rasa-pro 3.12.18.dev1__py3-none-any.whl → 3.12.19__py3-none-any.whl

rasa/dialogue_understanding/utils.py

@@ -1,7 +1,9 @@
 from contextlib import contextmanager
 from typing import Any, Dict, Generator, List, Optional, Text
 
-from rasa.dialogue_understanding.commands import Command
+import structlog
+
+from rasa.dialogue_understanding.commands import Command, NoopCommand, SetSlotCommand
 from rasa.dialogue_understanding.constants import (
     RASA_RECORD_COMMANDS_AND_PROMPTS_ENV_VAR_NAME,
 )
@@ -16,7 +18,6 @@ from rasa.shared.nlu.constants import (
     KEY_USER_PROMPT,
     PREDICTED_COMMANDS,
     PROMPTS,
-    SET_SLOT_COMMAND,
 )
 from rasa.shared.nlu.training_data.message import Message
 from rasa.shared.providers.llm.llm_response import LLMResponse
@@ -26,6 +27,8 @@ record_commands_and_prompts = get_bool_env_variable(
     RASA_RECORD_COMMANDS_AND_PROMPTS_ENV_VAR_NAME, False
 )
 
+structlogger = structlog.get_logger()
+
 
 @contextmanager
 def set_record_commands_and_prompts() -> Generator:
@@ -144,21 +147,74 @@ def _handle_via_nlu_in_coexistence(
     if not tracker:
         return False
 
+    commands = message.get(COMMANDS, [])
+
+    # If coexistence routing slot is not active, this setup doesn't
+    # support dual routing -> default to CALM
     if not tracker.has_coexistence_routing_slot:
+        structlogger.debug(
+            "utils.handle_via_nlu_in_coexistence"
+            ".tracker_missing_route_session_to_calm_slot",
+            event_info=(
+                f"Tracker doesn't have the '{ROUTE_TO_CALM_SLOT}' slot."
+                f"Routing to CALM."
+            ),
+            route_session_to_calm=commands,
+        )
         return False
 
+    # Check if the routing decision is stored in the tracker slot
+    # If slot is true -> route to CALM
+    # If slot is false -> route to DM1
     value = tracker.get_slot(ROUTE_TO_CALM_SLOT)
     if value is not None:
+        structlogger.debug(
+            "utils.handle_via_nlu_in_coexistence"
+            ".tracker_route_session_to_calm_slot_value",
+            event_info=(
+                f"Tracker slot '{ROUTE_TO_CALM_SLOT}' set to '{value}'. "
+                f"Routing to "
+                f"{'CALM' if value else 'NLU system'}."
+            ),
+            route_session_to_calm_value_in_tracker=value,
+        )
         return not value
 
-    # routing slot has been reset so we need to check
-    # the command issued by the Router component
-    if message.get(COMMANDS):
-        for command in message.get(COMMANDS):
-            if (
-                command.get("command") == SET_SLOT_COMMAND
-                and command.get("name") == ROUTE_TO_CALM_SLOT
-            ):
-                return not command.get("value")
-
+    # Non-sticky routing to DM1 is only allowed if NoopCommand is the sole predicted
+    # command. In that case, route to DM1
+    if len(commands) == 1 and commands[0].get("command") == NoopCommand.command():
+        structlogger.debug(
+            "utils.handle_via_nlu_in_coexistence.noop_command_detected",
+            event_info="NoopCommand found. Routing to NLU system non-sticky.",
+            commands=commands,
+        )
+        return True
+
+    # If the slot was reset (e.g. new session), try to infer routing from
+    # attached commands. Look for a SetSlotCommand targeting the ROUTE_TO_CALM_SLOT
+    for command in message.get(COMMANDS, []):
+        # If slot is true -> route to CALM
+        # If slot is false -> route to DM1
+        if (
+            command.get("command") == SetSlotCommand.command()
+            and command.get("name") == ROUTE_TO_CALM_SLOT
+        ):
+            structlogger.debug(
+                "utils.handle_via_nlu_in_coexistence.set_slot_command_detected",
+                event_info=(
+                    f"SetSlotCommand setting the '{ROUTE_TO_CALM_SLOT}' to "
+                    f"'{command.get('value')}'. "
+                    f"Routing to "
+                    f"{'CALM' if command.get('value') else 'NLU system'}."
+                ),
+                commands=commands,
+            )
+            return not command.get("value")
+
+    # If no routing info is available -> default to CALM
+    structlogger.debug(
+        "utils.handle_via_nlu_in_coexistence.no_routing_info_available",
+        event_info="No routing info available. Routing to CALM.",
+        commands=commands,
+    )
     return False

rasa/dialogue_understanding_test/du_test_schema.yml

@@ -5,12 +5,12 @@ mapping:
     sequence:
       - type: map
         mapping:
-          regex;(^[a-zA-Z_]+[a-zA-Z0-9_]*$):
+          regex;(^[a-zA-Z_]+[a-zA-Z0-9_\-]*$):
             type: "seq"
             sequence:
               - type: map
                 mapping:
-                  regex;(^[a-zA-Z_]+[a-zA-Z0-9_]*$):
+                  regex;(^[a-zA-Z_]+[a-zA-Z0-9_\-]*$):
                     type: any
 
   metadata:
@@ -129,7 +129,7 @@ mapping:
             type: "seq"
             sequence:
               - type: "str"
-                pattern: ^[a-zA-Z_]+[a-zA-Z0-9_]*$
+                pattern: ^[a-zA-Z_]+[a-zA-Z0-9_\-]*$
           metadata:
             type: "str"
             pattern: ^[a-zA-Z_]+[a-zA-Z0-9_]*$

rasa/e2e_test/e2e_test_schema.yml

@@ -5,12 +5,12 @@ mapping:
     sequence:
       - type: map
         mapping:
-          regex;(^[a-zA-Z_]+[a-zA-Z0-9_]*$):
+          regex;(^[a-zA-Z_]+[a-zA-Z0-9_\-]*$):
             type: "seq"
             sequence:
               - type: map
                 mapping:
-                  regex;(^[a-zA-Z_]+[a-zA-Z0-9_]*$):
+                  regex;(^[a-zA-Z_]+[a-zA-Z0-9_\-]*$):
                     type: any
 
   metadata:
@@ -129,7 +129,7 @@ mapping:
             type: "seq"
             sequence:
               - type: "str"
-                pattern: ^[a-zA-Z_]+[a-zA-Z0-9_]*$
+                pattern: ^[a-zA-Z_]+[a-zA-Z0-9_\-]*$
           metadata:
             type: "str"
             pattern: ^[a-zA-Z_]+[a-zA-Z0-9_]*$

rasa/hooks.py

@@ -1,20 +1,8 @@
 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
@@ -30,7 +18,6 @@ if TYPE_CHECKING:
 
 hookimpl = pluggy.HookimplMarker("rasa")
 logger = logging.getLogger(__name__)
-structlogger = structlog.get_logger()
 
 
 @hookimpl  # type: ignore[misc]
@@ -70,8 +57,6 @@ 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
 
 
@@ -130,43 +115,3 @@ def after_server_stop() -> None:
 
     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/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/shared/constants.py

@@ -342,8 +342,3 @@ ROLE_SYSTEM = "system"
 # Used for key values in ValidateSlotPatternFlowStackFrame
 REFILL_UTTER = "refill_utter"
 REJECTIONS = "rejections"
-
-LANGFUSE_METADATA_USER_ID = "trace_user_id"
-LANGFUSE_METADATA_SESSION_ID = "session_id"
-LANGFUSE_CUSTOM_METADATA_DICT = "trace_metadata"
-LANGFUSE_TAGS = "tags"

rasa/shared/providers/constants.py

@@ -4,12 +4,3 @@ LITE_LLM_API_KEY_FIELD = "api_key"
 LITE_LLM_API_VERSION_FIELD = "api_version"
 LITE_LLM_MODEL_FIELD = "model"
 LITE_LLM_AZURE_AD_TOKEN = "azure_ad_token"
-
-# Enable or disable Langfuse integration
-RASA_LANGFUSE_INTEGRATION_ENABLED_ENV_VAR = "RASA_LANGFUSE_INTEGRATION_ENABLED"
-# Langfuse configuration
-LANGFUSE_CALLBACK_NAME = "langfuse"
-LANGFUSE_HOST_ENV_VAR = "LANGFUSE_HOST"
-LANGFUSE_PROJECT_ID_ENV_VAR = "LANGFUSE_PROJECT_ID"
-LANGFUSE_PUBLIC_KEY_ENV_VAR = "LANGFUSE_PUBLIC_KEY"
-LANGFUSE_SECRET_KEY_ENV_VAR = "LANGFUSE_SECRET_KEY"

rasa/shared/providers/llm/_base_litellm_client.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import logging
 from abc import abstractmethod
-from typing import Any, Dict, List, Optional, Union, cast
+from typing import Any, Dict, List, Union, cast
 
 import structlog
 from litellm import acompletion, completion, validate_environment
@@ -126,11 +126,7 @@ class _BaseLiteLLMClient:
             raise ProviderClientValidationError(event_info)
 
     @suppress_logs(log_level=logging.WARNING)
-    def completion(
-        self,
-        messages: Union[List[dict], List[str], str],
-        metadata: Optional[Dict[str, Any]] = None,
-    ) -> LLMResponse:
+    def completion(self, messages: Union[List[dict], List[str], str]) -> LLMResponse:
         """Synchronously generate completions for given list of messages.
 
         Args:
@@ -142,7 +138,6 @@ class _BaseLiteLLMClient:
                 - a list of messages. Each message is a string and will be formatted
                     as a user message.
                 - a single message as a string which will be formatted as user message.
-            metadata: Optional metadata to be passed to the LLM call.
 
         Returns:
             List of message completions.
@@ -160,9 +155,7 @@ class _BaseLiteLLMClient:
 
     @suppress_logs(log_level=logging.WARNING)
     async def acompletion(
-        self,
-        messages: Union[List[dict], List[str], str],
-        metadata: Optional[Dict[str, Any]] = None,
+        self, messages: Union[List[dict], List[str], str]
     ) -> LLMResponse:
         """Asynchronously generate completions for given list of messages.
 
@@ -175,7 +168,6 @@ class _BaseLiteLLMClient:
                 - a list of messages. Each message is a string and will be formatted
                     as a user message.
                 - a single message as a string which will be formatted as user message.
-            metadata: Optional metadata to be passed to the LLM call.
 
         Returns:
             List of message completions.
@@ -186,9 +178,7 @@ class _BaseLiteLLMClient:
         try:
             formatted_messages = self._get_formatted_messages(messages)
             arguments = resolve_environment_variables(self._completion_fn_args)
-            response = await acompletion(
-                messages=formatted_messages, metadata=metadata, **arguments
-            )
+            response = await acompletion(messages=formatted_messages, **arguments)
             return self._format_response(response)
         except Exception as e:
             message = ""

rasa/shared/providers/llm/litellm_router_llm_client.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import logging
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Union
 
 import structlog
 
@@ -122,12 +122,9 @@ class LiteLLMRouterLLMClient(_BaseLiteLLMRouterClient, _BaseLiteLLMClient):
             raise ProviderClientAPIException(e)
 
     @suppress_logs(log_level=logging.WARNING)
-    def completion(
-        self,
-        messages: Union[List[dict], List[str], str],
-        metadata: Optional[Dict[str, Any]] = None,
-    ) -> LLMResponse:
-        """Synchronously generate completions for given list of messages.
+    def completion(self, messages: Union[List[dict], List[str], str]) -> LLMResponse:
+        """
+        Synchronously generate completions for given list of messages.
 
         Method overrides the base class method to call the appropriate
         completion method based on the configuration. If the chat completions
@@ -143,11 +140,8 @@ class LiteLLMRouterLLMClient(_BaseLiteLLMRouterClient, _BaseLiteLLMClient):
                 - a list of messages. Each message is a string and will be formatted
                     as a user message.
                 - a single message as a string which will be formatted as user message.
-            metadata: Optional metadata to be passed to the LLM call.
-
         Returns:
             List of message completions.
-
         Raises:
             ProviderClientAPIException: If the API request fails.
         """
@@ -164,11 +158,10 @@ class LiteLLMRouterLLMClient(_BaseLiteLLMRouterClient, _BaseLiteLLMClient):
 
     @suppress_logs(log_level=logging.WARNING)
     async def acompletion(
-        self,
-        messages: Union[List[dict], List[str], str],
-        metadata: Optional[Dict[str, Any]] = None,
+        self, messages: Union[List[dict], List[str], str]
     ) -> LLMResponse:
-        """Asynchronously generate completions for given list of messages.
+        """
+        Asynchronously generate completions for given list of messages.
 
         Method overrides the base class method to call the appropriate
         completion method based on the configuration. If the chat completions
@@ -184,11 +177,8 @@ class LiteLLMRouterLLMClient(_BaseLiteLLMRouterClient, _BaseLiteLLMClient):
                 - a list of messages. Each message is a string and will be formatted
                     as a user message.
                 - a single message as a string which will be formatted as user message.
-            metadata: Optional metadata to be passed to the LLM call.
-
         Returns:
             List of message completions.
-
         Raises:
             ProviderClientAPIException: If the API request fails.
         """

rasa/shared/providers/llm/llm_client.py

@@ -1,19 +1,21 @@
 from __future__ import annotations
 
-from typing import Any, Dict, List, Optional, Protocol, Union, runtime_checkable
+from typing import Dict, List, Protocol, Union, runtime_checkable
 
 from rasa.shared.providers.llm.llm_response import LLMResponse
 
 
 @runtime_checkable
 class LLMClient(Protocol):
-    """Protocol for an LLM client that specifies the interface for interacting
+    """
+    Protocol for an LLM client that specifies the interface for interacting
     with the API.
     """
 
     @classmethod
     def from_config(cls, config: dict) -> LLMClient:
-        """Initializes the llm client with the given configuration.
+        """
+        Initializes the llm client with the given configuration.
 
         This class method should be implemented to parse the given
         configuration and create an instance of an llm client.
@@ -22,24 +24,17 @@ class LLMClient(Protocol):
 
     @property
     def config(self) -> Dict:
-        """Returns the configuration for that the llm client is initialized with.
+        """
+        Returns the configuration for that the llm client is initialized with.
 
         This property should be implemented to return a dictionary containing
         the configuration settings for the llm client.
         """
         ...
 
-    def completion(
-        self,
-        messages: Union[List[dict], List[str], str],
-        metadata: Optional[Dict[str, Any]] = None,
-    ) -> LLMResponse:
-        """Synchronously generate completions for given list of messages.
-        def completion(
-        self,
-        messages: Union[List[dict], List[str], str],
-        metadata: Optional[Dict[str, Any]] = None,
-        ) -> LLMResponse:
+    def completion(self, messages: Union[List[dict], List[str], str]) -> LLMResponse:
+        """
+        Synchronously generate completions for given list of messages.
 
         This method should be implemented to take a list of messages (as
         strings) and return a list of completions (as strings).
@@ -53,19 +48,16 @@ class LLMClient(Protocol):
                 - a list of messages. Each message is a string and will be formatted
                     as a user message.
                 - a single message as a string which will be formatted as user message.
-            metadata: Optional metadata to be passed to the LLM call.
-
         Returns:
             LLMResponse
         """
         ...
 
     async def acompletion(
-        self,
-        messages: Union[List[dict], List[str], str],
-        metadata: Optional[Dict[str, Any]] = None,
+        self, messages: Union[List[dict], List[str], str]
     ) -> LLMResponse:
-        """Asynchronously generate completions for given list of messages.
+        """
+        Asynchronously generate completions for given list of messages.
 
         This method should be implemented to take a list of messages (as
         strings) and return a list of completions (as strings).
@@ -79,15 +71,14 @@ class LLMClient(Protocol):
                 - a list of messages. Each message is a string and will be formatted
                     as a user message.
                 - a single message as a string which will be formatted as user message.
-            metadata: Optional metadata to be passed to the LLM call.
-
         Returns:
             LLMResponse
         """
         ...
 
     def validate_client_setup(self, *args, **kwargs) -> None:  # type: ignore
-        """Perform client setup validation.
+        """
+        Perform client setup validation.
 
         This method should be implemented to validate whether the client can be
         used with the parameters provided through configuration or environment

rasa/shared/providers/llm/self_hosted_llm_client.py

@@ -237,9 +237,7 @@ class SelfHostedLLMClient(_BaseLiteLLMClient):
             raise ProviderClientAPIException(e)
 
     async def acompletion(
-        self,
-        messages: Union[List[dict], List[str], str],
-        metadata: Optional[Dict[str, Any]] = None,
+        self, messages: Union[List[dict], List[str], str]
     ) -> LLMResponse:
         """Asynchronous completion of the model with the given messages.
 
@@ -257,7 +255,6 @@ class SelfHostedLLMClient(_BaseLiteLLMClient):
                 - a list of messages. Each message is a string and will be formatted
                     as a user message.
                 - a single message as a string which will be formatted as user message.
-            metadata: Optional metadata to be passed to the LLM call.
 
         Returns:
             The completion response.
@@ -266,11 +263,7 @@ class SelfHostedLLMClient(_BaseLiteLLMClient):
             return await super().acompletion(messages)
         return await self._atext_completion(messages)
 
-    def completion(
-        self,
-        messages: Union[List[dict], List[str], str],
-        metadata: Optional[Dict[str, Any]] = None,
-    ) -> LLMResponse:
+    def completion(self, messages: Union[List[dict], List[str], str]) -> LLMResponse:
         """Completion of the model with the given messages.
 
         Method overrides the base class method to call the appropriate
@@ -280,7 +273,6 @@ class SelfHostedLLMClient(_BaseLiteLLMClient):
 
         Args:
             messages: The messages to be used for completion.
-            metadata: Optional metadata to be passed to the LLM call.
 
         Returns:
             The completion response.

rasa/tracing/instrumentation/attribute_extractors.py

@@ -372,7 +372,6 @@ def extract_llm_config(
 def extract_attrs_for_llm_based_command_generator(
     self: "LLMBasedCommandGenerator",
     prompt: str,
-    metadata: Optional[Dict[str, Any]] = None,
 ) -> Dict[str, Any]:
     from rasa.dialogue_understanding.generator.flow_retrieval import (
         DEFAULT_EMBEDDINGS_CONFIG,
@@ -388,7 +387,8 @@ def extract_attrs_for_llm_based_command_generator(
 
 
 def extract_attrs_for_contextual_response_rephraser(
-    self: Any, prompt: str
+    self: Any,
+    prompt: str,
 ) -> Dict[str, Any]:
     from rasa.core.nlg.contextual_response_rephraser import DEFAULT_LLM_CONFIG
 

rasa/version.py

@@ -1,3 +1,3 @@
 # this file will automatically be changed,
 # do not add anything but the version number here!
-__version__ = "3.12.18.dev1"
+__version__ = "3.12.19"

{rasa_pro-3.12.18.dev1.dist-info → rasa_pro-3.12.19.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: rasa-pro
-Version: 3.12.18.dev1
+Version: 3.12.19
 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
@@ -63,7 +63,6 @@ Requires-Dist: keras (==2.14.0)
 Requires-Dist: langchain (>=0.2.17,<0.3.0)
 Requires-Dist: langchain-community (>=0.2.19,<0.3.0)
 Requires-Dist: langcodes (>=3.5.0,<4.0.0)
-Requires-Dist: langfuse (>=2.60.2,<2.61.0)
 Requires-Dist: litellm (>=1.69.0,<1.70.0)
 Requires-Dist: matplotlib (>=3.7,<3.8)
 Requires-Dist: mattermostwrapper (>=2.2,<2.3)