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

rasa/graph_components/validators/default_recipe_validator.py

@@ -10,22 +10,13 @@ from rasa.core.policies.flow_policy import FlowPolicy
 from rasa.core.policies.memoization import AugmentedMemoizationPolicy, MemoizationPolicy
 from rasa.core.policies.policy import Policy, SupportedData
 from rasa.core.policies.rule_policy import RulePolicy
-from rasa.core.policies.ted_policy import TEDPolicy
-from rasa.core.policies.unexpected_intent_policy import UnexpecTEDIntentPolicy
 from rasa.engine.graph import ExecutionContext, GraphComponent, GraphSchema, SchemaNode
 from rasa.engine.storage.resource import Resource
 from rasa.engine.storage.storage import ModelStorage
-from rasa.nlu.classifiers.diet_classifier import DIETClassifier
-from rasa.nlu.extractors.crf_entity_extractor import (
-    CRFEntityExtractor,
-    CRFEntityExtractorOptions,
-)
 from rasa.nlu.extractors.entity_synonyms import EntitySynonymMapper
-from rasa.nlu.extractors.mitie_entity_extractor import MitieEntityExtractor
 from rasa.nlu.extractors.regex_entity_extractor import RegexEntityExtractor
 from rasa.nlu.featurizers.featurizer import Featurizer
 from rasa.nlu.featurizers.sparse_featurizer.regex_featurizer import RegexFeaturizer
-from rasa.nlu.selectors.response_selector import ResponseSelector
 from rasa.nlu.tokenizers.tokenizer import Tokenizer
 from rasa.shared.constants import (
     DEFAULT_CONFIG_PATH,
@@ -45,11 +36,45 @@ from rasa.shared.core.training_data.structures import RuleStep, StoryGraph
 from rasa.shared.exceptions import InvalidConfigException
 from rasa.shared.importers.importer import TrainingDataImporter
 from rasa.shared.nlu.training_data.training_data import TrainingData
+from rasa.shared.utils.common import conditional_import
 
-# TODO: Can we replace this with the registered types from the regitry?
-TRAINABLE_EXTRACTORS = [MitieEntityExtractor, CRFEntityExtractor, DIETClassifier]
+# Conditional imports for TensorFlow-dependent components
+TEDPolicy, TED_POLICY_AVAILABLE = conditional_import(
+    "rasa.core.policies.ted_policy", "TEDPolicy"
+)
+UnexpecTEDIntentPolicy, UNEXPECTED_INTENT_POLICY_AVAILABLE = conditional_import(
+    "rasa.core.policies.unexpected_intent_policy", "UnexpecTEDIntentPolicy"
+)
+DIETClassifier, DIET_CLASSIFIER_AVAILABLE = conditional_import(
+    "rasa.nlu.classifiers.diet_classifier", "DIETClassifier"
+)
+ResponseSelector, RESPONSE_SELECTOR_AVAILABLE = conditional_import(
+    "rasa.nlu.selectors.response_selector", "ResponseSelector"
+)
+
+# Conditional imports for nlu components requiring other dependencies than tensorflow
+MitieEntityExtractor, MITIE_ENTITY_EXTRACTOR_AVAILABLE = conditional_import(
+    "rasa.nlu.extractors.mitie_entity_extractor", "MitieEntityExtractor"
+)
+CRFEntityExtractor, CRF_ENTITY_EXTRACTOR_AVAILABLE = conditional_import(
+    "rasa.nlu.extractors.crf_entity_extractor", "CRFEntityExtractor"
+)
+CRFEntityExtractorOptions, _ = conditional_import(
+    "rasa.nlu.extractors.crf_entity_extractor", "CRFEntityExtractorOptions"
+)
+
+# TODO: Can we replace this with the registered types from the registry?
+TRAINABLE_EXTRACTORS = []
+if CRF_ENTITY_EXTRACTOR_AVAILABLE:
+    TRAINABLE_EXTRACTORS.append(CRFEntityExtractor)
+if MITIE_ENTITY_EXTRACTOR_AVAILABLE:
+    TRAINABLE_EXTRACTORS.append(MitieEntityExtractor)
+if DIET_CLASSIFIER_AVAILABLE:
+    TRAINABLE_EXTRACTORS.append(DIETClassifier)
 # TODO: replace these once the Recipe is merged (used in tests)
-POLICY_CLASSSES = {TEDPolicy, MemoizationPolicy, RulePolicy}
+POLICY_CLASSSES = {MemoizationPolicy, RulePolicy}
+if TED_POLICY_AVAILABLE:
+    POLICY_CLASSSES.add(TEDPolicy)
 
 
 def _types_to_str(types: Iterable[Type]) -> Text:
@@ -158,18 +183,27 @@ class DefaultV1RecipeValidator(GraphComponent):
                 docs=DOCS_URL_COMPONENTS,
             )
 
+        available_extractors = {DIETClassifier}
+        if CRF_ENTITY_EXTRACTOR_AVAILABLE:
+            available_extractors.add(CRFEntityExtractor)
+
         if training_data.entity_examples and self._component_types.isdisjoint(
-            {DIETClassifier, CRFEntityExtractor}
+            available_extractors
         ):
             if training_data.entity_roles_groups_used():
+                crf_name = (
+                    CRFEntityExtractor.__name__
+                    if CRFEntityExtractor
+                    else "CRFEntityExtractor"
+                )
                 rasa.shared.utils.io.raise_warning(
                     f"You have defined training data with entities that "
                     f"have roles/groups, but your NLU configuration does not "
                     f"include a '{DIETClassifier.__name__}' "
-                    f"or a '{CRFEntityExtractor.__name__}'. "
+                    f"or a '{crf_name}'. "
                     f"To train entities that have roles/groups, "
                     f"add either '{DIETClassifier.__name__}' "
-                    f"or '{CRFEntityExtractor.__name__}' to your "
+                    f"or '{crf_name}' to your "
                     f"configuration.",
                     docs=DOCS_URL_COMPONENTS,
                 )
@@ -203,7 +237,16 @@ class DefaultV1RecipeValidator(GraphComponent):
             )
 
         if training_data.lookup_tables:
-            if self._component_types.isdisjoint([CRFEntityExtractor, DIETClassifier]):
+            lookup_extractors = [DIETClassifier]
+            if CRF_ENTITY_EXTRACTOR_AVAILABLE:
+                lookup_extractors.append(CRFEntityExtractor)
+
+            if self._component_types.isdisjoint(lookup_extractors):
+                crf_name = (
+                    CRFEntityExtractor.__name__
+                    if CRFEntityExtractor
+                    else "CRFEntityExtractor"
+                )
                 rasa.shared.utils.io.raise_warning(
                     f"You have defined training data consisting of lookup tables, but "
                     f"your NLU configuration does not include any components "
@@ -211,33 +254,45 @@ class DefaultV1RecipeValidator(GraphComponent):
                     f"To make use of the features that are created with the "
                     f"help of the lookup tables, "
                     f"add a '{DIETClassifier.__name__}' or a "
-                    f"'{CRFEntityExtractor.__name__}' "
+                    f"'{crf_name}' "
                     f"with the 'pattern' feature "
                     f"to your configuration.",
                     docs=DOCS_URL_COMPONENTS,
                 )
 
-            elif CRFEntityExtractor in self._component_types:
+            elif (
+                CRF_ENTITY_EXTRACTOR_AVAILABLE
+                and CRFEntityExtractor in self._component_types
+            ):
                 crf_schema_nodes = [
                     schema_node
                     for schema_node in self._graph_schema.nodes.values()
                     if schema_node.uses == CRFEntityExtractor
                 ]
-                has_pattern_feature = any(
-                    CRFEntityExtractorOptions.PATTERN in feature_list
-                    for crf in crf_schema_nodes
-                    for feature_list in crf.config.get("features", [])
+                has_pattern_feature = (
+                    any(
+                        CRFEntityExtractorOptions.PATTERN in feature_list
+                        for crf in crf_schema_nodes
+                        for feature_list in crf.config.get("features", [])
+                    )
+                    if CRFEntityExtractorOptions
+                    else False
                 )
 
                 if not has_pattern_feature:
+                    crf_name = (
+                        CRFEntityExtractor.__name__
+                        if CRFEntityExtractor
+                        else "CRFEntityExtractor"
+                    )
                     rasa.shared.utils.io.raise_warning(
                         f"You have defined training data consisting of "
                         f"lookup tables, but your NLU configuration's "
-                        f"'{CRFEntityExtractor.__name__}' "
+                        f"'{crf_name}' "
                         f"does not include the "
                         f"'pattern' feature. To featurize lookup tables, "
                         f"add the 'pattern' feature to the "
-                        f"'{CRFEntityExtractor.__name__}' "
+                        f"'{crf_name}' "
                         "in your configuration.",
                         docs=DOCS_URL_COMPONENTS,
                     )
@@ -446,13 +501,16 @@ class DefaultV1RecipeValidator(GraphComponent):
             return
 
         # if we are using a flow policy, there shouldn't be any dm1 policies
-        dm1_policies = (
+        dm1_policies_list = [
             RulePolicy,
-            TEDPolicy,
             MemoizationPolicy,
             AugmentedMemoizationPolicy,
-            UnexpecTEDIntentPolicy,
-        )
+        ]
+        if TED_POLICY_AVAILABLE:
+            dm1_policies_list.append(TEDPolicy)
+        if UNEXPECTED_INTENT_POLICY_AVAILABLE:
+            dm1_policies_list.append(UnexpecTEDIntentPolicy)
+        dm1_policies = tuple(dm1_policies_list)
 
         for schema_node in self._graph_schema.nodes.values():
             if issubclass(schema_node.uses, dm1_policies):

rasa/hooks.py

@@ -19,7 +19,7 @@ hookimpl = pluggy.HookimplMarker("rasa")
 logger = logging.getLogger(__name__)
 
 
-@hookimpl  # type: ignore[misc]
+@hookimpl
 def refine_cli(
     subparsers: "SubParsersAction",
     parent_parsers: List[argparse.ArgumentParser],
@@ -37,7 +37,7 @@ def refine_cli(
     return None
 
 
-@hookimpl  # type: ignore[misc]
+@hookimpl
 def configure_commandline(cmdline_arguments: argparse.Namespace) -> Optional[Text]:
     from rasa.cli import x as rasa_x
     from rasa.tracing import config
@@ -59,21 +59,21 @@ def configure_commandline(cmdline_arguments: argparse.Namespace) -> Optional[Tex
     return endpoints_file
 
 
-@hookimpl  # type: ignore[misc]
+@hookimpl
 def init_telemetry(endpoints_file: Optional[Text]) -> None:
     import rasa.telemetry
 
     rasa.telemetry.identify_endpoint_config_traits(endpoints_file)
 
 
-@hookimpl  # type: ignore[misc]
+@hookimpl
 def init_managers(endpoints_file: Optional[Text]) -> None:
     from rasa.core.secrets_manager.factory import load_secret_manager
 
     load_secret_manager(endpoints_file)
 
 
-@hookimpl  # type: ignore[misc]
+@hookimpl
 def create_tracker_store(
     endpoint_config: Union["TrackerStore", "EndpointConfig"],
     domain: "Domain",

rasa/llm_fine_tuning/utils.py

@@ -61,9 +61,9 @@ def patch_invoke_llm_in_generators(mock_impl: Callable) -> Generator:
     try:
         # apply the monkey-patch everywhere
         for cls in originals:
-            cls.invoke_llm = mock_impl  # type: ignore[assignment]
+            cls.invoke_llm = mock_impl  # type: ignore[method-assign]
         yield
     finally:
         # restore originals (even if an exception happened)
         for cls, orig in originals.items():
-            cls.invoke_llm = orig  # type: ignore[assignment]
+            cls.invoke_llm = orig  # type: ignore[method-assign]

rasa/model_manager/model_api.py

@@ -39,11 +39,9 @@ from rasa.model_manager.trainer_service import (
     update_training_status,
 )
 from rasa.model_manager.utils import (
-    InvalidPathException,
     get_logs_content,
     logs_base_path,
     models_base_path,
-    subpath,
 )
 from rasa.model_manager.warm_rasa_process import (
     initialize_warm_rasa_process,
@@ -53,6 +51,7 @@ from rasa.server import ErrorResponse
 from rasa.shared.exceptions import InvalidConfigException
 from rasa.shared.utils.yaml import dump_obj_as_yaml_to_string
 from rasa.studio.upload import build_calm_import_parts
+from rasa.utils.io import InvalidPathException, subpath
 
 dotenv.load_dotenv()
 
@@ -571,10 +570,10 @@ def external_blueprint() -> Blueprint:
     """Create a blueprint for the model manager API."""
     from rasa.core.channels.socketio import SocketBlueprint
 
-    sio = AsyncServer(async_mode="sanic", cors_allowed_origins="*")
-    bp = SocketBlueprint(sio, "", "model_api_external")
+    sio_server = AsyncServer(async_mode="sanic", cors_allowed_origins="*")
+    bp = SocketBlueprint(sio_server, "", "model_api_external")
 
-    create_bridge_server(sio, running_bots)
+    create_bridge_server(sio_server, running_bots)
 
     @bp.get("/health")
     async def health(request: Request) -> response.HTTPResponse:

rasa/model_manager/runner_service.py

@@ -15,11 +15,11 @@ from rasa.model_manager import config
 from rasa.model_manager.utils import (
     logs_path,
     models_base_path,
-    subpath,
     write_encoded_data_to_file,
 )
 from rasa.model_manager.warm_rasa_process import start_rasa_process
 from rasa.studio.prompts import handle_prompts
+from rasa.utils.io import subpath
 
 structlogger = structlog.get_logger()
 
@@ -195,7 +195,7 @@ def fetch_remote_model_to_dir(
     try:
         return persistor.retrieve(model_name=model_name, target_path=target_path)
     except FileNotFoundError as e:
-        raise ModelNotFound() from e
+        raise ModelNotFound("Model not found") from e
 
 
 def fetch_size_of_remote_model(

rasa/model_manager/socket_bridge.py

@@ -1,9 +1,7 @@
-import json
 from typing import Any, Dict, Optional
 
 import structlog
-from socketio import AsyncServer
-from socketio.asyncio_client import AsyncClient
+from socketio import AsyncClient, AsyncServer  # type: ignore[attr-defined]
 from socketio.exceptions import ConnectionRefusedError
 
 from rasa.model_manager.runner_service import BotSession
@@ -20,7 +18,7 @@ socket_proxy_clients = {}
 
 
 async def socketio_websocket_traffic_wrapper(
-    sio: AsyncServer,
+    sio_server: AsyncServer,
     running_bots: Dict[str, BotSession],
     sid: str,
     auth: Optional[Dict],
@@ -56,7 +54,9 @@ async def socketio_websocket_traffic_wrapper(
         structlogger.error("model_runner.bot_not_alive", deployment_id=deployment_id)
         raise ConnectionRefusedError("model_runner.bot_not_alive")
 
-    client = await create_bridge_client(sio, bot.internal_url, sid, deployment_id)
+    client = await create_bridge_client(
+        sio_server, bot.internal_url, sid, deployment_id
+    )
 
     if client.sid is not None:
         structlogger.debug(
@@ -71,20 +71,24 @@ async def socketio_websocket_traffic_wrapper(
         raise ConnectionRefusedError("model_runner.bot_connection_failed")
 
 
-def create_bridge_server(sio: AsyncServer, running_bots: Dict[str, BotSession]) -> None:
+def create_bridge_server(
+    sio_server: AsyncServer, running_bots: Dict[str, BotSession]
+) -> None:
     """Create handlers for the socket server side.
 
     Forwards messages coming from the user to the bot.
     """
 
-    @sio.on("connect")
+    @sio_server.on("connect")
     async def socketio_websocket_traffic(
         sid: str, environ: Dict, auth: Optional[Dict]
     ) -> bool:
         """Bridge websockets between user chat socket and bot server."""
-        return await socketio_websocket_traffic_wrapper(sio, running_bots, sid, auth)
+        return await socketio_websocket_traffic_wrapper(
+            sio_server, running_bots, sid, auth
+        )
 
-    @sio.on("disconnect")
+    @sio_server.on("disconnect")
     async def disconnect(sid: str) -> None:
         """Disconnect the bot connection."""
         structlogger.debug("model_runner.bot_disconnect", sid=sid)
@@ -92,7 +96,7 @@ def create_bridge_server(sio: AsyncServer, running_bots: Dict[str, BotSession])
             await socket_proxy_clients[sid].disconnect()
             del socket_proxy_clients[sid]
 
-    @sio.on("*")
+    @sio_server.on("*")
     async def handle_message(event: str, sid: str, data: Dict[str, Any]) -> None:
         """Bridge messages between user and bot.
 
@@ -109,7 +113,7 @@ def create_bridge_server(sio: AsyncServer, running_bots: Dict[str, BotSession])
 
 
 async def create_bridge_client(
-    sio: AsyncServer, url: str, sid: str, deployment_id: str
+    sio_server: AsyncServer, url: str, sid: str, deployment_id: str
 ) -> AsyncClient:
     """Create a new socket bridge client.
 
@@ -124,36 +128,36 @@ async def create_bridge_client(
         structlogger.debug(
             "model_runner.bot_session_confirmed", deployment_id=deployment_id
         )
-        await sio.emit("session_confirm", room=sid)
+        await sio_server.emit("session_confirm", room=sid)
 
     @client.event  # type: ignore[misc]
     async def bot_message(data: Dict[str, Any]) -> None:
         structlogger.debug("model_runner.bot_message", deployment_id=deployment_id)
-        await sio.emit("bot_message", data, room=sid)
+        await sio_server.emit("bot_message", data, room=sid)
 
     @client.event  # type: ignore[misc]
     async def error(data: Dict[str, Any]) -> None:
         structlogger.debug(
             "model_runner.bot_error", deployment_id=deployment_id, data=data
         )
-        await sio.emit("error", data, room=sid)
+        await sio_server.emit("error", data, room=sid)
 
     @client.event  # type: ignore[misc]
     async def tracker(data: Dict[str, Any]) -> None:
-        await sio.emit("tracker", json.loads(data), room=sid)
+        await sio_server.emit("tracker", data, room=sid)
 
     @client.event  # type: ignore[misc]
     async def disconnect() -> None:
         structlogger.debug(
             "model_runner.bot_connection_closed", deployment_id=deployment_id
         )
-        await sio.emit("disconnect", room=sid)
+        await sio_server.emit("disconnect", room=sid)
 
     @client.event  # type: ignore[misc]
     async def connect_error() -> None:
         structlogger.error(
             "model_runner.bot_connection_error", deployment_id=deployment_id
         )
-        await sio.emit("disconnect", room=sid)
+        await sio_server.emit("disconnect", room=sid)
 
     return client

rasa/model_manager/trainer_service.py

@@ -14,7 +14,6 @@ from rasa.model_manager.utils import (
     ensure_base_directory_exists,
     logs_path,
     models_base_path,
-    subpath,
     write_encoded_data_to_file,
 )
 from rasa.model_manager.warm_rasa_process import (
@@ -22,6 +21,7 @@ from rasa.model_manager.warm_rasa_process import (
 )
 from rasa.model_training import generate_random_model_name
 from rasa.studio.prompts import handle_prompts
+from rasa.utils.io import subpath
 
 structlogger = structlog.get_logger()
 
@@ -53,6 +53,15 @@ class TrainingSession(BaseModel):
         """Check if the training is running."""
         return self.status == TrainingSessionStatus.RUNNING
 
+    def has_just_finished(self) -> bool:
+        if not self.is_status_indicating_alive():
+            # skip if the training is not running
+            return False
+        if self.process.poll() is None:
+            # process is still running
+            return False
+        return True
+
     def model_path(self) -> str:
         """Return the path to the model."""
         return subpath(models_base_path(), f"{self.model_name}.tar.gz")
@@ -89,14 +98,8 @@ def terminate_training(training: TrainingSession) -> None:
 
 
 def update_training_status(training: TrainingSession) -> None:
-    if not training.is_status_indicating_alive():
-        # skip if the training is not running
-        return
-    if training.process.poll() is None:
-        # process is still running
-        return
-
-    complete_training(training)
+    if training.has_just_finished():
+        complete_training(training)
 
 
 def complete_training(training: TrainingSession) -> None:

rasa/model_manager/utils.py

@@ -5,15 +5,11 @@ from typing import Optional
 import structlog
 
 from rasa.model_manager import config
-from rasa.shared.exceptions import RasaException
+from rasa.utils.io import subpath
 
 structlogger = structlog.get_logger()
 
 
-class InvalidPathException(RasaException):
-    """Raised if a path is invalid - e.g. path traversal is detected."""
-
-
 def write_encoded_data_to_file(encoded_data: bytes, file: str) -> None:
     """Write base64 encoded data to a file."""
     # create the directory if it does not exist of the parent directory
@@ -53,30 +49,6 @@ def logs_path(action_id: str) -> str:
     return subpath(logs_base_path(), f"{action_id}.txt")
 
 
-def subpath(parent: str, child: str) -> str:
-    """Return the path to the child directory of the parent directory.
-
-    Ensures, that child doesn't navigate to parent directories. Prevents
-    path traversal. Raises an InvalidPathException if the path is invalid.
-
-    Based on Snyk's directory traversal mitigation:
-    https://learn.snyk.io/lesson/directory-traversal/
-    """
-    safe_path = os.path.abspath(os.path.join(parent, child))
-    parent = os.path.abspath(parent)
-
-    common_base = os.path.commonpath([parent, safe_path])
-    if common_base != parent:
-        raise InvalidPathException(f"Invalid path: {safe_path}")
-
-    if os.path.basename(safe_path) != child:
-        raise InvalidPathException(
-            f"Invalid path - path traversal detected: {safe_path}"
-        )
-
-    return safe_path
-
-
 def get_logs_content(action_id: str) -> Optional[str]:
     """Return the content of the log file for a given action id."""
     try:

rasa/model_manager/warm_rasa_process.py

@@ -1,6 +1,7 @@
 import os
 import shlex
 import subprocess
+import time
 import uuid
 from dataclasses import dataclass
 from typing import List
@@ -149,19 +150,28 @@ def warmup() -> None:
     We import them now, so that the training / deployment can later
     directly start.
     """
+    start_time = time.time()
     try:
         import langchain  # noqa: F401
         import litellm  # noqa: F401
         import matplotlib  # noqa: F401
         import numpy  # noqa: F401
         import pandas  # noqa: F401
-        import presidio_analyzer  # noqa: F401
-        import spacy  # noqa: F401
         import tensorflow  # noqa: F401
 
         import rasa.validator  # noqa: F401
-    except ImportError:
+    except ImportError as e:
+        structlogger.warning(
+            "model_trainer.warmup_error",
+            error=str(e),
+        )
         pass
+    finally:
+        end_time = time.time()
+        structlogger.debug(
+            "model_trainer.warmup_time",
+            time_in_seconds=end_time - start_time,
+        )
 
 
 def warm_rasa_main() -> None: