LICENSE
README.md
pyproject.toml
src/langcheck/__init__.py
src/langcheck/_handle_logs.py
src/langcheck/stats.py
src/langcheck.egg-info/PKG-INFO
src/langcheck.egg-info/SOURCES.txt
src/langcheck.egg-info/dependency_links.txt
src/langcheck.egg-info/requires.txt
src/langcheck.egg-info/top_level.txt
src/langcheck/augment/__init__.py
src/langcheck/augment/_common/_jailbreak_template.py
src/langcheck/augment/_common/_payload_splitting.py
src/langcheck/augment/en/__init__.py
src/langcheck/augment/en/_change_case.py
src/langcheck/augment/en/_jailbreak_template.py
src/langcheck/augment/en/_keyboard_typo.py
src/langcheck/augment/en/_ocr_typo.py
src/langcheck/augment/en/_payload_splitting.py
src/langcheck/augment/en/_remove_punctuation.py
src/langcheck/augment/en/_rephrase.py
src/langcheck/augment/en/_rephrase_with_system_role_context.py
src/langcheck/augment/en/_rephrase_with_user_role_context.py
src/langcheck/augment/en/_synonym.py
src/langcheck/augment/en/_to_full_width.py
src/langcheck/augment/en/_gender/__init__.py
src/langcheck/augment/en/_gender/_gender.py
src/langcheck/augment/en/_gender/_gender_pronouns.py
src/langcheck/augment/ja/__init__.py
src/langcheck/augment/ja/_conv_kana.py
src/langcheck/augment/ja/_jailbreak_template.py
src/langcheck/augment/ja/_payload_splitting.py
src/langcheck/augment/ja/_rephrase_with_system_role_context.py
src/langcheck/augment/ja/_rephrase_with_user_role_context.py
src/langcheck/augment/ja/_synonym.py
src/langcheck/metrics/__init__.py
src/langcheck/metrics/_pairwise_text_quality_utils.py
src/langcheck/metrics/custom_text_quality.py
src/langcheck/metrics/metric_inputs.py
src/langcheck/metrics/metric_value.py
src/langcheck/metrics/reference_based_text_quality.py
src/langcheck/metrics/text_structure.py
src/langcheck/metrics/de/__init__.py
src/langcheck/metrics/de/_tokenizers.py
src/langcheck/metrics/de/_translation.py
src/langcheck/metrics/de/query_based_text_quality.py
src/langcheck/metrics/de/reference_based_text_quality.py
src/langcheck/metrics/de/reference_free_text_quality.py
src/langcheck/metrics/de/source_based_text_quality.py
src/langcheck/metrics/en/__init__.py
src/langcheck/metrics/en/pairwise_text_quality.py
src/langcheck/metrics/en/query_based_text_quality.py
src/langcheck/metrics/en/reference_based_text_quality.py
src/langcheck/metrics/en/reference_free_text_quality.py
src/langcheck/metrics/en/source_based_text_quality.py
src/langcheck/metrics/eval_clients/__init__.py
src/langcheck/metrics/eval_clients/_anthropic.py
src/langcheck/metrics/eval_clients/_base.py
src/langcheck/metrics/eval_clients/_gemini.py
src/langcheck/metrics/eval_clients/_litellm.py
src/langcheck/metrics/eval_clients/_llama.py
src/langcheck/metrics/eval_clients/_openai.py
src/langcheck/metrics/eval_clients/_openrouter.py
src/langcheck/metrics/eval_clients/_prometheus.py
src/langcheck/metrics/eval_clients/extractor/__init__.py
src/langcheck/metrics/eval_clients/extractor/_base.py
src/langcheck/metrics/eval_clients/extractor/string_match_extractor.py
src/langcheck/metrics/ja/__init__.py
src/langcheck/metrics/ja/_tokenizers.py
src/langcheck/metrics/ja/pairwise_text_quality.py
src/langcheck/metrics/ja/query_based_text_quality.py
src/langcheck/metrics/ja/reference_based_text_quality.py
src/langcheck/metrics/ja/reference_free_text_quality.py
src/langcheck/metrics/ja/source_based_text_quality.py
src/langcheck/metrics/model_manager/__init__.py
src/langcheck/metrics/model_manager/_model_loader.py
src/langcheck/metrics/model_manager/_model_management.py
src/langcheck/metrics/model_manager/config/metric_config.yaml
src/langcheck/metrics/prompts/_utils.py
src/langcheck/metrics/prompts/de/get_score/plain_text.j2
src/langcheck/metrics/prompts/de/get_score/structured_output.j2
src/langcheck/metrics/prompts/de/metrics/answer_relevance.j2
src/langcheck/metrics/prompts/de/metrics/context_relevance.j2
src/langcheck/metrics/prompts/de/metrics/factual_consistency.j2
src/langcheck/metrics/prompts/de/metrics/fluency.j2
src/langcheck/metrics/prompts/de/metrics/sentiment.j2
src/langcheck/metrics/prompts/de/metrics/toxicity.j2
src/langcheck/metrics/prompts/en/confidence_estimating/simulated_annotators.j2
src/langcheck/metrics/prompts/en/get_score/plain_text.j2
src/langcheck/metrics/prompts/en/get_score/structured_output.j2
src/langcheck/metrics/prompts/en/jailbreak_templates/basic.j2
src/langcheck/metrics/prompts/en/jailbreak_templates/chatgpt_dan.j2
src/langcheck/metrics/prompts/en/jailbreak_templates/chatgpt_good_vs_evil.j2
src/langcheck/metrics/prompts/en/jailbreak_templates/john.j2
src/langcheck/metrics/prompts/en/jailbreak_templates/universal_adversarial_suffix.j2
src/langcheck/metrics/prompts/en/metrics/adult_content.j2
src/langcheck/metrics/prompts/en/metrics/answer_correctness.j2
src/langcheck/metrics/prompts/en/metrics/answer_relevance.j2
src/langcheck/metrics/prompts/en/metrics/answer_safety.j2
src/langcheck/metrics/prompts/en/metrics/context_relevance.j2
src/langcheck/metrics/prompts/en/metrics/factual_consistency.j2
src/langcheck/metrics/prompts/en/metrics/fluency.j2
src/langcheck/metrics/prompts/en/metrics/harmful_activity.j2
src/langcheck/metrics/prompts/en/metrics/hate_speech.j2
src/langcheck/metrics/prompts/en/metrics/jailbreak_prompt.j2
src/langcheck/metrics/prompts/en/metrics/pairwise_comparison.j2
src/langcheck/metrics/prompts/en/metrics/personal_data_leakage.j2
src/langcheck/metrics/prompts/en/metrics/prompt_leakage_v1.j2
src/langcheck/metrics/prompts/en/metrics/prompt_leakage_v2.j2
src/langcheck/metrics/prompts/en/metrics/rephrase_v1.j2
src/langcheck/metrics/prompts/en/metrics/rephrase_v2.j2
src/langcheck/metrics/prompts/en/metrics/rephrase_with_system_role_context.j2
src/langcheck/metrics/prompts/en/metrics/rephrase_with_user_role_context.j2
src/langcheck/metrics/prompts/en/metrics/sentiment.j2
src/langcheck/metrics/prompts/en/metrics/summarization_quality.j2
src/langcheck/metrics/prompts/en/metrics/system_prompt_adherence.j2
src/langcheck/metrics/prompts/en/metrics/toxicity_v1.j2
src/langcheck/metrics/prompts/en/metrics/toxicity_v2.j2
src/langcheck/metrics/prompts/en/metrics/user_frustration.j2
src/langcheck/metrics/prompts/en/metrics/prometheus/answer_relevance.j2
src/langcheck/metrics/prompts/en/metrics/prometheus/context_relevance.j2
src/langcheck/metrics/prompts/en/metrics/prometheus/factual_consistency.j2
src/langcheck/metrics/prompts/en/metrics/prometheus/fluency.j2
src/langcheck/metrics/prompts/en/metrics/prometheus/pairwise_comparison.j2
src/langcheck/metrics/prompts/en/metrics/prometheus/sentiment.j2
src/langcheck/metrics/prompts/en/metrics/prometheus/toxicity_v1.j2
src/langcheck/metrics/prompts/en/metrics/prometheus/toxicity_v2.j2
src/langcheck/metrics/prompts/en/payload_splitting/smartgpt.j2
src/langcheck/metrics/prompts/ja/get_score/plain_text.j2
src/langcheck/metrics/prompts/ja/get_score/structured_output.j2
src/langcheck/metrics/prompts/ja/jailbreak_templates/basic.j2
src/langcheck/metrics/prompts/ja/jailbreak_templates/chatgpt_good_vs_evil.j2
src/langcheck/metrics/prompts/ja/jailbreak_templates/john.j2
src/langcheck/metrics/prompts/ja/metrics/adult_content.j2
src/langcheck/metrics/prompts/ja/metrics/answer_correctness.j2
src/langcheck/metrics/prompts/ja/metrics/answer_relevance.j2
src/langcheck/metrics/prompts/ja/metrics/answer_safety.j2
src/langcheck/metrics/prompts/ja/metrics/context_relevance.j2
src/langcheck/metrics/prompts/ja/metrics/factual_consistency.j2
src/langcheck/metrics/prompts/ja/metrics/fluency.j2
src/langcheck/metrics/prompts/ja/metrics/harmful_activity.j2
src/langcheck/metrics/prompts/ja/metrics/hate_speech.j2
src/langcheck/metrics/prompts/ja/metrics/jailbreak_prompt.j2
src/langcheck/metrics/prompts/ja/metrics/pairwise_comparison.j2
src/langcheck/metrics/prompts/ja/metrics/personal_data_leakage.j2
src/langcheck/metrics/prompts/ja/metrics/prompt_leakage_v1.j2
src/langcheck/metrics/prompts/ja/metrics/prompt_leakage_v2.j2
src/langcheck/metrics/prompts/ja/metrics/rephrase_with_system_role_context.j2
src/langcheck/metrics/prompts/ja/metrics/rephrase_with_user_role_context.j2
src/langcheck/metrics/prompts/ja/metrics/sentiment.j2
src/langcheck/metrics/prompts/ja/metrics/summarization_quality.j2
src/langcheck/metrics/prompts/ja/metrics/system_prompt_adherence.j2
src/langcheck/metrics/prompts/ja/metrics/toxicity_v1.j2
src/langcheck/metrics/prompts/ja/metrics/toxicity_v2.j2
src/langcheck/metrics/prompts/ja/metrics/user_frustration.j2
src/langcheck/metrics/prompts/ja/payload_splitting/smartgpt.j2
src/langcheck/metrics/scorer/_base.py
src/langcheck/metrics/scorer/detoxify_models.py
src/langcheck/metrics/scorer/hf_models.py
src/langcheck/metrics/zh/__init__.py
src/langcheck/metrics/zh/_tokenizers.py
src/langcheck/metrics/zh/reference_based_text_quality.py
src/langcheck/metrics/zh/reference_free_text_quality.py
src/langcheck/metrics/zh/source_based_text_quality.py
src/langcheck/plot/__init__.py
src/langcheck/plot/_css.py
src/langcheck/plot/_histogram.py
src/langcheck/plot/_scatter.py
src/langcheck/plot/_utils.py
src/langcheck/utils/__init__.py
src/langcheck/utils/io.py
src/langcheck/utils/progress_bar.py
tests/test_stats.py