rasa-pro 3.13.12__py3-none-any.whl → 3.14.0__py3-none-any.whl

rasa/utils/openapi.py

@@ -0,0 +1,144 @@
+from typing import Any, Dict, List, Type
+
+from pydantic.main import BaseModel
+from sanic_openapi import openapi
+from sanic_openapi.openapi3.types import Schema
+
+_SUPPORTED_ATTRIBUTES = frozenset(["format", "enum", "required", "example"])
+
+
+def _to_schema(
+    definition_stack: List[str], schema_def: Dict[str, Any], definitions: Dict[str, Any]
+) -> Schema:
+    type = schema_def.get("type")
+
+    if type == "object":
+        properties_spec = schema_def.get("properties", {})
+        properties = {}
+        for key in properties_spec:
+            properties[key] = _to_schema(
+                definition_stack=definition_stack,
+                schema_def=properties_spec[key],
+                definitions=definitions,
+            )
+        schema = openapi.Object(
+            title=schema_def.get("title"),
+            description=schema_def.get("description"),
+            required=schema_def.get("required"),
+            properties=properties,
+        )
+    elif type == "array":
+        schema = openapi.Array(
+            description=schema_def.get("description"),
+            required=schema_def.get("required"),
+            items=_to_schema(
+                definition_stack=definition_stack,
+                schema_def=schema_def.get("items"),
+                definitions=definitions,
+            ),
+        )
+    elif type is None:
+        if allof_spec := schema_def.get("allOf"):  # Model, Enum
+            definition = allof_spec[0]["$ref"].split("/")[-1]
+            definition_data = definitions.get(definition)
+            if definition_data is None:
+                schema = openapi.Object(
+                    title=definition, description=schema_def.get("description")
+                )
+            else:
+                schema = (
+                    _to_schema(
+                        definition_stack=definition_stack + [definition],
+                        schema_def={**definition_data},
+                        definitions=definitions,
+                    )
+                    if definition not in definition_stack
+                    else openapi.Object(
+                        title=definition, description=schema_def.get("description")
+                    )
+                )
+
+        elif anyof_spec := schema_def.get("anyOf"):  # Union
+            anyof = []
+            for any in anyof_spec:
+                if any.get("type"):
+                    schema_type_obj = Schema(
+                        **{
+                            "type": any.get("type"),
+                            "description": any.get("description"),
+                        }
+                    )
+                    anyof.append(schema_type_obj)
+                else:
+                    definition = any["$ref"].split("/")[-1]
+                    if definition not in definition_stack:
+                        definition_data = definitions.get(definition)
+                        if definition_data is not None:
+                            anyof.append(
+                                _to_schema(
+                                    definition_stack=definition_stack + [definition],
+                                    schema_def=definition_data,
+                                    definitions=definitions,
+                                )
+                            )
+                        else:
+                            anyof.append(
+                                openapi.Object(
+                                    title=definition,
+                                    description=schema_def.get(
+                                        "description", definition
+                                    ),
+                                    properties={},
+                                )
+                            )
+                    else:
+                        anyof.append(
+                            openapi.Object(
+                                title=definition,
+                                description=schema_def.get("description", definition),
+                                properties={},
+                            )
+                        )
+            schema = Schema(anyOf=anyof)
+        elif ref := schema_def.get("$ref"):  # $ref
+            definition = ref.split("/")[-1]
+            definition_data = definitions.get(definition)
+            if definition_data is not None:
+                schema = _to_schema(
+                    definition_stack=definition_stack,
+                    schema_def=definition_data,
+                    definitions=definitions,
+                )
+            else:
+                schema = openapi.Object(
+                    title=definition, description=schema_def.get("description")
+                )
+        else:  # Any type
+            schema = Schema(
+                **{"type": "object", "description": schema_def.get("description")}
+            )
+
+    else:
+        schema_spec = {
+            "type": schema_def.get("type"),
+            "description": schema_def.get("description"),
+        }
+        for spec in _SUPPORTED_ATTRIBUTES:
+            if schema_def.get(spec):
+                schema_spec[spec] = schema_def.get(spec)
+        schema = Schema(**schema_spec)
+
+    return schema
+
+
+def model_to_schema(model: Type[BaseModel]) -> Schema:
+    schema = model.model_json_schema()
+    # Handle both $defs (newer JSON Schema) and definitions (older JSON Schema)
+    definitions = schema.get("$defs") or schema.get("definitions") or {}
+    return _to_schema(
+        definition_stack=[],
+        schema_def=dict(
+            filter(lambda key: key[0] not in ("definitions", "$defs"), schema.items())
+        ),
+        definitions=definitions,
+    )

rasa/utils/plotting.py

@@ -99,7 +99,7 @@ def plot_confusion_matrix(
     zmax = confusion_matrix.max() if len(confusion_matrix) > 0 else 1
     plt.clf()
     if not color_map:
-        color_map = plt.cm.Blues
+        color_map = plt.cm.get_cmap("Blues")
     plt.imshow(
         confusion_matrix,
         interpolation="nearest",

rasa/utils/pypred.py

@@ -0,0 +1,45 @@
+"""Wrapper module for pypred that provides a fixed Predicate class.
+
+This module should be used instead of importing directly from pypred.
+
+This patch fixes an issue where pypred creates excessive logs of being unable
+to write a file when run in an environment with no write access is given.
+
+https://rasahq.atlassian.net/browse/ATO-1925
+
+The solution is based on https://github.com/FreeCAD/FreeCAD/issues/6315
+"""
+
+import logging
+from typing import Any
+
+import ply.yacc
+import pypred.parser
+from pypred import Predicate as OriginalPredicate  # noqa: TID251
+
+# Store the original yacc function
+_original_yacc = ply.yacc.yacc
+
+# Create a logger that suppresses warnings to avoid yacc table file version warnings
+_yacc_logger = logging.getLogger("ply.yacc")
+_yacc_logger.setLevel(logging.ERROR)
+
+
+def patched_yacc(*args: Any, **kwargs: Any) -> Any:
+    # Disable generation of debug ('parser.out') and table
+    # cache ('parsetab.py'), as it requires a writable location.
+    kwargs["write_tables"] = False
+    kwargs["module"] = pypred.parser
+    # Suppress yacc warnings by using a logger that only shows errors
+    kwargs["errorlog"] = _yacc_logger
+    return _original_yacc(*args, **kwargs)
+
+
+# Apply the patch
+ply.yacc.yacc = patched_yacc
+
+
+class Predicate(OriginalPredicate):
+    """Fixed version of pypred.Predicate that uses the patched yacc parser."""
+
+    pass

rasa/utils/tensorflow/__init__.py

@@ -0,0 +1,7 @@
+import importlib.util
+import logging
+
+logger = logging.getLogger(__name__)
+
+# check if TensorFlow is available
+TENSORFLOW_AVAILABLE = importlib.util.find_spec("tensorflow") is not None

rasa/utils/tensorflow/callback.py

@@ -2,111 +2,146 @@ import logging
 from pathlib import Path
 from typing import Any, Dict, Optional, Text
 
-import tensorflow as tf
-from tqdm import tqdm
+from rasa.utils.tensorflow import TENSORFLOW_AVAILABLE
+
+if TENSORFLOW_AVAILABLE:
+    import tensorflow as tf
+    from tqdm import tqdm
+else:
+    # Placeholder values when TensorFlow is not available
+    tf = None
+    tqdm = None
 
 import rasa.shared.utils.io
 
 logger = logging.getLogger(__name__)
 
 
-class RasaTrainingLogger(tf.keras.callbacks.Callback):
-    """Callback for logging the status of training."""
-
-    def __init__(self, epochs: int, silent: bool) -> None:
-        """Initializes the callback.
-
-        Args:
-            epochs: Total number of epochs.
-            silent: If 'True' the entire progressbar wrapper is disabled.
-        """
-        super().__init__()
-
-        disable = silent or rasa.shared.utils.io.is_logging_disabled()
-        self.progress_bar = tqdm(range(epochs), desc="Epochs", disable=disable)
-
-    def on_epoch_end(self, epoch: int, logs: Optional[Dict[Text, Any]] = None) -> None:
-        """Updates the logging output on every epoch end.
-
-        Args:
-            epoch: The current epoch.
-            logs: The training metrics.
-        """
-        self.progress_bar.update(1)
-        self.progress_bar.set_postfix(logs)
-
-    def on_train_end(self, logs: Optional[Dict[Text, Any]] = None) -> None:
-        """Closes the progress bar after training.
-
-        Args:
-            logs: The training metrics.
-        """
-        self.progress_bar.close()
-
-
-class RasaModelCheckpoint(tf.keras.callbacks.Callback):
-    """Callback for saving intermediate model checkpoints."""
-
-    def __init__(self, checkpoint_dir: Path) -> None:
-        """Initializes the callback.
-
-        Args:
-            checkpoint_dir: Directory to store checkpoints to.
-        """
-        super().__init__()
-
-        self.checkpoint_file = checkpoint_dir / "checkpoint.tf_model"
-        self.best_metrics_so_far: Dict[Text, Any] = {}
-
-    def on_epoch_end(self, epoch: int, logs: Optional[Dict[Text, Any]] = None) -> None:
-        """Save the model on epoch end if the model has improved.
-
-        Args:
-            epoch: The current epoch.
-            logs: The training metrics.
-        """
-        if self._does_model_improve(logs):
-            logger.debug(f"Creating model checkpoint at epoch={epoch + 1} ...")
-            self.model.save_weights(
-                self.checkpoint_file, overwrite=True, save_format="tf"
-            )
-
-    def _does_model_improve(self, curr_results: Dict[Text, Any]) -> bool:
-        """Checks whether the current results are better than the best so far.
-
-        Results are considered better if each metric is equal or better than the best so
-        far, and at least one is better.
-
-        Args:
-            curr_results: The training metrics for this epoch.
-        """
-        curr_metric_names = [
-            k
-            for k in curr_results.keys()
-            if k.startswith("val") and (k.endswith("_acc") or k.endswith("_f1"))
-        ]
-        # the "val" prefix is prepended to metrics in fit if _should_eval returns true
-        # for this particular epoch
-        if len(curr_metric_names) == 0:
-            # the metrics are not validation metrics
-            return False
-        # initialize best_metrics_so_far with the first results
-        if not self.best_metrics_so_far:
-            for metric_name in curr_metric_names:
-                self.best_metrics_so_far[metric_name] = float(curr_results[metric_name])
-            return True
-
-        at_least_one_improved = False
-        improved_metrics = {}
-        for metric_name in self.best_metrics_so_far.keys():
-            if float(curr_results[metric_name]) < self.best_metrics_so_far[metric_name]:
-                # at least one of the values is worse
+if TENSORFLOW_AVAILABLE:
+
+    class RasaTrainingLogger(tf.keras.callbacks.Callback):
+        """Callback for logging the status of training."""
+
+        def __init__(self, epochs: int, silent: bool) -> None:
+            """Initializes the callback.
+
+            Args:
+                epochs: Total number of epochs.
+                silent: If 'True' the entire progressbar wrapper is disabled.
+            """
+            super().__init__()
+
+            disable = silent or rasa.shared.utils.io.is_logging_disabled()
+            self.progress_bar = tqdm(range(epochs), desc="Epochs", disable=disable)
+
+        def on_epoch_end(
+            self, epoch: int, logs: Optional[Dict[Text, Any]] = None
+        ) -> None:
+            """Updates the logging output on every epoch end.
+
+            Args:
+                epoch: The current epoch.
+                logs: The training metrics.
+            """
+            self.progress_bar.update(1)
+            self.progress_bar.set_postfix(logs)
+
+        def on_train_end(self, logs: Optional[Dict[Text, Any]] = None) -> None:
+            """Closes the progress bar after training.
+
+            Args:
+                logs: The training metrics.
+            """
+            self.progress_bar.close()
+
+    class RasaModelCheckpoint(tf.keras.callbacks.Callback):
+        """Callback for saving intermediate model checkpoints."""
+
+        def __init__(self, checkpoint_dir: Path) -> None:
+            """Initializes the callback.
+
+            Args:
+                checkpoint_dir: Directory to store checkpoints to.
+            """
+            super().__init__()
+
+            self.checkpoint_file = checkpoint_dir / "checkpoint.weights.h5"
+            self.best_metrics_so_far: Dict[Text, Any] = {}
+
+        def on_epoch_end(
+            self, epoch: int, logs: Optional[Dict[Text, Any]] = None
+        ) -> None:
+            """Save the model on epoch end if the model has improved.
+
+            Args:
+                epoch: The current epoch.
+                logs: The training metrics.
+            """
+            if self._does_model_improve(logs):
+                logger.debug(f"Creating model checkpoint at epoch={epoch + 1} ...")
+                # Ensure model is built before saving weights
+                if not self.model.built:
+                    # Build the model with dummy data to ensure it's built
+                    import tensorflow as tf
+
+                    dummy_input = tf.zeros((1, 1))
+                    _ = self.model(dummy_input)
+
+                # Ensure the directory exists before saving
+                import os
+
+                os.makedirs(os.path.dirname(self.checkpoint_file), exist_ok=True)
+                self.model.save_weights(self.checkpoint_file, overwrite=True)
+
+        def _does_model_improve(self, curr_results: Dict[Text, Any]) -> bool:
+            """Checks whether the current results are better than the best so far.
+
+            Results are considered better if each metric is
+            equal or better than the best so far, and at least one is better.
+
+            Args:
+                curr_results: The training metrics for this epoch.
+            """
+            curr_metric_names = [
+                k
+                for k in curr_results.keys()
+                if k.startswith("val") and (k.endswith("_acc") or k.endswith("_f1"))
+            ]
+            # the "val" prefix is prepended to metrics in fit
+            # if _should_eval returns true
+            # for this particular epoch
+            if len(curr_metric_names) == 0:
+                # the metrics are not validation metrics
                 return False
-            if float(curr_results[metric_name]) > self.best_metrics_so_far[metric_name]:
-                at_least_one_improved = True
-                improved_metrics[metric_name] = float(curr_results[metric_name])
-
-        # all current values >= previous best and at least one is better
-        if at_least_one_improved:
-            self.best_metrics_so_far.update(improved_metrics)
-        return at_least_one_improved
+            # initialize best_metrics_so_far with the first results
+            if not self.best_metrics_so_far:
+                for metric_name in curr_metric_names:
+                    self.best_metrics_so_far[metric_name] = float(
+                        curr_results[metric_name]
+                    )
+                    return True
+
+            at_least_one_improved = False
+            improved_metrics = {}
+            for metric_name in self.best_metrics_so_far.keys():
+                if (
+                    float(curr_results[metric_name])
+                    < self.best_metrics_so_far[metric_name]
+                ):
+                    # at least one of the values is worse
+                    return False
+                if (
+                    float(curr_results[metric_name])
+                    > self.best_metrics_so_far[metric_name]
+                ):
+                    at_least_one_improved = True
+                    improved_metrics[metric_name] = float(curr_results[metric_name])
+
+            # all current values >= previous best and at least one is better
+            if at_least_one_improved:
+                self.best_metrics_so_far.update(improved_metrics)
+            return at_least_one_improved
+else:
+    # Placeholder classes when TensorFlow is not available
+    RasaTrainingLogger = None  # type: ignore
+    RasaModelCheckpoint = None  # type: ignore

rasa/utils/tensorflow/crf.py

@@ -9,7 +9,7 @@ from tensorflow.types.experimental import TensorLike
 # (modified to our neeeds)
 
 
-class CrfDecodeForwardRnnCell(tf.keras.layers.AbstractRNNCell):
+class CrfDecodeForwardRnnCell(tf.keras.layers.Layer):
     """Computes the forward decoding in a linear-chain CRF."""
 
     def __init__(self, transition_params: TensorLike, **kwargs: Any) -> None:

rasa/utils/tensorflow/data_generator.py

@@ -71,13 +71,22 @@ class RasaDataGenerator(Sequence):
         # balancing on the next epoch
         return data
 
+    @staticmethod
+    def _create_default_array() -> np.ndarray:
+        """Create a default empty array for missing features.
+
+        Returns:
+            A default empty array with shape (0, 1) and dtype float32.
+        """
+        return np.zeros((0, 1), dtype=np.float32)
+
     @staticmethod
     def prepare_batch(
         data: Data,
         start: Optional[int] = None,
         end: Optional[int] = None,
         tuple_sizes: Optional[Dict[Text, int]] = None,
-    ) -> Tuple[Optional[np.ndarray], ...]:
+    ) -> Tuple[np.ndarray, ...]:
         """Slices model data into batch using given start and end value.
 
         Args:
@@ -85,8 +94,8 @@ class RasaDataGenerator(Sequence):
             start: The start index of the batch
             end: The end index of the batch
             tuple_sizes: In case the feature is not present we propagate the batch with
-              None. Tuple sizes contains the number of how many None values to add for
-              what kind of feature.
+              default arrays. Tuple sizes contains the number of how many default values
+              to add for what kind of feature.
 
         Returns:
             The features of the batch.
@@ -95,12 +104,14 @@ class RasaDataGenerator(Sequence):
 
         for key, attribute_data in data.items():
             for sub_key, f_data in attribute_data.items():
-                # add None for not present values during processing
+                # add default arrays for not present values during processing
                 if not f_data:
                     if tuple_sizes:
-                        batch_data += [None] * tuple_sizes[key]
+                        batch_data += [
+                            RasaDataGenerator._create_default_array()
+                        ] * tuple_sizes[key]
                     else:
-                        batch_data.append(None)
+                        batch_data.append(RasaDataGenerator._create_default_array())
                     continue
 
                 for v in f_data:
@@ -409,8 +420,10 @@ class RasaBatchDataGenerator(RasaDataGenerator):
         end = start + self._current_batch_size
 
         # return input and target data, as our target data is inside the input
-        # data return None for the target data
-        return self.prepare_batch(self._data, start, end), None
+        # data return default array for the target data
+        return self.prepare_batch(
+            self._data, start, end
+        ), RasaDataGenerator._create_default_array()
 
     def on_epoch_end(self) -> None:
         """Update the data after every epoch."""

rasa/utils/tensorflow/layers.py

@@ -3,9 +3,7 @@ from typing import Any, Callable, List, Optional, Text, Tuple, Union
 
 import tensorflow as tf
 import tensorflow.keras.backend as K
-
-# TODO: The following is not (yet) available via tf.keras
-from keras.src.utils.control_flow_util import smart_cond
+from tensorflow.python.keras.utils.control_flow_util import smart_cond
 
 import rasa.utils.tensorflow.crf
 import rasa.utils.tensorflow.layers_utils as layers_utils
@@ -278,6 +276,7 @@ class RandomlyConnectedDense(tf.keras.layers.Dense):
             kernel_constraint: Constraint function applied to
                 the `kernel` weights matrix.
             bias_constraint: Constraint function applied to the bias vector.
+            **kwargs: Additional keyword arguments passed to the parent class.
         """
         super().__init__(**kwargs)
 
@@ -298,16 +297,19 @@ class RandomlyConnectedDense(tf.keras.layers.Dense):
             self.kernel_mask = None
             return
 
-        # Construct mask with given density and guarantee that every output is
-        # connected to at least one input
-        kernel_mask = self._minimal_mask() + self._random_mask()
+        # Use callable initializer for TensorFlow 2.19.1 compatibility
+        def kernel_mask_initializer() -> tf.Tensor:
+            # Construct mask with given density and guarantee that every output is
+            # connected to at least one input
+            kernel_mask = self._minimal_mask() + self._random_mask()
 
-        # We might accidently have added a random connection on top of
-        # a fixed connection
-        kernel_mask = tf.clip_by_value(kernel_mask, 0, 1)
+            # We might accidently have added a random connection on top of
+            # a fixed connection
+            kernel_mask = tf.clip_by_value(kernel_mask, 0, 1)
+            return kernel_mask
 
         self.kernel_mask = tf.Variable(
-            initial_value=kernel_mask, trainable=False, name="kernel_mask"
+            initial_value=kernel_mask_initializer, trainable=False, name="kernel_mask"
         )
 
     def _random_mask(self) -> tf.Tensor:
@@ -367,7 +369,12 @@ class RandomlyConnectedDense(tf.keras.layers.Dense):
         Returns:
             The processed inputs.
         """
-        if self.density < 1.0:
+        # Apply kernel masking if needed (Keras 3.x compatibility check)
+        if (
+            self.density < 1.0
+            and hasattr(self, "kernel_mask")
+            and self.kernel_mask is not None
+        ):
             # Set fraction of the `kernel` weights to zero according to precomputed mask
             self.kernel.assign(self.kernel * self.kernel_mask)
         return super().call(inputs)
@@ -724,6 +731,7 @@ class DotProductLoss(tf.keras.layers.Layer):
                 Currently, the only possible value is `SOFTMAX`.
             similarity_type: Similarity measure to use, either `cosine` or `inner`.
             name: Optional name of the layer.
+            **kwargs: Additional keyword arguments passed to the parent class.
 
         Raises:
             TFLayerConfigException: When `similarity_type` is not one of `COSINE` or
@@ -883,6 +891,7 @@ class SingleLabelDotProductLoss(DotProductLoss):
                 values are approximately bounded.
             model_confidence: Normalization of confidence values during inference.
                 Currently, the only possible value is `SOFTMAX`.
+            **kwargs: Additional keyword arguments passed to the parent class.
         """
         super().__init__(
             num_candidates,
@@ -1244,6 +1253,7 @@ class MultiLabelDotProductLoss(DotProductLoss):
                 Used inside _loss_cross_entropy() only.
             model_confidence: Normalization of confidence values during inference.
                 Currently, the only possible value is `SOFTMAX`.
+            **kwargs: Additional keyword arguments passed to the parent class.
         """
         super().__init__(
             num_candidates,

rasa/utils/tensorflow/metrics.py

@@ -1,7 +1,6 @@
 from typing import Any, Dict, Optional
 
 import tensorflow as tf
-from tensorflow.keras import backend as K
 from tensorflow.types.experimental import TensorLike
 
 # original code taken from
@@ -118,7 +117,7 @@ class FBetaScore(tf.keras.metrics.Metric):
 
         def _zero_wt_init(name: Any) -> Any:
             return self.add_weight(
-                name, shape=self.init_shape, initializer="zeros", dtype=self.dtype
+                name=name, shape=self.init_shape, initializer="zeros", dtype=self.dtype
             )
 
         self.true_positives = _zero_wt_init("true_positives")
@@ -197,7 +196,12 @@ class FBetaScore(tf.keras.metrics.Metric):
 
     def reset_state(self) -> None:
         reset_value = tf.zeros(self.init_shape, dtype=self.dtype)
-        K.batch_set_value([(v, reset_value) for v in self.variables])
+        # In Keras 3.x, self.variables contains string names, not variable objects,
+        # so each metric variable is reset using assign() instead of K.batch_set_value()
+        self.true_positives.assign(reset_value)
+        self.false_positives.assign(reset_value)
+        self.false_negatives.assign(reset_value)
+        self.weights_intermediate.assign(reset_value)
 
     def reset_states(self) -> None:
         # Backwards compatibility alias of `reset_state`. New classes should