Skip to main content

LLM-powered automated data labeling with schema-first, confidence-scored, and local-model ready

Project description

Tagnify

LLM-powered automated data labeling — schema-first, confidence-scored, local-model ready.

from tagnify import Tagnify, Schema, Example

schema = Schema(
    labels=["positive", "negative", "neutral"],
    examples=[Example(text="Great product!", label="positive")]
)

tagnify = Tagnify(model="qwen2.5:7b")
result = tagnify.label("This was a disappointing experience.", schema)

print(result.label)       # "negative"
print(result.confidence)  # 0.91

Installation

pip install tagnify

Requires Ollama running locally.

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

tagnify-0.1.0.tar.gz (19.3 kB view details)

Uploaded Source

Built Distribution

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

tagnify-0.1.0-py3-none-any.whl (11.1 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: tagnify-0.1.0.tar.gz
  • Upload date:
  • Size: 19.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tagnify-0.1.0.tar.gz
Algorithm Hash digest
SHA256 c7e11746c3907bd967848dbac2e3a0fc423ab9fdb128fa4968b4ef3991144737
MD5 3a39d13dd56849b623807984c1ff609b
BLAKE2b-256 8fc8974b8643daf0e9b663556d7f2d968d9f51503c983f535d635c2c34463157

See more details on using hashes here.

Provenance

The following attestation bundles were made for tagnify-0.1.0.tar.gz:

Publisher: publish.yml on MaulanaArya30/tagnify

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

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

File metadata

  • Download URL: tagnify-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 11.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tagnify-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 cb853b98b3a5c5ca84b2ae9a4bb113d0e8912db3567e091c356431c41e086731
MD5 97d0ccc5db08f321a63391380a7901a5
BLAKE2b-256 80e03d4606a22190884271713a564568d427a620fd98b59f8433844b7607f0f1

See more details on using hashes here.

Provenance

The following attestation bundles were made for tagnify-0.1.0-py3-none-any.whl:

Publisher: publish.yml on MaulanaArya30/tagnify

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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