tide2 1.1.0__py3-none-any.whl

tide2/__init__.py

@@ -0,0 +1,12 @@
+"""
+.. include:: ../../README.md
+"""
+
+try:
+    # Written by hatch-vcs at build time from the git tag (see pyproject.toml).
+    from tide2._version import __version__
+except ImportError:  # pragma: no cover - source checkout without a build
+    __version__ = "0.0.0.dev0"
+
+__author__ = "TiDE-CORE 2.0 Team"
+__docformat__ = "google"

tide2/_version.py

@@ -0,0 +1,24 @@
+# file generated by vcs-versioning
+# don't change, don't track in version control
+from __future__ import annotations
+
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
+
+version: str
+__version__: str
+__version_tuple__: tuple[int | str, ...]
+version_tuple: tuple[int | str, ...]
+commit_id: str | None
+__commit_id__: str | None
+
+__version__ = version = '1.1.0'
+__version_tuple__ = version_tuple = (1, 1, 0)
+
+__commit_id__ = commit_id = None

tide2/actors/__init__.py

@@ -0,0 +1,63 @@
+"""
+Unified Ray actors for batch processing.
+
+This module provides Ray actors for recognition, anonymization, and transformer
+inference that work across all execution modes: local, VM, and cluster.
+
+Actors:
+    RecognizerActor: PII/PHI recognition using Presidio AnalyzerEngine
+    AnonymizerActor: Anonymization using Presidio AnonymizerEngine with HIPS
+    TransformerInferenceActor: GPU-based transformer NER inference
+
+Factory Functions:
+    create_anonymizer_actor: Create AnonymizerActor with keys (bytes or file paths)
+    create_transformer_actor: Create TransformerInferenceActor with model config
+
+Example:
+    from tide2.actors import RecognizerActor, create_anonymizer_actor
+
+    # Use directly with Ray Data
+    ds.map_batches(RecognizerActor, batch_size=100, ...)
+
+    # Create configured actor with factory
+    AnonymizerActorClass = create_anonymizer_actor("/path/to/private.key", "/path/to/public.key")
+    ds.map_batches(AnonymizerActorClass, batch_size=100, ...)
+"""
+
+from tide2.actors.anonymizer import AnonymizerActor
+from tide2.actors.anonymizer import create_anonymizer_actor
+from tide2.actors.anonymizer import create_anonymizer_actor_class  # Backwards compatibility
+from tide2.actors.llm_recognizer import LlmRecognizerActor
+from tide2.actors.reassembly import ReassemblyActor
+from tide2.actors.recognizer import NoOpContextEnhancer
+from tide2.actors.recognizer import RecognizerActor
+
+
+def __getattr__(name: str):
+    """Lazy import for torch-dependent transformer actors."""
+    _transformer_exports = {
+        "BIOAggregationActor",
+        "TransformerInferenceActor",
+        "create_transformer_actor",
+        "create_transformer_actor_class",
+    }
+    if name in _transformer_exports:
+        from tide2.actors import transformer as _mod
+
+        return getattr(_mod, name)
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+
+
+__all__ = [
+    "AnonymizerActor",
+    "BIOAggregationActor",
+    "LlmRecognizerActor",
+    "NoOpContextEnhancer",
+    "ReassemblyActor",
+    "RecognizerActor",
+    "TransformerInferenceActor",
+    "create_anonymizer_actor",
+    "create_anonymizer_actor_class",
+    "create_transformer_actor",
+    "create_transformer_actor_class",
+]