Skip to main content

Quickstart

End-to-end workflow from login to document processing.

1. Log In​

fissionbox auth login

2. Set Your Default Namespace​

fissionbox namespace use --namespace-id ns-abc123

This saves the namespace so you don't need to pass --namespace-id on every command.

3. Queue Documents for Processing​

The queue command is the recommended workflow for batches. It handles upload, live monitoring, and download in one step:

fissionbox document queue \
    --path ./invoices/ \
    --path extra.pdf \
    --extract-images \
    --output-dir ./fissionbox-output

This does three phases automatically:

  1. Upload — Progress bar with filename, file size, count, and elapsed time
  2. Watch — Live table polling every 5s showing status, elapsed time, chunk/image counts, and available artifacts
  3. Download — Progress bar across all files, then a file-tree view per document

4. View Results​

Each processed document gets its own folder:

./fissionbox-output/
  invoice_jan/
    response.json     ← full extraction response
    markdown.md       ← document text as Markdown
    extracted.json    ← structured fields (if schema used)
    chunks.ndjson     ← text chunks for RAG / vector stores
    images/           ← extracted images
    annotated.pdf     ← annotated PDF (if annotation run)

Next Steps​