opik-optimizer 2.0.1__tar.gz → 2.1.1__tar.gz

{opik_optimizer-2.0.1 → opik_optimizer-2.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opik_optimizer
-Version: 2.0.1
+Version: 2.1.1
 Summary: Agent optimization with Opik
 Home-page: https://github.com/comet-ml/opik
 Author: Comet ML
@@ -18,7 +18,7 @@ Requires-Dist: dspy<3
 Requires-Dist: gepa>=0.0.7
 Requires-Dist: ujson
 Requires-Dist: hf_xet
-Requires-Dist: litellm
+Requires-Dist: litellm<=1.75.6
 Requires-Dist: mcp>=1.0.0
 Requires-Dist: opik>=1.7.17
 Requires-Dist: optuna
@@ -32,6 +32,7 @@ Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-cov; extra == "dev"
 Requires-Dist: langgraph; extra == "dev"
 Requires-Dist: pre-commit; extra == "dev"
+Requires-Dist: scikit-learn; extra == "dev"
 Dynamic: author
 Dynamic: home-page
 Dynamic: license-file
@@ -51,6 +52,7 @@ The Opik Agent Optimizer refines your prompts to achieve better performance from
 * **MetaPromptOptimizer** - Employs meta-prompting techniques for optimization
 * **MiproOptimizer** - Implements MIPRO (Multi-Input Prompt Optimization) algorithm
 * **GepaOptimizer** - Leverages GEPA (Genetic-Pareto) optimization approach
+* **ParameterOptimizer** - Optimizes LLM call parameters (temperature, top_p, etc.) using Bayesian optimization
 
 ## 🎯 Key Features
 

{opik_optimizer-2.0.1 → opik_optimizer-2.1.1}/README.md

@@ -12,6 +12,7 @@ The Opik Agent Optimizer refines your prompts to achieve better performance from
 * **MetaPromptOptimizer** - Employs meta-prompting techniques for optimization
 * **MiproOptimizer** - Implements MIPRO (Multi-Input Prompt Optimization) algorithm
 * **GepaOptimizer** - Leverages GEPA (Genetic-Pareto) optimization approach
+* **ParameterOptimizer** - Optimizes LLM call parameters (temperature, top_p, etc.) using Bayesian optimization
 
 ## 🎯 Key Features
 

{opik_optimizer-2.0.1 → opik_optimizer-2.1.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "opik_optimizer"
-version = "2.0.1"
+version = "2.1.1"
 description = "Agent optimization with Opik"
 authors = [
     {name = "Comet ML", email = "support@comet.com"}
@@ -16,7 +16,7 @@ dependencies = [
     "gepa>=0.0.7",
     "ujson",
     "hf_xet",
-    "litellm",
+    "litellm<=1.75.6",
     "mcp>=1.0.0",
     "opik>=1.7.17",
     "optuna",
@@ -34,6 +34,7 @@ dev = [
     # "google-adk",
     "langgraph",
     "pre-commit",
+    "scikit-learn",
 ]
 
 [tool.setuptools.packages.find]

{opik_optimizer-2.0.1 → opik_optimizer-2.1.1}/src/opik_optimizer/__init__.py

@@ -16,8 +16,15 @@ from .gepa_optimizer import GepaOptimizer
 from .logging_config import setup_logging
 from .meta_prompt_optimizer import MetaPromptOptimizer
 from .mipro_optimizer import MiproOptimizer
+from .hierarchical_reflective_optimizer import HierarchicalReflectiveOptimizer
 from .optimization_config.configs import TaskConfig
 from .optimization_result import OptimizationResult
+from .parameter_optimizer import (
+    ParameterOptimizer,
+    ParameterSearchSpace,
+    ParameterSpec,
+    ParameterType,
+)
 
 __version__ = importlib.metadata.version("opik_optimizer")
 
@@ -34,9 +41,14 @@ __all__ = [
     "MetaPromptOptimizer",
     "MiproOptimizer",
     "EvolutionaryOptimizer",
+    "HierarchicalReflectiveOptimizer",
+    "ParameterOptimizer",
     "OptimizationResult",
     "OptimizableAgent",
     "setup_logging",
     "datasets",
     "TaskConfig",
+    "ParameterSearchSpace",
+    "ParameterSpec",
+    "ParameterType",
 ]

{opik_optimizer-2.0.1 → opik_optimizer-2.1.1}/src/opik_optimizer/base_optimizer.py

@@ -470,6 +470,39 @@ class BaseOptimizer(ABC):
             f"{self.__class__.__name__} does not implement optimize_mcp yet."
         )
 
+    def optimize_parameter(
+        self,
+        prompt: "chat_prompt.ChatPrompt",
+        dataset: Dataset,
+        metric: Callable,
+        parameter_space: Any,
+        experiment_config: dict | None = None,
+        n_trials: int | None = None,
+        n_samples: int | None = None,
+        agent_class: type[OptimizableAgent] | None = None,
+        **kwargs: Any,
+    ) -> optimization_result.OptimizationResult:
+        """
+        Optimize LLM call parameters such as temperature or top_k.
+
+        Args:
+            prompt: The chat prompt to evaluate with tuned parameters
+            dataset: Dataset providing evaluation examples
+            metric: Objective function to maximize
+            parameter_space: Definition of the search space for tunable parameters
+            experiment_config: Optional experiment metadata
+            n_trials: Number of trials to run (optimizer specific default if None)
+            n_samples: Number of dataset samples to evaluate per trial (None for all)
+            agent_class: Optional custom agent class to execute evaluations
+            **kwargs: Additional optimizer specific settings
+
+        Returns:
+            OptimizationResult: Structured result describing the best parameters found
+        """
+        raise NotImplementedError(
+            f"{self.__class__.__name__} does not implement optimize_parameter yet."
+        )
+
     def get_history(self) -> list[OptimizationRound]:
         """
         Get the optimization history.

opik_optimizer-2.1.1/src/opik_optimizer/hierarchical_reflective_optimizer/__init__.py

@@ -0,0 +1,5 @@
+from .hierarchical_reflective_optimizer import HierarchicalReflectiveOptimizer
+
+__all__ = [
+    "HierarchicalReflectiveOptimizer",
+]