ragbits-evaluate 1.3.0__tar.gz → 1.4.0__tar.gz

{ragbits_evaluate-1.3.0 → ragbits_evaluate-1.4.0}/CHANGELOG.md

@@ -2,6 +2,24 @@
 
 ## Unreleased
 
+## 1.4.0 (2026-02-04)
+
+### Changed
+
+- ragbits-core updated to version v1.4.0
+
+- Feat: introduce agent evaluation pipelines and metrics (HotpotQA, HumanEval, GAIA) (#829)
+
+- Feat: introduce agent simulation module with utilities for agent-to-agent conversation and evaluation scenarios (#857)
+
+- Feat: add structured results to agent simulation with `SimulationResult`, `TurnResult`, `TaskResult`, and `ConversationMetrics` models (#885)
+
+- Feat: add generic `DomainContext` and `DataSnapshot` for flexible agent simulation context (#884)
+
+- Feat: add metrics collection system for agent simulation (`MetricCollector` protocol, `LatencyMetricCollector`, `TokenUsageMetricCollector`, `ToolUsageMetricCollector`) (#882)
+
+- Fix: improve `continuous-eval` import compatibility for different package versions specified by constraints
+
 ## 1.3.0 (2025-09-11)
 
 ### Changed

{ragbits_evaluate-1.3.0 → ragbits_evaluate-1.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ragbits-evaluate
-Version: 1.3.0
+Version: 1.4.0
 Summary: Evaluation module for Ragbits components
 Project-URL: Homepage, https://github.com/deepsense-ai/ragbits
 Project-URL: Bug Reports, https://github.com/deepsense-ai/ragbits/issues
@@ -27,7 +27,7 @@ Requires-Dist: distilabel<2.0.0,>=1.5.0
 Requires-Dist: hydra-core<2.0.0,>=1.3.2
 Requires-Dist: neptune[optuna]<2.0.0,>=1.12.0
 Requires-Dist: optuna<5.0.0,>=4.0.0
-Requires-Dist: ragbits-core==1.3.0
+Requires-Dist: ragbits-core==1.4.0
 Provides-Extra: relari
 Requires-Dist: continuous-eval<1.0.0,>=0.3.12; extra == 'relari'
 Description-Content-Type: text/markdown

{ragbits_evaluate-1.3.0 → ragbits_evaluate-1.4.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ragbits-evaluate"
-version = "1.3.0"
+version = "1.4.0"
 description = "Evaluation module for Ragbits components"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -32,7 +32,7 @@ classifiers = [
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
     "Topic :: Software Development :: Libraries :: Python Modules",
 ]
-dependencies = ["hydra-core>=1.3.2,<2.0.0", "neptune[optuna]>=1.12.0,<2.0.0", "optuna>=4.0.0,<5.0.0", "distilabel>=1.5.0,<2.0.0", "datasets>=3.0.1,<4.0.0", "ragbits-core==1.3.0"]
+dependencies = ["hydra-core>=1.3.2,<2.0.0", "neptune[optuna]>=1.12.0,<2.0.0", "optuna>=4.0.0,<5.0.0", "distilabel>=1.5.0,<2.0.0", "datasets>=3.0.1,<4.0.0", "ragbits-core==1.4.0"]
 
 [project.urls]
 "Homepage" = "https://github.com/deepsense-ai/ragbits"
@@ -45,15 +45,6 @@ relari = [
     "continuous-eval>=0.3.12,<1.0.0",
 ]
 
-[tool.uv]
-dev-dependencies = [
-    "pre-commit~=3.8.0",
-    "pytest~=8.3.3",
-    "pytest-cov~=5.0.0",
-    "pytest-asyncio~=0.24.0",
-    "pip-licenses>=4.0.0,<5.0.0"
-]
-
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"

{ragbits_evaluate-1.3.0 → ragbits_evaluate-1.4.0}/src/ragbits/evaluate/metrics/question_answer.py

@@ -4,14 +4,6 @@ from asyncio import AbstractEventLoop
 from itertools import chain
 from typing import Generic, TypeVar
 
-from continuous_eval.llm_factory import LLMInterface
-from continuous_eval.metrics.base import LLMBasedMetric
-from continuous_eval.metrics.generation.text import (
-    LLMBasedAnswerCorrectness,
-    LLMBasedAnswerRelevance,
-    LLMBasedFaithfulness,
-    LLMBasedStyleConsistency,
-)
 from typing_extensions import Self
 
 from ragbits.agents.types import QuestionAnswerPromptOutputT
@@ -20,6 +12,31 @@ from ragbits.core.utils.helpers import batched
 from ragbits.evaluate.metrics.base import Metric
 from ragbits.evaluate.pipelines.question_answer import QuestionAnswerResult
 
+try:
+    from continuous_eval.llm_factory import LLMInterface
+    from continuous_eval.metrics.base import LLMBasedMetric
+    from continuous_eval.metrics.generation.text import (
+        LLMBasedAnswerCorrectness,
+        LLMBasedAnswerRelevance,
+        LLMBasedFaithfulness,
+        LLMBasedStyleConsistency,
+    )
+except ModuleNotFoundError:
+    from continuous_eval.llms.base import LLMInterface
+    from continuous_eval.metrics import Metric as LLMBasedMetric
+    from continuous_eval.metrics.generation.text import (
+        AnswerCorrectness as LLMBasedAnswerCorrectness,
+    )
+    from continuous_eval.metrics.generation.text import (
+        AnswerRelevance as LLMBasedAnswerRelevance,
+    )
+    from continuous_eval.metrics.generation.text import (
+        Faithfulness as LLMBasedFaithfulness,
+    )
+    from continuous_eval.metrics.generation.text import (
+        StyleConsistency as LLMBasedStyleConsistency,
+    )
+
 MetricT = TypeVar("MetricT", bound=LLMBasedMetric)