Skip to main content

fabricatio-judge extends the Fabricatio ecosystem to provide advanced judgment capabilities for LLM-driven applications.

Project description

fabricatio-judge

A Python module for evidence-based decision making in LLM applications.

📦 Installation

This package is part of the fabricatio monorepo and can be installed as an optional dependency:

pip install fabricatio[judge]

Or install all components:

pip install fabricatio[full]

🔍 Overview

Provides the AdvancedJudge class for structured judgment tasks, using collected evidence to determine a final boolean verdict.

Key Features:

  • Asynchronous judgment execution
  • Evidence tracking (affirmative & denying)
  • Integration with Fabricatio agent framework
  • Extensible for custom logic

🧩 Usage

from fabricatio.capabilities import AdvancedJudge
from fabricatio.models import JudgeMent


class MyJudge(AdvancedJudge):
    pass  # Implement custom logic if needed


async def evaluate():
    judge = MyJudge()
    result: JudgeMent = await judge.evidently_judge("Is water wet?")
    print(f"Verdict: {result.final_judgement}")

📁 Structure

fabricatio-judge/
├── capabilities/     - Judgment logic (`AdvancedJudge`)
└── models/           - Judgment output model (`JudgeMent`)

📄 License

MIT – see LICENSE

GitHub: github.com/Whth/fabricatio

Project details


Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

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

fabricatio_judge-0.1.3.dev1-py3-none-any.whl (4.9 kB view details)

Uploaded Python 3

File details

Details for the file fabricatio_judge-0.1.3.dev1-py3-none-any.whl.

File metadata

File hashes

Hashes for fabricatio_judge-0.1.3.dev1-py3-none-any.whl
Algorithm Hash digest
SHA256 fc7b5e528c8a473526817e426b75101a02625ff261bff552d18a2551450af633
MD5 e4e0151bc0b6171006ce0be993d18bd6
BLAKE2b-256 71bd7b574e482c6865605ce40b6cc7f354073738b536b59d1cd3c12779284016

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