CHANGELOG.md
LICENSE
MANIFEST.in
README.md
pyproject.toml
eic_model_evaluation.egg-info/PKG-INFO
eic_model_evaluation.egg-info/SOURCES.txt
eic_model_evaluation.egg-info/dependency_links.txt
eic_model_evaluation.egg-info/requires.txt
eic_model_evaluation.egg-info/top_level.txt
model_evaluation/__init__.py
model_evaluation/connectors/__init__.py
model_evaluation/connectors/base.py
model_evaluation/connectors/exceptions.py
model_evaluation/connectors/factory.py
model_evaluation/connectors/managed/__init__.py
model_evaluation/connectors/managed/base_managed.py
model_evaluation/connectors/managed/vertex_rag.py
model_evaluation/connectors/mixins/__init__.py
model_evaluation/connectors/mixins/langchain_mixin.py
model_evaluation/connectors/rag/__init__.py
model_evaluation/connectors/rag/base_rag.py
model_evaluation/connectors/rag/simple_rag.py
model_evaluation/connectors/standard/__init__.py
model_evaluation/connectors/standard/anthropic.py
model_evaluation/connectors/standard/base_llm.py
model_evaluation/connectors/standard/groq.py
model_evaluation/connectors/standard/openai.py
model_evaluation/connectors/standard/together.py
model_evaluation/connectors/standard/vertex.py
model_evaluation/connectors/vectorstores/__init__.py
model_evaluation/connectors/vectorstores/base.py
model_evaluation/connectors/vectorstores/chroma.py
model_evaluation/connectors/vectorstores/faiss.py
model_evaluation/connectors/vectorstores/remote.py
model_evaluation/costs/__init__.py
model_evaluation/costs/config.py
model_evaluation/costs/core/__init__.py
model_evaluation/costs/core/estimator.py
model_evaluation/costs/core/pricing.py
model_evaluation/costs/core/tracker.py
model_evaluation/costs/models/__init__.py
model_evaluation/costs/models/schema.py
model_evaluation/costs/utils/__init__.py
model_evaluation/costs/utils/format.py
model_evaluation/evaluation/__init__.py
model_evaluation/evaluation/runner.py
model_evaluation/evaluation/components/__init__.py
model_evaluation/evaluation/components/metric_factory.py
model_evaluation/evaluation/components/result_aggregator.py
model_evaluation/evaluation/components/validator.py
model_evaluation/evaluation/core/__init__.py
model_evaluation/evaluation/core/comparator.py
model_evaluation/evaluation/core/engine.py
model_evaluation/evaluation/core/exceptions.py
model_evaluation/evaluation/core/executor.py
model_evaluation/evaluation/core/schema.py
model_evaluation/generation/__init__.py
model_evaluation/generation/components/__init__.py
model_evaluation/generation/components/detectors.py
model_evaluation/generation/components/loaders.py
model_evaluation/generation/components/parsers.py
model_evaluation/generation/components/selectors.py
model_evaluation/generation/components/splitters.py
model_evaluation/generation/core/__init__.py
model_evaluation/generation/core/config.py
model_evaluation/generation/core/datasets.py
model_evaluation/generation/core/exceptions.py
model_evaluation/generation/core/schema.py
model_evaluation/generation/validation/__init__.py
model_evaluation/generation/validation/base.py
model_evaluation/generation/validation/validators.py
model_evaluation/metrics/__init__.py
model_evaluation/metrics/base.py
model_evaluation/metrics/exceptions.py
model_evaluation/metrics/registry.py
model_evaluation/metrics/llm_judge/__init__.py
model_evaluation/metrics/llm_judge/answer_relevance.py
model_evaluation/metrics/llm_judge/base_llm_judge.py
model_evaluation/metrics/llm_judge/compliance.py
model_evaluation/metrics/llm_judge/conciseness.py
model_evaluation/metrics/llm_judge/custom_criteria.py
model_evaluation/metrics/llm_judge/factual.py
model_evaluation/metrics/llm_judge/faithfulness.py
model_evaluation/metrics/llm_judge/logical_consistency.py
model_evaluation/metrics/llm_judge/toxicity.py
model_evaluation/metrics/mixins/__init__.py
model_evaluation/metrics/mixins/llm_judge_mixin.py
model_evaluation/metrics/retrieval/__init__.py
model_evaluation/metrics/retrieval/base_retrieval.py
model_evaluation/metrics/retrieval/ndcg.py
model_evaluation/metrics/retrieval/precision.py
model_evaluation/metrics/retrieval/recall.py
model_evaluation/metrics/similarity/__init__.py
model_evaluation/metrics/similarity/codebleu.py
model_evaluation/metrics/similarity/determinism.py
model_evaluation/metrics/similarity/semantic.py
model_evaluation/reporting/__init__.py
model_evaluation/reporting/data_formatter.py
model_evaluation/reporting/generator.py
model_evaluation/reporting/narrative_reporter.py
model_evaluation/reporting/formats/__init__.py
model_evaluation/reporting/formats/base.py
model_evaluation/reporting/formats/csv_format.py
model_evaluation/reporting/formats/json_format.py
model_evaluation/reporting/formats/markdown_format.py
model_evaluation/reporting/templates/__init__.py
model_evaluation/reporting/templates/base.py
model_evaluation/reporting/templates/builtin.py
model_evaluation/ui/__init__.py
model_evaluation/ui/app.py
model_evaluation/ui/components/__init__.py
model_evaluation/ui/components/cost_display.py
model_evaluation/ui/components/dataset_preview.py
model_evaluation/ui/components/metrics_selector.py
model_evaluation/ui/components/model_selector.py
model_evaluation/ui/components/results_table.py
model_evaluation/ui/state/__init__.py
model_evaluation/ui/state/session_state.py
model_evaluation/ui/tabs/__init__.py
model_evaluation/ui/tabs/comparison_tab.py
model_evaluation/ui/tabs/config_tab.py
model_evaluation/ui/tabs/evaluation_tab.py
model_evaluation/ui/tabs/generation_tab.py
model_evaluation/ui/tabs/results_tab.py
model_evaluation/utils/__init__.py
model_evaluation/utils/parsing.py
model_evaluation/utils/prompts.py
model_evaluation/utils/providers.py
tests/test_connectors_base.py
tests/test_connectors_factory.py
tests/test_connectors_managed.py
tests/test_connectors_mixins_backends.py
tests/test_connectors_rag.py
tests/test_connectors_standard.py
tests/test_connectors_vectorstores.py
tests/test_costs_estimator.py
tests/test_costs_pricing.py
tests/test_costs_tracker.py
tests/test_evaluation_components.py
tests/test_evaluation_executor.py
tests/test_generation_components.py
tests/test_generation_dataset_generator.py
tests/test_generation_loaders.py
tests/test_generation_validation.py
tests/test_metrics_registry.py
tests/test_metrics_retrieval.py
tests/test_reporting_data_formatter.py
tests/test_reporting_formats.py
tests/test_reporting_generator.py
tests/test_utils_parsing.py
tests/test_utils_providers.py