rasa-pro 3.12.18.dev1__py3-none-any.whl → 3.13.0a1.dev2__py3-none-any.whl

rasa/engine/validation.py

@@ -23,9 +23,10 @@ import structlog
 import typing_utils
 
 import rasa.utils.common
-from rasa.core import ContextualResponseRephraser, IntentlessPolicy
+from rasa.core.available_endpoints import AvailableEndpoints
+from rasa.core.nlg.contextual_response_rephraser import ContextualResponseRephraser
+from rasa.core.policies.intentless_policy import IntentlessPolicy
 from rasa.core.policies.policy import PolicyPrediction
-from rasa.core.utils import AvailableEndpoints
 from rasa.dialogue_understanding.coexistence.constants import (
     CALM_ENTRY,
     NLU_ENTRY,

rasa/hooks.py

@@ -1,36 +1,22 @@
 import argparse
 import logging
-import os
 from typing import TYPE_CHECKING, List, Optional, Text, Union
 
-import litellm
 import pluggy
-import structlog
-
-from rasa.shared.providers.constants import (
-    LANGFUSE_CALLBACK_NAME,
-    LANGFUSE_HOST_ENV_VAR,
-    LANGFUSE_PROJECT_ID_ENV_VAR,
-    LANGFUSE_PUBLIC_KEY_ENV_VAR,
-    LANGFUSE_SECRET_KEY_ENV_VAR,
-    RASA_LANGFUSE_INTEGRATION_ENABLED_ENV_VAR,
-)
 
 # IMPORTANT: do not import anything from rasa here - use scoped imports
 #  this avoids circular imports, as the hooks are used in different places
 #  across the codebase.
 
 if TYPE_CHECKING:
-    from rasa.anonymization.anonymization_pipeline import AnonymizationPipeline
     from rasa.cli import SubParsersAction
     from rasa.core.brokers.broker import EventBroker
-    from rasa.core.tracker_store import TrackerStore
+    from rasa.core.tracker_stores.tracker_store import TrackerStore
     from rasa.shared.core.domain import Domain
     from rasa.utils.endpoints import EndpointConfig
 
 hookimpl = pluggy.HookimplMarker("rasa")
 logger = logging.getLogger(__name__)
-structlogger = structlog.get_logger()
 
 
 @hookimpl  # type: ignore[misc]
@@ -70,8 +56,6 @@ def configure_commandline(cmdline_arguments: argparse.Namespace) -> Optional[Tex
         config.configure_tracing(tracer_provider)
         config.configure_metrics(endpoints_file)
 
-    _init_langfuse_integration()
-
     return endpoints_file
 
 
@@ -95,7 +79,7 @@ def create_tracker_store(
     domain: "Domain",
     event_broker: Optional["EventBroker"],
 ) -> "TrackerStore":
-    from rasa.core.auth_retry_tracker_store import AuthRetryTrackerStore
+    from rasa.core.tracker_stores.auth_retry_tracker_store import AuthRetryTrackerStore
     from rasa.utils.endpoints import EndpointConfig
 
     if isinstance(endpoint_config, EndpointConfig):
@@ -103,70 +87,3 @@ def create_tracker_store(
             endpoint_config=endpoint_config, domain=domain, event_broker=event_broker
         )
     return endpoint_config
-
-
-@hookimpl  # type: ignore[misc]
-def init_anonymization_pipeline(endpoints_file: Optional[Text]) -> None:
-    """Hook implementation for initializing the anonymization pipeline."""
-    from rasa.anonymization.anonymization_pipeline import load_anonymization_pipeline
-
-    load_anonymization_pipeline(endpoints_file)
-
-
-@hookimpl  # type: ignore[misc]
-def get_anonymization_pipeline() -> Optional["AnonymizationPipeline"]:
-    """Hook implementation for getting the anonymization pipeline."""
-    from rasa.anonymization.anonymization_pipeline import AnonymizationPipelineProvider
-
-    return AnonymizationPipelineProvider().get_anonymization_pipeline()
-
-
-@hookimpl  # type: ignore[misc]
-def after_server_stop() -> None:
-    """Hook implementation for stopping the anonymization pipeline."""
-    from rasa.anonymization.anonymization_pipeline import AnonymizationPipelineProvider
-
-    anon_pipeline = AnonymizationPipelineProvider().get_anonymization_pipeline()
-
-    if anon_pipeline is not None:
-        anon_pipeline.stop()
-
-
-def _is_langfuse_integration_enabled() -> bool:
-    return (
-        os.environ.get(RASA_LANGFUSE_INTEGRATION_ENABLED_ENV_VAR, "false").lower()
-        == "true"
-    )
-
-
-def _init_langfuse_integration() -> None:
-    if not _is_langfuse_integration_enabled():
-        structlogger.info(
-            "hooks._init_langfuse_integration.disabled",
-            event_info="Langfuse integration is disabled.",
-        )
-        return
-
-    if (
-        not os.environ.get(LANGFUSE_HOST_ENV_VAR)
-        or not os.environ.get(LANGFUSE_PROJECT_ID_ENV_VAR)
-        or not os.environ.get(LANGFUSE_PUBLIC_KEY_ENV_VAR)
-        or not os.environ.get(LANGFUSE_SECRET_KEY_ENV_VAR)
-    ):
-        structlogger.warning(
-            "hooks._init_langfuse_integration.missing_langfuse_keys",
-            event_info=(
-                "Langfuse integration is enabled, but some environment variables "
-                "are missing. Please set LANGFUSE_HOST, LANGFUSE_PROJECT_ID, "
-                "LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY environment "
-                "variables to use Langfuse integration."
-            ),
-        )
-        return
-
-    litellm.success_callback = [LANGFUSE_CALLBACK_NAME]
-    litellm.failure_callback = [LANGFUSE_CALLBACK_NAME]
-    structlogger.info(
-        "hooks.langfuse_callbacks_initialized",
-        event_info="Langfuse integration initialized.",
-    )

rasa/llm_fine_tuning/paraphrasing/conversation_rephraser.py

@@ -22,11 +22,7 @@ from rasa.shared.constants import (
 from rasa.shared.exceptions import ProviderClientAPIException
 from rasa.shared.providers.mappings import OPENAI_PROVIDER
 from rasa.shared.utils.constants import LOG_COMPONENT_SOURCE_METHOD_INIT
-from rasa.shared.utils.llm import (
-    USER,
-    get_prompt_template,
-    llm_factory,
-)
+from rasa.shared.utils.llm import USER, get_prompt_template, llm_factory
 
 SEPARATOR = "\n\n"
 BACKUP_SEPARATOR = "\nUSER:"

rasa/llm_fine_tuning/utils.py

@@ -1,6 +1,6 @@
 from contextlib import contextmanager
 from datetime import datetime
-from typing import Any, Callable, Dict, Generator, List, Optional, Union
+from typing import Callable, Generator, List, Union
 
 import structlog
 
@@ -24,9 +24,7 @@ def make_mock_invoke_llm(commands: str) -> Callable:
     """
 
     async def _mock_invoke_llm(
-        self: LLMBasedCommandGenerator,
-        prompt: Union[List[dict], List[str], str],
-        metadata: Optional[Dict[str, Any]] = None,
+        self: LLMBasedCommandGenerator, prompt: Union[List[dict], List[str], str]
     ) -> LLMResponse:
         structlogger.debug(
             f"LLM call intercepted, response mocked. "

rasa/model_manager/model_api.py

@@ -7,12 +7,16 @@ from typing import Any, Callable, Dict, Optional, Union
 import dotenv
 import psutil
 import structlog
+from ruamel.yaml import YAMLError
 from sanic import Blueprint, Sanic, response
 from sanic.exceptions import NotFound
 from sanic.request import Request
 from sanic.response import json
 from socketio import AsyncServer
 
+import rasa
+from rasa.cli.project_templates.defaults import get_rasa_defaults
+from rasa.cli.scaffold import ProjectTemplateName, scaffold_path
 from rasa.constants import MODEL_ARCHIVE_EXTENSION
 from rasa.exceptions import ModelNotFound
 from rasa.model_manager import config
@@ -45,6 +49,10 @@ from rasa.model_manager.warm_rasa_process import (
     initialize_warm_rasa_process,
     shutdown_warm_rasa_processes,
 )
+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
 
 dotenv.load_dotenv()
 
@@ -97,7 +105,7 @@ async def update_status_of_all_bots() -> None:
         await update_bot_status(bot)
 
 
-def base_server_url(request: Request) -> str:
+def base_server_url(request: Optional[Request]) -> str:
     """Return the base URL of the server."""
     if SERVER_BASE_URL:
         return SERVER_BASE_URL.rstrip("/")
@@ -476,6 +484,86 @@ def internal_blueprint() -> Blueprint:
         except ModelNotFound:
             return response.raw(b"", status=404)
 
+    @bp.post("/defaults")
+    async def get_defaults(request: Request) -> response.HTTPResponse:
+        """Returns the system defaults like prompts, patterns, etc."""
+        body = request.json or {}
+        config_yaml = body.get("config")
+        if config_yaml is None:
+            exc = ErrorResponse(
+                HTTPStatus.BAD_REQUEST,
+                "BadRequest",
+                "Missing `config` key in request body.",
+            )
+            return response.json(exc.error_info, status=exc.status)
+
+        endpoints_yaml = body.get("endpoints")
+        if endpoints_yaml is None:
+            exc = ErrorResponse(
+                HTTPStatus.BAD_REQUEST,
+                "BadRequest",
+                "Missing `endpoints` key in request body.",
+            )
+            return response.json(exc.error_info, status=exc.status)
+
+        try:
+            defaults = get_rasa_defaults(config_yaml, endpoints_yaml)
+        except (YAMLError, InvalidConfigException) as e:
+            exc = ErrorResponse(
+                HTTPStatus.INTERNAL_SERVER_ERROR,
+                "InitDataError",
+                f"Failed to load defaults. Error: {e!s}",
+            )
+            return response.json(exc.error_info, status=exc.status)
+        return response.json(defaults.model_dump(exclude_none=True))
+
+    @bp.get("/project_template")
+    async def get_project_template(request: Request) -> response.HTTPResponse:
+        """Return initial project template data."""
+        template = request.args.get("template", ProjectTemplateName.DEFAULT.value)
+
+        try:
+            template_enum = ProjectTemplateName(template)
+        except ValueError:
+            valid_templates = ", ".join([t.value for t in ProjectTemplateName])
+            exc = ErrorResponse(
+                HTTPStatus.BAD_REQUEST,
+                "BadRequest",
+                f"Unknown template '{template}'. Valid templates: "
+                f"{valid_templates}",
+            )
+            return response.json(exc.error_info, status=exc.status)
+
+        template_dir = scaffold_path(template_enum)
+        if not os.path.isdir(template_dir):
+            exc = ErrorResponse(
+                HTTPStatus.INTERNAL_SERVER_ERROR,
+                "InitDataError",
+                f"Template directory '{template_dir}' not found.",
+            )
+            return response.json(exc.error_info, status=exc.status)
+
+        assistant_name, parts = build_calm_import_parts(
+            data_path=f"{template_dir}/data",
+            domain_path=f"{template_dir}/domain",
+            config_path=f"{template_dir}/config.yml",
+            endpoints_path=f"{template_dir}/endpoints.yml",
+            assistant_name=template_enum.value,
+        )
+
+        defaults = get_rasa_defaults(
+            config_yaml=dump_obj_as_yaml_to_string(parts.config),
+            endpoints_yaml=dump_obj_as_yaml_to_string(parts.endpoints),
+        )
+        return response.json(
+            {
+                **parts.model_dump(exclude_none=True),
+                "assistantName": assistant_name,
+                "defaults": defaults.model_dump(exclude_none=True),
+                "version": rasa.__version__,
+            }
+        )
+
     return bp
 
 
@@ -483,7 +571,7 @@ 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="*")
+    sio = AsyncServer(async_mode="sanic", cors_allowed_origins=[])
     bp = SocketBlueprint(sio, "", "model_api_external")
 
     create_bridge_server(sio, running_bots)

rasa/model_manager/socket_bridge.py

@@ -131,13 +131,6 @@ async def create_bridge_client(
         structlogger.debug("model_runner.bot_message", deployment_id=deployment_id)
         await sio.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)
-
     @client.event  # type: ignore[misc]
     async def tracker(data: Dict[str, Any]) -> None:
         await sio.emit("tracker", json.loads(data), room=sid)

rasa/model_manager/trainer_service.py

@@ -7,7 +7,7 @@ from typing import Any, Dict, Optional
 import structlog
 from pydantic import BaseModel, ConfigDict
 
-from rasa.constants import MODEL_ARCHIVE_EXTENSION
+from rasa.constants import MODEL_ARCHIVE_EXTENSION, RASA_DIR_NAME
 from rasa.model_manager import config
 from rasa.model_manager.utils import (
     ensure_base_directory_exists,
@@ -51,6 +51,15 @@ 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")
@@ -87,14 +96,8 @@ 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:
@@ -171,7 +174,7 @@ def seed_training_directory_with_rasa_cache(
             training_base_path=training_base_path,
         )
         # copy the cache to the training directory
-        shutil.copytree(src=cache_path, dst=subpath(training_base_path, ".rasa"))
+        shutil.copytree(src=cache_path, dst=subpath(training_base_path, RASA_DIR_NAME))
 
 
 def persist_rasa_cache(assistant_id: str, training_base_path: str) -> None:
@@ -184,12 +187,12 @@ def persist_rasa_cache(assistant_id: str, training_base_path: str) -> None:
     cache_path = cache_for_assistant_path(assistant_id)
 
     # if the training failed and didn't create a cache, skip this step
-    if not os.path.exists(subpath(training_base_path, ".rasa")):
+    if not os.path.exists(subpath(training_base_path, RASA_DIR_NAME)):
         return
 
     # clean up the cache directory first
     shutil.rmtree(cache_path, ignore_errors=True)
-    shutil.copytree(src=subpath(training_base_path, ".rasa"), dst=cache_path)
+    shutil.copytree(src=subpath(training_base_path, RASA_DIR_NAME), dst=cache_path)
 
 
 def write_training_data_to_files(

rasa/plugin.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import argparse
 import functools
 import sys
-from typing import TYPE_CHECKING, Any, List, Optional, Text, Union
+from typing import TYPE_CHECKING, List, Optional, Text, Union
 
 import pluggy
 
@@ -11,7 +11,7 @@ from rasa.cli import SubParsersAction
 
 if TYPE_CHECKING:
     from rasa.core.brokers.broker import EventBroker
-    from rasa.core.tracker_store import TrackerStore
+    from rasa.core.tracker_stores.tracker_store import TrackerStore
     from rasa.shared.core.domain import Domain
     from rasa.shared.core.trackers import DialogueStateTracker
     from rasa.utils.endpoints import EndpointConfig
@@ -32,11 +32,8 @@ def plugin_manager() -> pluggy.PluginManager:
 
 def init_hooks(manager: pluggy.PluginManager) -> None:
     """Initialise hooks into rasa."""
-    import rasa.utils.licensing
     from rasa import hooks
 
-    rasa.utils.licensing.validate_license_from_env()
-
     manager.register(hooks)
 
 
@@ -72,16 +69,6 @@ def create_tracker_store(  # type: ignore[empty-body]
     """Hook specification for wrapping with AuthRetryTrackerStore."""
 
 
-@hookspec(firstresult=True)  # type: ignore[misc]
-def init_anonymization_pipeline(endpoints_file: Optional[Text]) -> None:
-    """Hook specification for initialising the anonymization pipeline."""
-
-
-@hookspec(firstresult=True)  # type: ignore[misc]
-def get_anonymization_pipeline() -> Optional[Any]:
-    """Hook specification for getting the anonymization pipeline."""
-
-
 @hookspec  # type: ignore[misc]
 def after_server_stop() -> None:
     """Hook specification for stopping the server.

rasa/privacy/constants.py

@@ -0,0 +1,83 @@
+PRIVACY_CONFIG_SCHEMA = "privacy/privacy_config_schema.json"
+REDACTION_CHAR_KEY = "redaction_char"
+KEEP_LEFT_KEY = "keep_left"
+KEEP_RIGHT_KEY = "keep_right"
+DELETION_KEY = "deletion"
+ANONYMIZATION_KEY = "anonymization"
+TRACKER_STORE_SETTINGS = "tracker_store_settings"
+SLOT_KEY = "slot"
+TEXT_KEY = "text"
+ENTITIES_KEY = "entities"
+VALUE_KEY = "value"
+ENTITY_LABEL_KEY = "label"
+
+USER_CHAT_INACTIVITY_IN_MINUTES_ENV_VAR_NAME = "USER_CHAT_INACTIVITY_IN_MINUTES"
+GLINER_MODEL_PATH_ENV_VAR_NAME = "GLINER_MODEL_PATH"
+HUGGINGFACE_CACHE_DIR_ENV_VAR_NAME = "HUGGINGFACE_HUB_CACHE_DIR"
+
+DEFAULT_PII_MODEL = "urchade/gliner_multi_pii-v1"
+GLINER_LABELS = [
+    "person",
+    "organization",
+    "company",
+    "phone number",
+    "address",
+    "full address",
+    "postcode",
+    "zip code",
+    "passport number",
+    "email",
+    "credit card number",
+    "social security number",
+    "health insurance id number",
+    "date of birth",
+    "mobile phone number",
+    "bank account number",
+    "medication",
+    "cpf",
+    "driver's license number",
+    "tax identification number",
+    "medical condition",
+    "identity card number",
+    "national id number",
+    "ip address",
+    "email address",
+    "iban",
+    "credit card expiration date",
+    "username",
+    "health insurance number",
+    "registration number",
+    "student id number",
+    "insurance number",
+    "membership number",
+    "booking number",
+    "landline phone number",
+    "blood type",
+    "cvv",
+    "reservation number",
+    "digital signature",
+    "social media handle",
+    "license plate number",
+    "cnpj",
+    "postal code",
+    "passport_number",
+    "serial number",
+    "vehicle registration number",
+    "fax number",
+    "visa number",
+    "insurance company",
+    "identity document number",
+    "transaction number",
+    "national health insurance number",
+    "cvc",
+    "birth certificate number",
+    "train ticket number",
+    "passport expiration date",
+    "social_security_number",
+    "personally identifiable information",
+    "banking routing number",
+    "sort code",
+    "routing number",
+    "tax number",
+    "swift code",
+]

rasa/privacy/event_broker_utils.py

@@ -0,0 +1,77 @@
+from typing import TYPE_CHECKING, List, Optional
+
+import structlog
+
+from rasa.core.brokers.broker import EventBroker
+from rasa.utils.endpoints import EndpointConfig
+
+if TYPE_CHECKING:
+    from asyncio import AbstractEventLoop
+
+structlogger = structlog.get_logger(__name__)
+
+
+async def create_event_brokers(
+    event_broker_endpoint: Optional[EndpointConfig],
+    event_loop: Optional["AbstractEventLoop"] = None,
+) -> List[EventBroker]:
+    """Create EventBroker objects for each anonymization topic or queue."""
+    if event_broker_endpoint is None or event_broker_endpoint.type is None:
+        structlogger.debug(
+            "rasa.privacy_filtering.create_event_broker.no_event_broker_type",
+        )
+        return []
+
+    if event_broker_endpoint.type == "kafka":
+        event_collection = event_broker_endpoint.kwargs.get("anonymization_topics", [])
+        event_collection_type = "topic"
+    elif event_broker_endpoint.type == "pika":
+        event_collection = event_broker_endpoint.kwargs.get("anonymization_queues", [])
+        event_collection_type = "queues"
+    else:
+        structlogger.debug(
+            "rasa.privacy_filtering.create_event_broker.unsupported_event_broker_type",
+            event_broker_type=event_broker_endpoint.type,
+        )
+        return []
+
+    if not event_collection:
+        structlogger.debug(
+            f"rasa.privacy_filtering.create_event_broker.no_anonymization_{event_collection_type}",
+            event_collection_type=event_collection_type,
+        )
+        return []
+
+    return await _create_event_brokers(
+        event_broker_endpoint, event_collection, event_collection_type, event_loop
+    )
+
+
+async def _create_event_brokers(
+    event_broker_endpoint: EndpointConfig,
+    event_collection: List[str],
+    event_collection_type: str,
+    event_loop: Optional["AbstractEventLoop"] = None,
+) -> List[EventBroker]:
+    """Create event brokers."""
+    event_brokers = []
+    for item in event_collection:
+        event_broker_endpoint.kwargs[event_collection_type] = (
+            item if event_collection_type == "topic" else [item]
+        )
+        structlogger.debug(
+            "rasa.privacy_filtering.create_event_broker",
+            event_info=f"Setting anonymized event streaming to '{item}'.",
+        )
+
+        event_broker = await EventBroker.create(event_broker_endpoint, event_loop)
+        if event_broker is None:
+            structlogger.debug(
+                "rasa.privacy_filtering.create_event_broker.no_event_broker_created",
+                event_info=f"No event broker created for publishing to '{item}'.",
+            )
+            continue
+
+        event_brokers.append(event_broker)
+
+    return event_brokers