rasa-pro 3.12.10__py3-none-any.whl → 3.12.11__py3-none-any.whl

rasa/keys

@@ -0,0 +1 @@
+{"segment": "CcvVD1I68Nkkxrv93cIqv1twIwrwG8nz", "sentry": "a283f1fde04347b099c8d729109dd450@o251570"}

rasa/nlu/extractors/crf_entity_extractor.py

@@ -1,9 +1,11 @@
 from __future__ import annotations
 
 import logging
+import shutil
 import typing
 from collections import OrderedDict
 from enum import Enum
+from pathlib import Path
 from typing import Any, Callable, Dict, List, Optional, Text, Tuple, Type
 
 import numpy as np
@@ -43,6 +45,10 @@ if typing.TYPE_CHECKING:
 
 CONFIG_FEATURES = "features"
 
+TAGGERS_DIR = "taggers"
+CRFSUITE_MODEL_FILE_NAME = "model.crfsuite"
+PLAIN_CRF_MODEL_FILE_NAME = "model.txt"
+
 
 class CRFToken:
     def __init__(
@@ -419,19 +425,11 @@ class CRFEntityExtractor(GraphComponent, EntityExtractorMixin):
         """Loads trained component (see parent class for full docstring)."""
         try:
             with model_storage.read_from(resource) as model_dir:
-                dataset = rasa.shared.utils.io.read_json_file(
-                    model_dir / "crf_dataset.json"
-                )
                 crf_order = rasa.shared.utils.io.read_json_file(
                     model_dir / "crf_order.json"
                 )
 
-                dataset = [
-                    [CRFToken.create_from_dict(token_data) for token_data in sub_list]
-                    for sub_list in dataset
-                ]
-
-                entity_taggers = cls.train_model(dataset, config, crf_order)
+                entity_taggers = cls._load_taggers(model_dir, config)
 
                 entity_extractor = cls(config, model_storage, resource, entity_taggers)
                 entity_extractor.crf_order = crf_order
@@ -443,19 +441,71 @@ class CRFEntityExtractor(GraphComponent, EntityExtractorMixin):
             )
             return cls(config, model_storage, resource)
 
+    @classmethod
+    def _load_taggers(
+        cls, model_dir: Path, config: Dict[Text, Any]
+    ) -> Dict[str, "CRF"]:
+        """
+        Load taggers from model directory that persists trained binary
+        `model.crfsuite` files.
+        """
+
+        import pycrfsuite
+        import sklearn_crfsuite
+
+        # Get tagger directories
+        taggers_base = model_dir / TAGGERS_DIR
+        if not taggers_base.exists():
+            return {}
+
+        taggers_dirs = [
+            directory for directory in taggers_base.iterdir() if directory.is_dir()
+        ]
+
+        entity_taggers: Dict[str, "CRF"] = {}
+
+        for tagger_dir in taggers_dirs:
+            # Instantiate sklearns CRF wrapper for the pycrfsuite's Tagger
+            entity_tagger = sklearn_crfsuite.CRF(
+                algorithm="lbfgs",
+                # coefficient for L1 penalty
+                c1=config["L1_c"],
+                # coefficient for L2 penalty
+                c2=config["L2_c"],
+                # stop earlier
+                max_iterations=config["max_iterations"],
+                # include transitions that are possible, but not observed
+                all_possible_transitions=True,
+            )
+
+            # Load pycrfsuite tagger from the persisted binary model.crfsuite file
+            entity_tagger._tagger = pycrfsuite.Tagger()
+            entity_tagger._tagger.open(str(tagger_dir / CRFSUITE_MODEL_FILE_NAME))
+
+            entity_taggers[tagger_dir.name] = entity_tagger
+
+        return entity_taggers
+
     def persist(self, dataset: List[List[CRFToken]]) -> None:
         """Persist this model into the passed directory."""
         with self._model_storage.write_to(self._resource) as model_dir:
-            data_to_store = [
-                [token.to_dict() for token in sub_list] for sub_list in dataset
-            ]
-
-            rasa.shared.utils.io.dump_obj_as_json_to_file(
-                model_dir / "crf_dataset.json", data_to_store
-            )
             rasa.shared.utils.io.dump_obj_as_json_to_file(
                 model_dir / "crf_order.json", self.crf_order
             )
+            if self.entity_taggers is not None:
+                for tag_name, entity_tagger in self.entity_taggers.items():
+                    # Create the directories for storing the CRF model
+                    tagger_dir = model_dir / TAGGERS_DIR / tag_name
+                    tagger_dir.mkdir(parents=True, exist_ok=True)
+                    # Create a plain text version of the CRF model
+                    entity_tagger.tagger_.dump(
+                        str(tagger_dir / PLAIN_CRF_MODEL_FILE_NAME)
+                    )
+                    # Persist binary version of the model.crfsuite
+                    shutil.copy2(
+                        src=entity_tagger.modelfile.name,
+                        dst=tagger_dir / CRFSUITE_MODEL_FILE_NAME,
+                    )
 
     @classmethod
     def _crf_tokens_to_features(

rasa/version.py

@@ -1,3 +1,3 @@
 # this file will automatically be changed,
 # do not add anything but the version number here!
-__version__ = "3.12.10"
+__version__ = "3.12.11"

{rasa_pro-3.12.10.dist-info → rasa_pro-3.12.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: rasa-pro
-Version: 3.12.10
+Version: 3.12.11
 Summary: State-of-the-art open-core Conversational AI framework for Enterprises that natively leverages generative AI for effortless assistant development.
 Keywords: nlp,machine-learning,machine-learning-library,bot,bots,botkit,rasa conversational-agents,conversational-ai,chatbot,chatbot-framework,bot-framework
 Author: Rasa Technologies GmbH

{rasa_pro-3.12.10.dist-info → rasa_pro-3.12.11.dist-info}/RECORD

@@ -532,6 +532,7 @@ rasa/graph_components/validators/default_recipe_validator.py,sha256=iOVoB7zVTKes
 rasa/graph_components/validators/finetuning_validator.py,sha256=VfCGytnweijKBG8bAqYp7zKZB2aRgi2ZI8R0eou5Ev4,12865
 rasa/hooks.py,sha256=5ZMrqNz323w56MMY6E8jeZ_YXgRqq8p-yi18S2XOmbo,4061
 rasa/jupyter.py,sha256=TCYVD4QPQIMmfA6ZwDUBOBTAECwCwbU2XOkosodLO9k,1782
+rasa/keys,sha256=2Stg1fstgJ203cOoW1B2gGMY29fhEnjIfTVxKv_fqPo,101
 rasa/llm_fine_tuning/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 rasa/llm_fine_tuning/annotation_module.py,sha256=6wBBjGwONVlikp79xAHp5g3rydEhPM6kP1bw1g-maYk,8578
 rasa/llm_fine_tuning/conversations.py,sha256=QZVaUsfXe5iIE830Bv-_3oo8luhGfHpirvubxzOoEvA,4116
@@ -582,7 +583,7 @@ rasa/nlu/emulators/luis.py,sha256=BaBluhzyHbELy2ji9zMIMYNbGklQEJqwGu-Z1zaRFS8,30
 rasa/nlu/emulators/no_emulator.py,sha256=x8VoSxRm4aec8Fk797ipy78KxyBcBjnQ08xesLhG0nI,335
 rasa/nlu/emulators/wit.py,sha256=6ltOc8S__UzesWPGI6-igxnkUa6ZKoNLhpZU7o2g4R4,1930
 rasa/nlu/extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-rasa/nlu/extractors/crf_entity_extractor.py,sha256=UT3lfVOLKWDSki5hGrrDxHq-zNjb6oquIgGQq0PoGsQ,27532
+rasa/nlu/extractors/crf_entity_extractor.py,sha256=Cv2ObNSyGdi-f2tCY0tu28gY12bf5x9mi5d1ncg1m6o,29400
 rasa/nlu/extractors/duckling_entity_extractor.py,sha256=vDW9VgQRgIw8Lc3nYoNJFR58IwSeB0Mt_K1Tz8lg7XQ,7687
 rasa/nlu/extractors/entity_synonyms.py,sha256=9Ums__jzagpkpQbCj5MKr44tkaicaA2zj_4KFe2FgME,7149
 rasa/nlu/extractors/extractor.py,sha256=WDw2a8fSmsHeYflNpZwYwQ2o-ffwUIkWY2B7gSlfuAY,17539
@@ -821,9 +822,9 @@ rasa/utils/train_utils.py,sha256=ClJx-6x3-h3Vt6mskacgkcCUJTMXjFPe3zAcy_DfmaU,212
 rasa/utils/url_tools.py,sha256=dZ1HGkVdWTJB7zYEdwoDIrEuyX9HE5WsxKKFVsXBLE0,1218
 rasa/utils/yaml.py,sha256=KjbZq5C94ZP7Jdsw8bYYF7HASI6K4-C_kdHfrnPLpSI,2000
 rasa/validator.py,sha256=524VlFTYK0B3iXYveVD6BDC3K0j1QfpzJ9O-TAWczmc,83166
-rasa/version.py,sha256=F6TWQP94ECROLtXqlCrwu9xSrvxZDs3JVTp6gPLbxfE,118
-rasa_pro-3.12.10.dist-info/METADATA,sha256=3wU4IxYsMJruxuysovjfW1wt7IOsh0YELYX4uvwhDhY,10616
-rasa_pro-3.12.10.dist-info/NOTICE,sha256=7HlBoMHJY9CL2GlYSfTQ-PZsVmLmVkYmMiPlTjhuCqA,218
-rasa_pro-3.12.10.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
-rasa_pro-3.12.10.dist-info/entry_points.txt,sha256=ckJ2SfEyTPgBqj_I6vm_tqY9dZF_LAPJZA335Xp0Q9U,43
-rasa_pro-3.12.10.dist-info/RECORD,,
+rasa/version.py,sha256=XvXtUVw5FDQnXtExrv4wXMnPazsNF9kg9UQ_UNtd3wQ,118
+rasa_pro-3.12.11.dist-info/METADATA,sha256=RhI4sfwSLwWa59piZoOXxn9CJg1xHBD1T-FJ2jk0yJE,10616
+rasa_pro-3.12.11.dist-info/NOTICE,sha256=7HlBoMHJY9CL2GlYSfTQ-PZsVmLmVkYmMiPlTjhuCqA,218
+rasa_pro-3.12.11.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
+rasa_pro-3.12.11.dist-info/entry_points.txt,sha256=ckJ2SfEyTPgBqj_I6vm_tqY9dZF_LAPJZA335Xp0Q9U,43
+rasa_pro-3.12.11.dist-info/RECORD,,