Skip to main content

Prototype numeric humanization API built on normalized assets

Project description

Humanumbers

Humanumbers is a Python package for turning rigid numeric text into more natural phrasing without losing the meaning of the original value.

Install

pip install humanumbers

Optional MCP support:

pip install "humanumbers[mcp]"

Basic usage

from humanumbers.service import get_service
from humanumbers.api_models import HumanizeRequest

service = get_service("en")
result = service.humanize(
    HumanizeRequest(
        text="The cable is 1245 mm long.",
        source_language="auto",
        output_language="en",
        mode="humanize",
        approximation="normal",
        system_preference="si",
        variants=3,
    )
)

print(result.model_dump())

Included surfaces

  • Python module: humanumbers
  • CLI entrypoints:
    • humanumbers-api
    • humanumbers-mcp

Requirements

Python 3.12+

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

humanumbers-0.1.0.tar.gz (86.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

humanumbers-0.1.0-py3-none-any.whl (112.5 kB view details)

Uploaded Python 3

File details

Details for the file humanumbers-0.1.0.tar.gz.

File metadata

  • Download URL: humanumbers-0.1.0.tar.gz
  • Upload date:
  • Size: 86.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for humanumbers-0.1.0.tar.gz
Algorithm Hash digest
SHA256 d03f03c8ce924e4fae7d6828f3960db2699e11bb1cb3f6dd2f15130e341ee76c
MD5 3bc907f7f1230dadfb64e136f83d0f7e
BLAKE2b-256 0629ebe1e5deb19d492d364693fe4b50a98f673931705a90c9f6150f0e24ec48

See more details on using hashes here.

File details

Details for the file humanumbers-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: humanumbers-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 112.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for humanumbers-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 a0ccfb844fa68d39dbcdef7029206e5264430bd6a129a69b6d9bcc880885a41c
MD5 50a8597fd9bdf10ec9eae5cdce3211c0
BLAKE2b-256 cacb4f2306c68c79c49dea4e2653dd8f1bec1de10e8fcb4f840c114a99bf3d85

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page