quantulum3
Extract quantities from unstructured text.
Decision gist · record as of 2026-08-14
Yes. The package is actively maintained, has no known vulnerabilities, installs with low friction, and solves a specific NLP problem (quantity extraction with disambiguation) that is difficult to implement from scratch. MIT licensing removes legal friction. Use it when you need to reliably extract and classify quantities from unstructured text; skip it if you only need simple regex-based number extraction.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.9 or later.
- Optional classifier features require additional dependencies installable via `pip install quantulum3[classifier]`.
- Low friction installation with only two runtime dependencies (inflect and num2words).
License · maintenance · safety
MIT (permissive) — MIT license permits commercial and private use with minimal restrictions—you may use, modify, and distribute the package freely provided you include the license notice.
last release 2026-03-09 (158 days) · last repo commit 2026-05-19 · 150 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 226,851 downloads/mo, #9,194 on PyPI
Alternatives
Verify before relying
pip install quantulum3
from quantulum3 import parser
quants = parser.parse('I want 2 liters of wine')
print(quants[0].value, quants[0].unit.name)- Whether the GloVe vector representation and Wikipedia disambiguation data are bundled or downloaded on first use, and what network/storage requirements that entails.
- Performance characteristics on large documents or real-time parsing scenarios.
- How well the parser handles domain-specific or non-English quantities.
- Typical accuracy and precision of the disambiguation classifier on real-world text.
What it is and what it does
Quantulum3 is a Python library that identifies and extracts numeric quantities and their units from plain text. It parses both standard units (litre, kilogram, terawatt) and spelled-out numbers, ranges, and uncertainties, then reconciles them against Wikipedia to determine their entity type (volume, mass, energy, etc.). When multiple units could match the same text, it uses a classifier trained on GloVe word vectors and Wikipedia context to disambiguate—for example, distinguishing currency from weight based on surrounding words.
The library returns Quantity objects containing the parsed value, unit name, entity classification, and span positions in the original text. It also supports inline parsing for debugging, export to JSON or dictionaries, and conversion to spoken form. Two lightweight runtime dependencies (inflect and num2words) handle number inflection and text-to-speech conversion. Optional classifier training is available for custom models.
Use it for
- Parse scientific or technical documents to identify measurements and their units for indexing or validation.
- Disambiguate currency amounts from weight or distance in mixed-domain text.
- Build a dimensionless number extractor for cases where only numeric values matter.
- Convert measurement text to structured data for downstream unit conversion or comparison.
- Extract and classify quantities from product descriptions or technical specifications.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The package is actively maintained, has no known vulnerabilities, installs with low friction, and solves a specific NLP problem (quantity extraction with disambiguation) that is difficult to implement from scratch. MIT licensing removes legal friction. Use it when you need to reliably extract and classify quantities from unstructured text; skip it if you only need simple regex-based number extraction.
Install
quantulum3 on PyPI
Before you install
Low friction installation with only two runtime dependencies (inflect and num2words). Active maintenance with recent releases; last commit 2026-05-19. Supports Python 3.9 through 3.13.
Requires Python 3.9 or later. Optional classifier features require additional dependencies installable via `pip install quantulum3[classifier]`.
License in practice
MIT license permits commercial and private use with minimal restrictions—you may use, modify, and distribute the package freely provided you include the license notice.
Quickstart
pip install quantulum3
from quantulum3 import parser
quants = parser.parse('I want 2 liters of wine')
print(quants[0].value, quants[0].unit.name)Verify before relying
- Whether the GloVe vector representation and Wikipedia disambiguation data are bundled or downloaded on first use, and what network/storage requirements that entails.
- Performance characteristics on large documents or real-time parsing scenarios.
- How well the parser handles domain-specific or non-English quantities.
- Typical accuracy and precision of the disambiguation classifier on real-world text.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 2 packagesinflectnum2words |
| Maintenance | Actively maintained 158 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 226,851 / month, #9,194 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 3 - AlphaIntended Audience :: DevelopersIntended Audience :: Science/ResearchNatural Language :: EnglishOperating System :: MacOS :: MacOS XOperating System :: Microsoft :: WindowsOperating System :: POSIXProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.9Topic :: Scientific/EngineeringTopic :: Text Processing :: Linguistic |
Evidence: quantulum3-0.10.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “extract quantities from text”
- quantulum3Extracts quantities, measurements, and their units from unstructured…
- recognizers-text-number-with-unitRecognizes and extracts numbers with units (age, currency,…
- quantitiesQuantities handles arithmetic and unit conversions for physical…
Give your agent the search over MCP, or paste the wish link into any chat.
More Scientific/Engineering packages
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
pandas provides fast, flexible data structures (Series and DataFrame) for loading, cleaning, transforming, and analyzing labeled or relational data in Python.
scipy provides numerical algorithms for mathematics, science, and engineering—including optimization, integration, linear algebra, Fourier transforms, signal and image processing, and ODE solvers—built on numpy arrays.
scikit-learn provides a comprehensive Python library for supervised and unsupervised machine learning, including classification, regression, clustering, dimensionality reduction, and model evaluation tools built on NumPy and SciPy.
Install it if you need to train, evaluate, or deploy supervised or unsupervised learning models.
dill extends Python's pickle module to serialize and deserialize a much wider range of Python objects, including functions, lambdas, classes, and interpreter sessions, to byte streams for storage or network transmission.
Multiprocess is an enhanced fork of Python's standard multiprocessing library that uses dill for better serialization, allowing you to spawn processes with a threading-like API and share complex objects between them.
Install it if you use multiprocessing and encounter pickle serialization limits with lambdas or complex objects.
See also recognizers-text-number-with-unit · quantities · recognizers-text-number · recognizers-text · recognizers-text-choice · unyt · textacy · gliner · langextract · Pint