documents-and-visualization
Work with spaCy Doc, Token, Span, DocBin, tokenization, matchers, serialization, scoring, and displaCy visualization.
- License 许可
- MIT
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- documents-and-visualization
- license
- MIT
- metadata
- { "disco-role": "operating" }
- description
- Work with spaCy Doc, Token, Span, DocBin, tokenization, matchers, serialization, scoring, and displaCy visualization.
- disable-model-invocation
- true
02 资源文件 7
- 参考文档references/doc-token-span-api.md2.7 KB
- 参考文档references/matching-and-rulers.md7.1 KB
- 参考文档references/serialization-scoring-visualization.md5.1 KB
- 参考文档references/tokenization-language-data.md5.8 KB
- 参考文档references/troubleshooting.md3.8 KB
- 脚本scripts/doc_api_smoke.py9.4 KB
- 脚本scripts/render_displacy_sample.py4.7 KB
03 SKILL.md 正文
documents-and-visualization
Use this sub-skill for the core spaCy document model: tokenization, Doc/Token/Span APIs, DocBin serialization, rule-based matching, EntityRuler/SpanRuler, scoring, and displaCy HTML rendering.
Read first
- references/doc-token-span-api.md for verified signatures and object-model details.
- references/tokenization-language-data.md for blank pipelines, language classes, and tokenizer customization.
- references/matching-and-rulers.md for
Matcher,PhraseMatcher,DependencyMatcher,EntityRuler, andSpanRuler. - references/serialization-scoring-visualization.md for
DocBin, scoring, and displaCy output patterns. - references/troubleshooting.md when span offsets, matcher patterns, serialization, or HTML rendering go wrong.
- scripts/doc_api_smoke.py for a safe blank-pipeline smoke that exercises the object model and matcher basics.
- scripts/render_displacy_sample.py for a tiny manual HTML render check.
What this sub-skill covers
spacy.blank()andspacy.load()for processing text with an existing package or local pipeline.nlp(text)andnlp.pipe()for document streaming andas_tuplescontext.Doc,Token,Span, extension attributes,char_span,retokenize, andDocBinround-trips.- Tokenizer behavior, language data, and blank-language caveats.
- Rule-based matching and entity/span rulers for token-pattern workflows.
- displaCy rendering for entities, dependencies, and spans.
What to route elsewhere
- Install/import, version, CLI entry-point, missing model package, or backend questions:
install-and-inspect. - Custom pipeline factories/components,
add_pipe, registry wiring, or pipe analysis:pipeline-components. init config,debug config,convert,train,evaluate,package, orvalidate:training-and-cli.spacy projectclone/assets/run/push/pull/DVC workflows:project-workflows.
Quick use pattern
- Start from the object you need:
Doc,Span,Token, matcher, ruler, or displacy. - Check the exact signature in the reference before assuming optional parameters.
- Run the bundled smoke script if you need a safe no-download proof of behavior.
- Use the troubleshooting reference when offsets, tokenization, or serialized artifacts do not line up.
Evidence basis
This sub-skill is distilled from spaCy's public docs, verified installed-package signatures, core token/matcher/serialization source, and behavior-backed tests. It is self-contained and does not require reopening the source checkout.
04 同仓库更多 Skills
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.
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.
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.
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.
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.
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).