Slim NLP Engine

presidio-analyzer/install_nlp_models.py

@@ -52,7 +52,7 @@ def install_models(conf_file: str) -> None:
 
 
 def _download_model(engine_name: str, model_name: Union[str, Dict[str, str]]) -> None:
-    if engine_name == "spacy":
+    if engine_name == "spacy" or engine_name == "slim":
         spacy_download(model_name)
     elif engine_name == "stanza":
         if stanza:

presidio-analyzer/presidio_analyzer/conf/slim.yaml

@@ -0,0 +1,120 @@
+supported_languages:
+  - en
+default_score_threshold: 0
+nlp_configuration:
+  nlp_engine_name: slim
+  models:
+    - lang_code: en
+      model_name: en_core_web_sm
+
+recognizer_registry:
+  # global_regex_flags: 26
+  recognizers:
+    # GLiNERRecognizer replaces SpacyRecognizer for NER-based entity detection.
+    # The slim NLP engine provides only tokenization and lemmatization;
+    # entity extraction is handled by self-contained recognizers like GLiNER.
+    - name: GLiNERRecognizer
+      type: predefined
+      enabled: true
+
+    - name: CreditCardRecognizer
+      supported_languages:
+      - language: en
+        context: [credit, card, visa, mastercard, cc, amex, discover, jcb, diners, maestro, instapayment]
+      type: predefined
+
+    - name: UsBankRecognizer
+      type: predefined
+
+    - name: UsLicenseRecognizer
+      type: predefined
+
+    - name: UsItinRecognizer
+      type: predefined
+
+    - name: UsPassportRecognizer
+      type: predefined
+
+    - name: UsSsnRecognizer
+      type: predefined
+
+    - name: NhsRecognizer
+      type: predefined
+
+    - name: UkNinoRecognizer
+      type: predefined
+      enabled: false
+
+    - name: UkPassportRecognizer
+      type: predefined
+      enabled: false
+
+    - name: SgFinRecognizer
+      type: predefined
+      enabled: false
+
+    - name: AuAbnRecognizer
+      type: predefined
+      enabled: false
+
+    - name: AuAcnRecognizer
+      type: predefined
+      enabled: false
+
+    - name: AuTfnRecognizer
+      type: predefined
+      enabled: false
+
+    - name: AuMedicareRecognizer
+      type: predefined
+      enabled: false
+
+    - name: InPanRecognizer
+      type: predefined
+      enabled: false
+
+    - name: InAadhaarRecognizer
+      supported_languages:
+      - en
+      type: predefined
+      enabled: false
+
+    - name: InVehicleRegistrationRecognizer
+      type: predefined
+      enabled: false
+
+    - name: InPassportRecognizer
+      type: predefined
+      enabled: false
+
+    - name: CryptoRecognizer
+      type: predefined
+
+    - name: DateRecognizer
+      type: predefined
+
+    - name: EmailRecognizer
+      type: predefined
+
+    - name: IbanRecognizer
+      type: predefined
+
+    - name: IpRecognizer
+      type: predefined
+
+    - name: MedicalLicenseRecognizer
+      type: predefined
+
+    - name: PhoneRecognizer
+      type: predefined
+
+    - name: UrlRecognizer
+      type: predefined
+
+    - name: InVoterRecognizer
+      type: predefined
+      enabled: false
+
+    - name: InGstinRecognizer
+      type: predefined
+      enabled: false

presidio-analyzer/presidio_analyzer/conf/slim_nlp.yaml

@@ -0,0 +1,5 @@
+nlp_engine_name: slim
+models:
+  -
+    lang_code: en
+    model_name: en_core_web_sm

presidio-analyzer/presidio_analyzer/nlp_engine/__init__.py

@@ -4,6 +4,7 @@
 from .ner_model_configuration import NerModelConfiguration
 from .nlp_artifacts import NlpArtifacts
 from .nlp_engine import NlpEngine
+from .slim_spacy_nlp_engine import SlimSpacyNlpEngine
 from .spacy_nlp_engine import SpacyNlpEngine
 from .stanza_nlp_engine import StanzaNlpEngine
 from .transformers_nlp_engine import TransformersNlpEngine
@@ -15,6 +16,7 @@
     "NerModelConfiguration",
     "NlpArtifacts",
     "NlpEngine",
+    "SlimSpacyNlpEngine",
     "SpacyNlpEngine",
     "StanzaNlpEngine",
     "NlpEngineProvider",

presidio-analyzer/presidio_analyzer/nlp_engine/nlp_engine_provider.py

@@ -8,6 +8,7 @@
 from presidio_analyzer.nlp_engine import (
     NerModelConfiguration,
     NlpEngine,
+    SlimSpacyNlpEngine,
     SpacyNlpEngine,
     StanzaNlpEngine,
     TransformersNlpEngine,
@@ -19,7 +20,7 @@
 class NlpEngineProvider:
     """Create different NLP engines from configuration.
 
-    :param nlp_engines: List of available NLP engines.
+    :param nlp_engines: List of available NLP engines
     Default: (SpacyNlpEngine, StanzaNlpEngine)
     :param nlp_configuration: Dict containing nlp configuration
     :example: configuration:
@@ -40,7 +41,12 @@ def __init__(
         nlp_configuration: Optional[Dict] = None,
     ):
         if nlp_engines is None:
-            nlp_engines = (SpacyNlpEngine, StanzaNlpEngine, TransformersNlpEngine)
+            nlp_engines = (
+                SpacyNlpEngine,
+                StanzaNlpEngine,
+                TransformersNlpEngine,
+                SlimSpacyNlpEngine,
+            )
 
         self.nlp_engines = {
             engine.engine_name: engine for engine in nlp_engines if engine.is_available
@@ -76,10 +82,9 @@ def _read_nlp_conf(conf_file: Union[Path, str]) -> Dict:
         with open(conf_file) as file:
             return yaml.safe_load(file)
 
-
     @staticmethod
     def _get_full_conf_path(
-        default_conf_file: Union[Path, str] = "default.yaml"
+        default_conf_file: Union[Path, str] = "default.yaml",
     ) -> Path:
         """Return a Path to the default conf file."""
         return Path(Path(__file__).parent, "../conf", default_conf_file)
@@ -97,15 +102,24 @@ def create_engine(self) -> NlpEngine:
         nlp_engine_class = self.nlp_engines[nlp_engine_name]
         nlp_models = self.nlp_configuration["models"]
 
-        ner_model_configuration = self.nlp_configuration.get("ner_model_configuration")
-        if ner_model_configuration:
-            ner_model_configuration = NerModelConfiguration.from_dict(
-                ner_model_configuration
+        if nlp_engine_name == SlimSpacyNlpEngine.engine_name:
+            generic_tokenizer = self.nlp_configuration.get("generic_tokenizer")
+            engine = nlp_engine_class(
+                models=nlp_models, generic_tokenizer=generic_tokenizer
+            )
+        else:
+            ner_model_configuration = self.nlp_configuration.get(
+                "ner_model_configuration"
+            )
+            if ner_model_configuration:
+                ner_model_configuration = NerModelConfiguration.from_dict(
+                    ner_model_configuration
+                )
+
+            engine = nlp_engine_class(
+                models=nlp_models, ner_model_configuration=ner_model_configuration
             )
 
-        engine = nlp_engine_class(
-            models=nlp_models, ner_model_configuration=ner_model_configuration
-        )
         engine.load()
         logger.info(
             f"Created NLP engine: {engine.engine_name}. "