nl-processing 0.2.1

Natural language processing playground

nl_processing

Dutch language processing toolkit powered by LangChain + OpenAI.

Installation

pip install nl_processing

Modules

Module	Class	Description	Docs
extract_text_from_image	ImageTextExtractor	Extract Dutch text from images via Vision API	docs
extract_words_from_text	WordExtractor	Extract and normalize words from markdown text	docs
translate_text	TextTranslator	Translate text (NL → RU) with markdown preservation	docs
translate_word	WordTranslator	Batch-translate words (NL → RU)	docs
database	DatabaseService	Persist words and translations to Neon PostgreSQL	docs
sampling	WordSampler	Weighted word sampling with adversarial distractors	docs

Each module's docs/ folder contains a product brief, PRD, and architecture doc.

Development

uv sync                # install dependencies
make check             # full lint + test pipeline
uv run pytest tests/unit   # unit tests only (free, no API key)

See docs/ENV_VARS.md for required environment variables and NEON.md for database setup.