Extracting Tables

Extracting tables

Use this when the user wants structured tabular data — financial statements, scientific tables, invoices, spreadsheet-style PDFs. Kreuzberg detects tables via a layout model (RT-DETR v2) and reconstructs cell structure with a configurable table model.

Basic usage

# Markdown tables embedded in the content stream
kreuzberg extract report.pdf --layout --content-format markdown

# Structured JSON output, tables appear under result.tables
kreuzberg extract report.pdf --layout --format json

--layout turns on layout-aware extraction; without it, tables fall back to plain text reflow and you lose cell boundaries.

Output shapes

Two surfaces, picked via --format (CLI shape) and --content-format (content rendering):

• Markdown tables in `content` — --content-format markdown. Tables

appear inline as | col | col | blocks. Good for LLM ingestion.

• Structured `tables` array — --format json. Each entry has

cells[][] (rows × cols), markdown (pre-rendered), page_index, bbox. Use this when downstream code needs exact cell access.

Both are populated at once when --layout is on. The tables array is always structured; the content stream switches representation.

kreuzberg extract financials.pdf --layout --format json \
  | jq '.tables[] | {page: .page_index, rows: (.cells | length)}'

Table models

--layout-table-model picks the reconstruction backend:

kreuzberg extract bank-statement.pdf \
  --layout --layout-table-model tatr --content-format markdown

Drop --layout-confidence when the layout model misses tables (default threshold ~0.5):

kreuzberg extract noisy-scan.pdf --layout --layout-confidence 0.3

Spreadsheets

.xlsx, .ods, .csv, .tsv are extracted by dedicated parsers — no layout model needed. Each sheet becomes a markdown table (or structured table) automatically:

kreuzberg extract workbook.xlsx --content-format markdown
kreuzberg extract data.csv --format json

Pass --no-cache=true only when iterating on the same file with different configs.

Config file alternative

# `output_format` in config files equals `--content-format` on the CLI.
output_format = "markdown"

[layout_detection]
enabled = true
confidence_threshold = 0.5
table_model = "tatr"

Then:

kreuzberg extract report.pdf --format json

Programmatic access

From Python, structured tables live on result.tables:

from kreuzberg import extract_file_sync, ExtractionConfig, LayoutDetectionConfig

config = ExtractionConfig(
    layout_detection=LayoutDetectionConfig(enabled=True, table_model="tatr"),
    output_format="markdown",
)
result = extract_file_sync("report.pdf", config=config)
for table in result.tables:
    print(table.markdown)        # rendered markdown
    print(table.cells[0][0])     # cell access

Node.js mirrors this (extractFile, result.tables, camelCase fields). See references/python-api.md and references/nodejs-api.md in the sibling kreuzberg skill for full type signatures.

Known limitations

• Merged cells — reconstructed as repeated values across the spanned

region; the merge is not preserved as metadata in v0.1.

• Rotated tables — enable --ocr-auto-rotate true for image-based

PDFs before extraction.

• Nested tables — flattened. Detection succeeds; structural nesting is

lost.

• Multi-page tables — each page yields a separate tables[] entry.

Stitch by matching column headers if needed.

• ONNX Runtime required — layout and table models are unavailable in

WASM builds and on the Android x86_64 emulator; native targets ship full support.

Common failure modes

• Empty `tables` with `--layout` on — confidence threshold too high or

table model mismatched. Drop --layout-confidence to 0.3, try --layout-table-model tatr.

• Markdown tables look ragged — switch --layout-table-model to

slanet_wired for bordered grids or slanet_wireless for invoices.

• Slow extraction — tatr is heavy. Use slanet_auto or

slanet_plus as a default; reach for tatr only when accuracy matters.

See references/cli-reference.md for the full layout flag set and references/advanced-features.md for the layout pipeline internals.