rasa-pro 3.10.24__py3-none-any.whl → 3.10.25__py3-none-any.whl

rasa/nlu/extractors/crf_entity_extractor.py

@@ -1,10 +1,12 @@
 from __future__ import annotations
 
-from collections import OrderedDict
-from enum import Enum
 import logging
+import shutil
 import typing
-from typing import Any, Dict, List, Optional, Text, Tuple, Callable, Type
+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/telemetry.py

@@ -894,7 +894,7 @@ def initialize_error_reporting() -> None:
             OSError,
         ],
         in_app_include=["rasa"],  # only submit errors in this package
-        with_locals=False,  # don't submit local variables
+        include_local_variables=False,  # don't submit local variables
         release=f"rasa-{rasa.__version__}",
         default_integrations=False,
         environment="development" if in_continuous_integration() else "production",

rasa/version.py

@@ -1,3 +1,3 @@
 # this file will automatically be changed,
 # do not add anything but the version number here!
-__version__ = "3.10.24"
+__version__ = "3.10.25"

{rasa_pro-3.10.24.dist-info → rasa_pro-3.10.25.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: rasa-pro
-Version: 3.10.24
+Version: 3.10.25
 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
@@ -26,7 +26,7 @@ Requires-Dist: SQLAlchemy (>=2.0.22,<2.1.0)
 Requires-Dist: absl-py (>=2.0,<2.1)
 Requires-Dist: aio-pika (>=8.2.3,<8.2.4)
 Requires-Dist: aiogram (>=2.15,<2.26)
-Requires-Dist: aiohttp (>=3.9.4,<3.10)
+Requires-Dist: aiohttp (>=3.10.11,<3.11)
 Requires-Dist: apscheduler (>=3.10,<3.11)
 Requires-Dist: attrs (>=23.1,<23.2)
 Requires-Dist: azure-storage-blob (>=12.16.0,<12.17.0)
@@ -113,7 +113,7 @@ Requires-Dist: sanic-routing (>=22.8.0,<23.0.0)
 Requires-Dist: scikit-learn (>=1.1.3,<1.2) ; python_version >= "3.9" and python_version < "3.11"
 Requires-Dist: scipy (>=1.10.1,<1.11.0) ; python_version >= "3.9" and python_version < "3.11"
 Requires-Dist: sentencepiece[sentencepiece] (>=0.1.99,<0.2.0) ; extra == "transformers" or extra == "full"
-Requires-Dist: sentry-sdk (>=1.14.0,<1.15.0)
+Requires-Dist: sentry-sdk (>=2.8.0,<3)
 Requires-Dist: setuptools (>=78.1.0,<78.2.0)
 Requires-Dist: sklearn-crfsuite (>=0.3.6,<0.4.0)
 Requires-Dist: skops (>=0.10.0,<0.11.0)

{rasa_pro-3.10.24.dist-info → rasa_pro-3.10.25.dist-info}/RECORD

@@ -509,7 +509,7 @@ rasa/nlu/emulators/luis.py,sha256=AWMGI17Su1q6PcE8l1S1mDJpwfVtx7ibY9rwBmg3Maw,30
 rasa/nlu/emulators/no_emulator.py,sha256=tLJ2DyWhOtaIBudVf7mJGsubca9Vunb6VhJB_tWJ8wU,334
 rasa/nlu/emulators/wit.py,sha256=0eMj_q49JGj0Z6JZjR7rHIABNF-F3POX7s5W5OkANyo,1930
 rasa/nlu/extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-rasa/nlu/extractors/crf_entity_extractor.py,sha256=5IW7Fa4lLLUxMrbHiRmBD7Y6B7TmS_o66USoSxYBOZk,27532
+rasa/nlu/extractors/crf_entity_extractor.py,sha256=pLiM6vEybqSW4refbBRr68QbE-9haxyHQo7vslymyI0,29400
 rasa/nlu/extractors/duckling_entity_extractor.py,sha256=XooWjw6eDC0sxZ-T1YgDnrLcRTBx6B40SFGLjHTHg-w,7686
 rasa/nlu/extractors/entity_synonyms.py,sha256=WShheUF7wbP7VWfpCNw3J4NouAcFjAupDsT4oAj_TUc,7148
 rasa/nlu/extractors/extractor.py,sha256=m6p07GDBZi1VhgYCkYJrWs_Zk87okV77hvoiwG_1xxA,17539
@@ -683,7 +683,7 @@ rasa/studio/download.py,sha256=9uE4KKaHnID_3-Tt_E5_D00XTwhLlj4oxORY8CZRrZc,17188
 rasa/studio/results_logger.py,sha256=0gCkEaZ1CeFmxRHArK5my_DsLYjApZrxfiRMT5asE6A,4963
 rasa/studio/train.py,sha256=gfPtirITzBDo9gV4hqDNSwPYtVp_22cq8OWI6YIBgyk,4243
 rasa/studio/upload.py,sha256=5hvj_DUzxq5JkZswro-KaLE4QAKwbMLGb8TakzS1etk,14290
-rasa/telemetry.py,sha256=Q6MQnDhOY6cKRVs3PayiM6WYWb8QJ_Hb3_eOm12n0tI,61093
+rasa/telemetry.py,sha256=6CMcbQ241zoTPzhtmBsPMfW8Glc2tm8uD6cd3J8t99A,61105
 rasa/tracing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 rasa/tracing/config.py,sha256=O4iHkE4kF6r4uVAt3JUb--TniK7pWD4j3d08Vf_GuYY,12736
 rasa/tracing/constants.py,sha256=N_MJLStE3IkmPKQCQv42epd3jdBMJ4Ith1dVO65N5ho,2425
@@ -728,9 +728,9 @@ rasa/utils/train_utils.py,sha256=f1NWpp5y6al0dzoQyyio4hc4Nf73DRoRSHDzEK6-C4E,212
 rasa/utils/url_tools.py,sha256=JQcHL2aLqLHu82k7_d9imUoETCm2bmlHaDpOJ-dKqBc,1218
 rasa/utils/yaml.py,sha256=KjbZq5C94ZP7Jdsw8bYYF7HASI6K4-C_kdHfrnPLpSI,2000
 rasa/validator.py,sha256=AsFJ8e1zWHW-hnH_IB3SGBBl68vstKPrrqbAydgjVhQ,63149
-rasa/version.py,sha256=xhBga-JTNnvCJXBHczNZMXAx6evYUpEiLJj1yvWVto0,118
-rasa_pro-3.10.24.dist-info/METADATA,sha256=d3LOzpxaEL6JzWWFX53OrqLUYj-UvIWm8Mu2qILmCsI,10856
-rasa_pro-3.10.24.dist-info/NOTICE,sha256=7HlBoMHJY9CL2GlYSfTQ-PZsVmLmVkYmMiPlTjhuCqA,218
-rasa_pro-3.10.24.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
-rasa_pro-3.10.24.dist-info/entry_points.txt,sha256=ckJ2SfEyTPgBqj_I6vm_tqY9dZF_LAPJZA335Xp0Q9U,43
-rasa_pro-3.10.24.dist-info/RECORD,,
+rasa/version.py,sha256=GWHwGypLvbRd-D94Ljby0tnp6afbxH7wn_u0DTC-sKA,118
+rasa_pro-3.10.25.dist-info/METADATA,sha256=rBmzUv8f5_vktUAhp1pNCqP6e2kaEhfG8udVtySLHXo,10852
+rasa_pro-3.10.25.dist-info/NOTICE,sha256=7HlBoMHJY9CL2GlYSfTQ-PZsVmLmVkYmMiPlTjhuCqA,218
+rasa_pro-3.10.25.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
+rasa_pro-3.10.25.dist-info/entry_points.txt,sha256=ckJ2SfEyTPgBqj_I6vm_tqY9dZF_LAPJZA335Xp0Q9U,43
+rasa_pro-3.10.25.dist-info/RECORD,,