← All features

Multi-Format Indexing

Index Markdown, Office, PDF, mail, calendar, transcripts, and browser exports

GNO indexes documents plus portable JSONL, mail, calendar, transcript, and browser exports. Export containers become independently searchable read-only records without live account access.

Use cases
Mixed-format research corpora
Teams indexing docs, slides, and spreadsheets together
Local archives exported from mail, calendar, browser, or transcript tools
Corpora that mix Markdown with Office, PDF, and export formats

What it gives you

  • Markdown with frontmatter extraction
  • PDF text extraction
  • Office documents (DOCX, XLSX, PPTX)
  • Plain text files
  • Portable JSONL records and explicit browser bookmark/history exports
  • EML/MBOX mail and ICS calendar events
  • WebVTT/SRT plus explicitly configured JSON or text transcripts
  • Read-only logical records with exact source locators and attachment inventory
  • Automatic structural first-pass chunking for ts/js/python/go/rust
  • Document-language detection for en, de, fr, it, zh, ja, and ko
  • Content deduplication via mirror hashing
  • Incremental indexing with SHA-256 change detection

Try it yourself

Representative commands and entry points. Full reference lives in the documentation.

gno setup ~/docs --name docs
gno collection add ~/exports --name exports --pattern '**/*.{jsonl,eml,mbox,ics,vtt,srt}'
gno update
gno ls --json

Keep reading

Related features and docs.