ML-005 vorbereiten: Registry, API-Routen und kompatibler Predictor

app/ml/predictor.py

@@ -1,21 +1,31 @@
 from __future__ import annotations
 
 import logging
-from functools import lru_cache
 from typing import Sequence
 
 from app.ml.feature_store import FeatureVector
-from app.ml.training import TrainingPipeline, TrainedArtifact
+from app.ml.registry.model_registry import ModelRegistry
+from app.ml.training import TrainedArtifact, TrainingPipeline
 
 logger = logging.getLogger(__name__)
 
 
 class Predictor:
-    def __init__(self, pipeline: TrainingPipeline) -> None:
+    def __init__(
+        self,
+        pipeline: TrainingPipeline | None = None,
+        registry: ModelRegistry | None = None,
+    ) -> None:
+        if isinstance(pipeline, ModelRegistry) and registry is None:
+            registry = pipeline
+            pipeline = None
+        if pipeline is None and registry is None:
+            raise ValueError("Predictor erfordert TrainingPipeline oder ModelRegistry.")
         self._pipeline = pipeline
+        self._registry = registry
 
     def predict(self, artifact_id: str, entity: FeatureVector) -> str:
-        artifact = self._pipeline.export(artifact_id)
+        artifact = self._get_artifact(artifact_id)
         if entity.sensor_id not in artifact.supported_sensors:
             raise ValueError(
                 f"Sensor '{entity.sensor_id}' wird vom Modell '{artifact_id}' nicht unterstützt."
@@ -30,4 +40,11 @@ class Predictor:
         artifacts = list(pipeline._artifacts)
         if not artifacts:
             raise ValueError("Kein trainiertes Modell gefunden.")
-        return pipeline.export(artifacts[-1])
+        return pipeline.export(artifacts[-1])
+
+    def _get_artifact(self, artifact_id: str) -> TrainedArtifact:
+        if self._registry is not None:
+            return self._registry.load_artifact(artifact_id)
+        if self._pipeline is not None:
+            return self._pipeline.export(artifact_id)
+        raise RuntimeError("Predictor nicht initialisiert.")

app/ml/registry/__init__.py

@@ -0,0 +1,3 @@
+from .model_registry import ModelRegistry
+
+__all__ = ["ModelRegistry"]

app/ml/registry/model_registry.py

@@ -0,0 +1,37 @@
+from __future__ import annotations
+
+import logging
+from pathlib import Path
+from typing import Iterable
+
+from app.ml.training import TrainedArtifact
+
+logger = logging.getLogger(__name__)
+
+
+class ModelRegistry:
+    def __init__(self, root: str | Path) -> None:
+        self._root = Path(root)
+        self._root.mkdir(parents=True, exist_ok=True)
+        self._artifacts: dict[str, TrainedArtifact] = {}
+
+    def register(self, artifact: TrainedArtifact) -> TrainedArtifact:
+        self._artifacts[artifact.artifact_id] = artifact
+        self._persist(artifact)
+        return artifact
+
+    def load_artifact(self, artifact_id: str) -> TrainedArtifact:
+        if artifact_id not in self._artifacts:
+            raise KeyError(f"Artifact '{artifact_id}' nicht registriert.")
+        return self._artifacts[artifact_id]
+
+    def list_models(self) -> Iterable[TrainedArtifact]:
+        return list(self._artifacts.values())
+
+    def _persist(self, artifact: TrainedArtifact) -> None:
+        target = self._root / f"{artifact.artifact_id}.json"
+        target.write_text(
+            f"{artifact.artifact_id}\t{','.join(artifact.supported_sensors)}\n",
+            encoding="utf-8",
+        )
+        logger.info("Modell gespeichert: %s", target)