Validates text outputs against quality criteria using metrics like BLEU, ROUGE, and semantic similarity. Designed for developers building systems that produce text (chatbots, content generators, summarisation tools) who need automated quality assurance beyond simple string matching.

Status

Under active development. See changelog.md for progress.

Installation

pip install veritext

# With semantic similarity support
pip install veritext[semantic]

Quick Start

from veritext import validators as v
from veritext.core.types import ValidationContext

# Create validators
validator = v.all_of([
    v.bleu(min_score=0.7),
    v.length(max_chars=500),
])

# Validate text
context = ValidationContext(reference="The cat sat on the mat.")
result = validator.check("A cat is sitting on the mat.", context)

if not result.passed:
    print(result.failure_summary)

Documentation

Licence

MIT