# snipsco/snips-nlu

Snips Python library to extract meaning from text

Repository: https://github.com/snipsco/snips-nlu
Canonical: https://ross.abutalabs.com/products/snips-nlu
Homepage: https://snips-nlu.readthedocs.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: nlp, nlu, python, machine-learning, text-classification, intent-classification, ner, named-entity-recognition, slot-filling, intent-parser, information-extraction, snips, machine-learning-library, chatbot, bot, ml
Last push: 2023-05-22T16:10:15+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3493, "days_push": 1199, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3973, forks 506 (observed 2026-08-28T04:08:30.884050+00:00)

## What it is
Snips NLU is a Python library (with a Rust core) that extracts structured meaning from natural language text by detecting user intents and extracting slot parameters. It powers chatbots and voice assistants by turning sentences like 'What will be the weather in Paris at 9pm?' into machine-readable intent and entity data.

## Use cases
- extract intents and slots from user utterances in a chatbot
- build a voice assistant that understands natural language commands
- classify user text into predefined intents
- perform named entity recognition and slot filling on sentences
- parse dates, locations, and other entities from queries
- run an intent parser locally without cloud NLU services

## When to choose
- you need lightweight, on-device or self-hosted NLU for a chatbot or voice assistant
- you want intent classification plus slot extraction in a single Python library
- you need multilingual intent parsing without external API calls

## When to avoid
- you need large transformer-based language understanding or generative LLM capabilities
- you require actively maintained software with frequent updates and community support
- you need state-of-the-art accuracy on complex, open-domain NLU tasks

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, machine-learning, parser
- domain: machine-learning, chatbots
- platform: python, cross-platform, cli
- tags: nlu, intent-classification, named-entity-recognition, slot-filling, voice-assistants, natural-language-processing

## Member repositories
- snipsco/snips-nlu (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:30.884050+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:24:20.892328+00:00, confidence not recorded.
  - readme: https://github.com/snipsco/snips-nlu (fetched 2026-08-28T04:08:30.884050+00:00, sha 90ac50384b90)
  - registry_pypi: https://pypi.org/pypi/snips-nlu/json (fetched 2026-08-29T09:18:14.075932+00:00, sha fc16902ef0a7)
- Data as of 2026-08-30T08:39:29.467469+00:00.