OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Articutapi

Articutapi is a Python API for Chinese word segmentation and part-of-speech tagging. Its repository describes segmentation based on modern written Chinese grammar rules rather than statistical or machine-learning methods, and provides online HTTP and Docker-based processing variants.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Articutapi — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Articutapi when a software pipeline needs Chinese segmentation and tagged output, and choose the HTTP, Docker multiprocessing or Docker WebSocket pattern according to the documented processing scenario.

Who it is for

  • Developers adding Chinese segmentation and tags to text-processing pipelines.
  • Teams processing Chinese text in batches through a Docker multiprocessing variant.
  • Builders of real-time chatbot text analysis using the Docker WebSocket variant.

Documented uses

  • Split Chinese text into words or meaningful word groups.
  • Annotate Chinese text with part-of-speech and semantic-role tags.
  • Extract content words, verbs, nouns or location terms from parse results.
  • Apply a user-defined dictionary to influence handling of selected terms.
  • Select finer or phrase-level segmentation for downstream language tasks.
Before you choose

Requirements & limits

The repository's Python example says empty account-email and API-key strings use a public allowance of 2,000 characters per hour. It also shows authenticated use with an account email and API key.

  • The segmentation is described as grammar-rule-based, not statistical or machine-learning-based.
  • The repository distinguishes online HTTP use, Docker multiprocessing for batch processing and Docker WebSocket processing for real-time use.
  • The documented levels differ in granularity: lv1 splits more finely; lv2 returns meaningful minimum units.
  • The user-defined dictionary is relevant when desired vocabulary handling goes beyond Articut's language knowledge.
  • The repository lists Python as the implementation language and an MIT license.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Apply a user-defined dictionary during parsing

Add user-specified vocabulary to a parse using the documented dictionary-file option.

Before you start

  • ArticutAPI Python package and a parseable text input.
  • A user-authored dictionary file in the shown JSON dictionary format.

Steps

  1. Create a JSON dictionary mapping preferred terms to associated entries, following the repository's example.

  2. Initialize the Articut client and set the dictionary-file path.

  3. Pass the path as userDefinedDictFILE to articut.parse().

Expected outcome

The returned segmentation and tags can mark entries supplied through the user-defined dictionary.

Guide limitations

  • The dictionary is user-authored; the repository describes this feature as a way to handle vocabulary beyond the language knowledge Articut processes.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
Droidtown/ArticutAPI · Official homepage title · retained in its source language
How we review sourcesSuggest a correction