Python SDK

The SDK path is designed for notebooks, scripts, small evaluations, and future bot-driven dictionary checks.

Load a dictionary

from skeinrank import load_dictionary

dictionary = load_dictionary("company_dictionary.json")

Extract canonical values

from skeinrank import extract_terms

result = extract_terms(
    "This runbook describes a k8s rollout backed by pg.",
    dictionary=dictionary,
)

print(result.canonical_values)

Canonicalize text

from skeinrank import canonicalize_text

canonicalized = canonicalize_text(
    "k8s rollout uses pg database",
    dictionary=dictionary,
)

print(canonicalized.text)

Extract from documents

from skeinrank import extract_terms_from_document

result = extract_terms_from_document(
    "incident-runbook.md",
    dictionary=dictionary,
)

print(result.document.file_name)
print(result.extraction.canonical_values)

Public objects

The stable local SDK surface is expected to include:

• Dictionary, DictionaryTerm, DictionaryAlias, DictionaryStopListEntry
• load_dictionary(...)
• validate_dictionary(...)
• extract_terms(...)
• canonicalize_text(...)
• load_document_text(...)
• extract_terms_from_document(...)
• ExtractionResult, TermMatch, CanonicalizedText

Design direction

The SDK should stay deterministic, local, and easy to test. The platform can manage terminology, but runtime extraction should not require a live database query for every request.