Skip to main content

Tiny wrapper exposing Prompture helpers to convert LLM output into TOON.

Project description

llm-to-toon

Tiny wrapper around prompture that returns TOON (Token-Oriented Object Notation) instead of JSON. Under the hood it uses prompture.extract_and_jsonify(..., output_format="toon") and converts the result into the ultra-compact TOON text automatically.

Install:

pip install llm-to-toon

Usage:

from llm_to_toon import from_llm_text

schema = {"name": "string", "age": "int"}
toon_text = from_llm_text("Name: Juan Age: 30", schema)
print(toon_text)

By default the helper spins up the local Ollama driver (gemma:latest). Pass your own Prompture driver if you want to call OpenAI, Azure, Groq, etc. For the full Prompture feature-set see the main project: https://github.com/jhd3197/prompture

Project details


Release history Release notifications | RSS feed

Download files

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

Source Distribution

llm_to_toon-1.4.0.tar.gz (2.0 kB view details)

Uploaded Source

Built Distribution

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

llm_to_toon-1.4.0-py3-none-any.whl (2.2 kB view details)

Uploaded Python 3

File details

Details for the file llm_to_toon-1.4.0.tar.gz.

File metadata

  • Download URL: llm_to_toon-1.4.0.tar.gz
  • Upload date:
  • Size: 2.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.5

File hashes

Hashes for llm_to_toon-1.4.0.tar.gz
Algorithm Hash digest
SHA256 b383175a06f84194144db8bb7cc57f967ab93d6be841ace76254335319adbacb
MD5 1aab3035af1894955f7e8ddfabfdeb9b
BLAKE2b-256 28bf90879e7923be7789dbf38f82823432c1142763ef37adfaf820d9da34279c

See more details on using hashes here.

File details

Details for the file llm_to_toon-1.4.0-py3-none-any.whl.

File metadata

  • Download URL: llm_to_toon-1.4.0-py3-none-any.whl
  • Upload date:
  • Size: 2.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.5

File hashes

Hashes for llm_to_toon-1.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d7e74a898df5de9e7e83c421581face4ee65f6ddaea71fdfd82b02ecdf8c7a37
MD5 cc9e82a81afc9d9fc3304632e1f23f99
BLAKE2b-256 3f4f77a53a6a6b46fb2141327f975f8b1cd5f79f3de01240452cc326dc0cf65d

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