AGENT SKILL

pipeline-configuration

Configure Docling's standard PDF pipeline options, OCR engines, table structure recovery, accelerators, model artifacts, remote-service gates, and option validation.

License 许可
MIT
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
pipeline-configuration
license
MIT
metadata
{ "disco-role": "operating" }
description
Configure Docling's standard PDF pipeline options, OCR engines, table structure recovery, accelerators, model artifacts, remote-service gates, and option validation.
disable-model-invocation
true

02 资源文件 4

03 SKILL.md 正文

Pipeline Configuration

Use this sub-skill when a task needs Docling PDF pipeline tuning rather than a simple conversion call.

Route Here For

  • Building PdfPipelineOptions or ThreadedPdfPipelineOptions for InputFormat.PDF.
  • Enabling/disabling OCR, choosing OCR engines, setting OCR language lists, or forcing full-page OCR.
  • Tuning table structure extraction, especially do_cell_matching and TableFormerMode.
  • Selecting AcceleratorOptions device/thread settings for CPU, CUDA, MPS, or XPU.
  • Setting artifacts_path, DOCLING_ARTIFACTS_PATH, or docling-tools models download for prefetched model caches.
  • Diagnosing pipeline option validation, wrong option object placement, or OperationNotAllowed from remote-service components.

Route Elsewhere

  • Basic document conversion, export formats, DocumentConverter.convert, or convert_string: use the conversion sub-skill.
  • CLI flag syntax and supported input/output formats: use the cli-and-formats sub-skill.
  • VLM, ASR, picture enrichment, code/formula, chart extraction, or other heavy enrichment workflows: use the advanced-pipelines sub-skill.

Core Pattern

from docling.datamodel.accelerator_options import AcceleratorDevice, AcceleratorOptions
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions, TableFormerMode
from docling.document_converter import DocumentConverter, PdfFormatOption

pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = True
pipeline_options.ocr_options.lang = ["en"]
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = False
pipeline_options.table_structure_options.mode = TableFormerMode.ACCURATE
pipeline_options.accelerator_options = AcceleratorOptions(
    num_threads=4,
    device=AcceleratorDevice.AUTO,
)

converter = DocumentConverter(
    format_options={
        InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
    }
)
result = converter.convert("input.pdf", max_num_pages=100, max_file_size=20 * 1024 * 1024)

References

  • references/options-reference.md for field names, defaults, and validated snippets.
  • references/ocr-and-tables.md for OCR engines and table recovery choices.
  • references/troubleshooting.md for common pipeline failures and fixes.
  • scripts/inspect_pipeline_options.py to print installed option fields/defaults without opening source files.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351