---
title: "onenlp cookbook"
url: https://recursiveai.org/onenlp/cookbook/
description: "Short recipes for common OneNLP tasks, each with complete code you can copy."
version: "1.0.0"
---

# onenlp cookbook

Short recipes for common OneNLP tasks, each with complete code you can copy.

## Text processing

- [Detect the language of text in C#](https://recursiveai.org/onenlp/cookbook/language-detection/index.md): Identify a string’s language locally with the model included in OneNLP.
- [Named entity recognition in C#](https://recursiveai.org/onenlp/cookbook/named-entity-recognition/index.md): Find names of people and places with OneNLP’s packaged English model.
- [Tokenize text in C#](https://recursiveai.org/onenlp/cookbook/tokenize-text/index.md): Split prose into words and punctuation, not language-model token IDs.
- [Split text into sentences in C#](https://recursiveai.org/onenlp/cookbook/split-sentences/index.md): Split sentences with Unicode rules and language-specific abbreviation data.
- [Lemmatize text in C#](https://recursiveai.org/onenlp/cookbook/lemmatize-text/index.md): Get dictionary forms such as “run” for “running” with the English model.

## Analyze text

- [Part-of-speech tagging in C#](https://recursiveai.org/onenlp/cookbook/part-of-speech-tagging/index.md): Label English words as nouns, verbs and other parts of speech.
- [Dependency parsing in C#](https://recursiveai.org/onenlp/cookbook/dependency-parsing/index.md): Link words to their grammatical heads to find subjects and modifiers.
- [Generate sentence embeddings in C#](https://recursiveai.org/onenlp/cookbook/sentence-embeddings/index.md): Turn sentences into numeric vectors for similarity and search, locally.
- [Extract dates and numbers from text in C#](https://recursiveai.org/onenlp/cookbook/extract-dates-and-numbers/index.md): Extract dates and written numbers; resolve “tomorrow” against a reference date.
- [Train a text classifier in C#](https://recursiveai.org/onenlp/cookbook/text-classification/index.md): Train a classifier to label text, using two tiny demonstration examples.