directory - @param path [String] Directory path - @param pattern [String] Glob pattern (default: '**/*.md') - @param force [Boolean] Force re-sync even if unchanged - @return [Array] Results for each file

load_file(path, force: false)

Load a single markdown file into long-term memory - @param path [String] Path to markdown file - @param force [Boolean] Force re-sync even if mtime unchanged - @return [Hash] Load result with keys: - :file_path [String] Absolute path to file - :chunks_created [Integer] Number of new chunks created - :chunks_updated [Integer] Number of existing chunks updated - :chunks_deleted [Integer] Number of chunks soft-deleted - :skipped [Boolean] True if file was unchanged and skipped