Command Line Interface

pip install datalab-python-sdk

export DATALAB_API_KEY=your_api_key_here

datalab convert document.pdf --api_key YOUR_API_KEY

# Convert a single file
datalab convert document.pdf

# Convert to specific format
datalab convert document.pdf --format html

# Convert with processing mode
datalab convert document.pdf --mode accurate

# Save to specific directory
datalab convert document.pdf --output_dir ./output/

# Output formats
datalab convert document.pdf --format markdown
datalab convert document.pdf --format html
datalab convert document.pdf --format json
datalab convert document.pdf --format chunks

# Processing modes
datalab convert document.pdf --mode fast       # Lowest latency (default)
datalab convert document.pdf --mode balanced   # Balance of speed and accuracy
datalab convert document.pdf --mode accurate   # Highest accuracy

# Limit pages
datalab convert document.pdf --max_pages 10

# Specific page range (0-indexed)
datalab convert document.pdf --page_range "0-5,10,15-20"

# For spreadsheets, page_range filters by sheet index
datalab convert workbook.xlsx --page_range "0,2"

# Add page delimiters
datalab convert document.pdf --paginate

# Add block IDs for citations (HTML only)
datalab convert document.pdf --format html --add_block_ids

# Disable image extraction
datalab convert document.pdf --disable_image_extraction

# Disable image captions
datalab convert document.pdf --disable_image_captions

# Skip cached results
datalab convert document.pdf --skip_cache

# Convert all supported files
datalab convert ./documents/ --output_dir ./output/

# Filter by extension
datalab convert ./documents/ --extensions pdf,docx

# Control concurrency
datalab convert ./documents/ --max_concurrent 5

# Extract data using a page schema
datalab extract invoice.pdf \
  --page_schema '{"invoice_number": {"type": "string"}, "total": {"type": "number"}}'

# Extract with a specific mode
datalab extract invoice.pdf \
  --page_schema '{"title": {"type": "string"}}' \
  --mode accurate

# Extract using a checkpoint from a previous conversion
datalab extract invoice.pdf \
  --page_schema '{"total": {"type": "number"}}' \
  --checkpoint_id "ckpt_abc123"

# Segment a document
datalab segment report.pdf \
  --segmentation_schema '{"sections": [{"name": "intro", "description": "Introduction"}, {"name": "body", "description": "Main content"}]}'

# Segment with a checkpoint
datalab segment report.pdf \
  --segmentation_schema '{"sections": [{"name": "summary", "description": "Executive summary"}]}' \
  --checkpoint_id "ckpt_abc123"

# Extract tracked changes from a Word document
datalab track-changes contract.docx

# Specify output format
datalab track-changes contract.docx --format html

# With pagination
datalab track-changes contract.docx --format html --paginate

# Run a custom processor
datalab custom-pipeline document.pdf --pipeline_id "cp_XXXXX"

# Run with evaluation
datalab custom-pipeline document.pdf \
  --pipeline_id "cp_XXXXX" \
  --run_eval

# Specify format and mode
datalab custom-pipeline document.pdf \
  --pipeline_id "cp_XXXXX" \
  --format json \
  --mode accurate

# Create a document from a markdown file
datalab create-document --markdown input.md --output output.docx

# Create a document from inline markdown content
datalab create-document \
  --markdown "# Title\n\nDocument content here." \
  --output document.docx

# Convert all PDFs in a directory with accurate mode
datalab convert ./invoices/ \
  --extensions pdf \
  --mode accurate \
  --format json \
  --output_dir ./processed/

# Extract structured data using a schema
datalab extract invoice.pdf \
  --page_schema '{
    "invoice_number": {"type": "string", "description": "Invoice ID"},
    "total": {"type": "number", "description": "Total amount"},
    "vendor": {"type": "string", "description": "Vendor name"}
  }' \
  --mode balanced \
  --output_dir ./extracted/

# Process many files with high concurrency
datalab convert ./documents/ \
  --max_concurrent 10 \
  --mode fast \
  --output_dir ./output/

# General help
datalab --help

# Command-specific help
datalab convert --help
datalab extract --help
datalab segment --help
datalab track-changes --help
datalab custom-pipeline --help
datalab create-document --help