rasa-pro 3.11.13__py3-none-any.whl → 3.11.15__py3-none-any.whl

rasa/dialogue_understanding/generator/multi_step/multi_step_llm_command_generator.py

@@ -255,7 +255,7 @@ class MultiStepLLMCommandGenerator(LLMBasedCommandGenerator):
         skip_question_re = re.compile(r"SkipQuestion\(\)")
         knowledge_re = re.compile(r"SearchAndReply\(\)")
         humand_handoff_re = re.compile(r"HumanHandoff\(\)")
-        clarify_re = re.compile(r"Clarify\(([\"\'a-zA-Z0-9_, ]+)\)")
+        clarify_re = re.compile(r"Clarify\(([\"\'a-zA-Z0-9_\-, ]+)\)")
         cannot_handle_re = re.compile(r"CannotHandle\(\)")
 
         for action in actions.strip().splitlines():

rasa/dialogue_understanding/generator/single_step/single_step_llm_command_generator.py

@@ -329,7 +329,7 @@ class SingleStepLLMCommandGenerator(LLMBasedCommandGenerator):
         skip_question_re = re.compile(r"SkipQuestion\(\)")
         knowledge_re = re.compile(r"SearchAndReply\(\)")
         humand_handoff_re = re.compile(r"HumanHandoff\(\)")
-        clarify_re = re.compile(r"Clarify\(([\"\'a-zA-Z0-9_, ]+)\)")
+        clarify_re = re.compile(r"Clarify\(([\"\'a-zA-Z0-9_\-, ]+)\)")
         repeat_re = re.compile(r"RepeatLastBotMessages\(\)")
 
         for action in actions.strip().splitlines():

rasa/dialogue_understanding/processor/command_processor_component.py

@@ -1,8 +1,8 @@
 from __future__ import annotations
 
-from typing import Any, Dict, List, Text
-import rasa.dialogue_understanding.processor.command_processor
+from typing import Any, Dict, List, Optional, Text
 
+import rasa.dialogue_understanding.processor.command_processor
 from rasa.engine.graph import ExecutionContext, GraphComponent
 from rasa.engine.storage.resource import Resource
 from rasa.engine.storage.storage import ModelStorage
@@ -37,8 +37,8 @@ class CommandProcessorComponent(GraphComponent):
         self,
         tracker: DialogueStateTracker,
         flows: FlowsList,
-        story_graph: StoryGraph,
-        domain: Domain,
+        domain: Optional[Domain] = None,
+        story_graph: Optional[StoryGraph] = None,
     ) -> List[Event]:
         """Execute commands to update tracker state."""
         return rasa.dialogue_understanding.processor.command_processor.execute_commands(

rasa/engine/recipes/default_recipe.py

@@ -382,7 +382,9 @@ class DefaultV1Recipe(Recipe):
         return preprocessors
 
     def _get_needs_from_args(
-        self, component: Type[GraphComponent], fn_name: str
+        self,
+        component: Type[GraphComponent],
+        fn_name: str,
     ) -> Dict[str, str]:
         """Get the needed arguments from the method on the component.
 
@@ -420,6 +422,7 @@ class DefaultV1Recipe(Recipe):
         parameters = {
             name
             for name, param in sig.parameters.items()
+            # only consider parameters which are positional or keyword
             if param.kind == param.POSITIONAL_OR_KEYWORD
         }
 
@@ -736,8 +739,28 @@ class DefaultV1Recipe(Recipe):
                 predict_config, predict_nodes, train_nodes, preprocessors
             )
 
+        # The `story_graph_provider` is only needed if the intentless policy is used.
+        # If it is not used, we can remove it from the nodes as it slows down the
+        # loading time if users have a large number of stories.
+        if not self._intentless_policy_used(predict_nodes):
+            # Removes the `story_graph_provider` from the nodes
+            predict_nodes.pop("story_graph_provider", None)
+            if "command_processor" in predict_nodes:
+                # Removes story_graph from the command processor inputs
+                predict_nodes["command_processor"].needs.pop("story_graph", None)
+
         return predict_nodes
 
+    @staticmethod
+    def _intentless_policy_used(nodes: Dict[Text, SchemaNode]) -> bool:
+        """Checks if the intentless policy is used in the nodes."""
+        from rasa.core import IntentlessPolicy
+
+        for schema_node in nodes.values():
+            if schema_node.matches_type(IntentlessPolicy):
+                return True
+        return False
+
     def _add_nlu_predict_nodes(
         self,
         last_run_node: Text,
@@ -908,7 +931,8 @@ class DefaultV1Recipe(Recipe):
         predict_nodes["command_processor"] = SchemaNode(
             **DEFAULT_PREDICT_KWARGS,
             needs=self._get_needs_from_args(
-                CommandProcessorComponent, "execute_commands"
+                CommandProcessorComponent,
+                "execute_commands",
             ),
             uses=CommandProcessorComponent,
             fn="execute_commands",

rasa/llm_fine_tuning/paraphrasing/conversation_rephraser.py

@@ -10,11 +10,13 @@ from rasa.llm_fine_tuning.paraphrasing.rephrased_user_message import (
     RephrasedUserMessage,
 )
 from rasa.shared.constants import (
+    MAX_COMPLETION_TOKENS_CONFIG_KEY,
     MODEL_NAME_CONFIG_KEY,
     MODEL_CONFIG_KEY,
     LLM_CONFIG_KEY,
     PROMPT_TEMPLATE_CONFIG_KEY,
     PROVIDER_CONFIG_KEY,
+    TEMPERATURE_CONFIG_KEY,
     TIMEOUT_CONFIG_KEY,
 )
 from rasa.shared.exceptions import ProviderClientAPIException
@@ -38,8 +40,8 @@ DEFAULT_LLM_CONFIG = {
     PROVIDER_CONFIG_KEY: OPENAI_PROVIDER,
     MODEL_CONFIG_KEY: "gpt-4o-mini",
     TIMEOUT_CONFIG_KEY: 7,
-    "temperature": 0.0,
-    "max_tokens": 4096,
+    TEMPERATURE_CONFIG_KEY: 0.0,
+    MAX_COMPLETION_TOKENS_CONFIG_KEY: 4096,
 }
 
 structlogger = structlog.get_logger()

rasa/model_manager/config.py

@@ -1,6 +1,8 @@
 import sys
 import os
 
+from rasa.constants import RASA_REMOTE_STORAGE_ENV_VAR_NAME
+
 DEFAULT_SERVER_BASE_WORKING_DIRECTORY = "working-data"
 
 SERVER_BASE_WORKING_DIRECTORY = os.environ.get(
@@ -12,7 +14,7 @@ SERVER_PORT = os.environ.get("RASA_MODEL_SERVER_PORT", 8000)
 SERVER_BASE_URL = os.environ.get("RASA_MODEL_SERVER_BASE_URL", None)
 
 # defaults to storing on the local hard drive
-SERVER_MODEL_REMOTE_STORAGE = os.environ.get("RASA_REMOTE_STORAGE", None)
+SERVER_MODEL_REMOTE_STORAGE = os.environ.get(RASA_REMOTE_STORAGE_ENV_VAR_NAME, None)
 
 # The path to the python executable that is running this script
 # we will use the same python to run training / bots

rasa/model_manager/model_api.py

@@ -531,8 +531,7 @@ def size_of_model(model_name: str) -> Optional[int]:
             model_name=model_file_name,
         )
         return fetch_size_of_remote_model(
-            model_file_name,
-            config.SERVER_MODEL_REMOTE_STORAGE,
+            model_file_name, config.SERVER_MODEL_REMOTE_STORAGE, model_path
         )
     raise ModelNotFound("Model not found.")
 

rasa/model_manager/runner_service.py

@@ -166,13 +166,13 @@ def fetch_remote_model_to_dir(
 ) -> str:
     """Fetch the model from remote storage.
 
-    Returns the path to the model diretory.
+    Returns the path to the model directory.
     """
     from rasa.core.persistor import get_persistor
 
     persistor = get_persistor(storage_type)
 
-    # we now there must be a persistor, because the config is set
+    # we know there must be a persistor, because the config is set
     # this is here to please the type checker for the call below
     assert persistor is not None
 
@@ -182,7 +182,9 @@ def fetch_remote_model_to_dir(
         raise ModelNotFound() from e
 
 
-def fetch_size_of_remote_model(model_name: str, storage_type: str) -> int:
+def fetch_size_of_remote_model(
+    model_name: str, storage_type: str, model_path: str
+) -> int:
     """Fetch the size of the model from remote storage."""
     from rasa.core.persistor import get_persistor
 
@@ -192,7 +194,9 @@ def fetch_size_of_remote_model(model_name: str, storage_type: str) -> int:
     # this is here to please the type checker for the call below
     assert persistor is not None
 
-    return persistor.size_of_persisted_model(model_name=model_name)
+    return persistor.size_of_persisted_model(
+        model_name=model_name, target_path=model_path
+    )
 
 
 def start_bot_process(

rasa/model_manager/trainer_service.py

@@ -276,6 +276,7 @@ def start_training_process(
                 "--keep-local-model-copy",
                 "--remote-storage",
                 config.SERVER_MODEL_REMOTE_STORAGE,
+                "--remote-root-only",
             ]
         )
 

rasa/model_training.py

@@ -158,6 +158,7 @@ async def train(
     remote_storage: Optional[StorageType] = None,
     file_importer: Optional[TrainingDataImporter] = None,
     keep_local_model_copy: bool = False,
+    remote_root_only: bool = False,
 ) -> TrainingResult:
     """Trains a Rasa model (Core and NLU).
 
@@ -185,6 +186,8 @@ async def train(
             If it is not provided, a new instance will be created.
         keep_local_model_copy: If `True` the model will be stored locally even if
             remote storage is configured.
+        remote_root_only: If `True`, the model will be stored in the root of the
+            remote model storage.
 
     Returns:
         An instance of `TrainingResult`.
@@ -267,6 +270,7 @@ async def train(
             dry_run=dry_run,
             remote_storage=remote_storage,
             keep_local_model_copy=keep_local_model_copy,
+            remote_root_only=remote_root_only,
             **(core_additional_arguments or {}),
             **(nlu_additional_arguments or {}),
         )
@@ -282,6 +286,7 @@ async def _train_graph(
     dry_run: bool = False,
     remote_storage: Optional[StorageType] = None,
     keep_local_model_copy: bool = False,
+    remote_root_only: bool = False,
     **kwargs: Any,
 ) -> TrainingResult:
     if model_to_finetune:
@@ -363,7 +368,9 @@ async def _train_graph(
                 is_finetuning=is_finetuning,
             )
             if remote_storage:
-                push_model_to_remote_storage(full_model_path, remote_storage)
+                push_model_to_remote_storage(
+                    full_model_path, remote_storage, remote_root_only
+                )
                 if not keep_local_model_copy:
                     full_model_path.unlink()
                 structlogger.info(
@@ -581,14 +588,16 @@ async def train_nlu(
     ).model
 
 
-def push_model_to_remote_storage(model_path: Path, remote_storage: StorageType) -> None:
+def push_model_to_remote_storage(
+    model_path: Path, remote_storage: StorageType, remote_root_only: bool = False
+) -> None:
     """Push model to remote storage."""
     from rasa.core.persistor import get_persistor
 
     persistor = get_persistor(remote_storage)
 
     if persistor is not None:
-        persistor.persist(str(model_path))
+        persistor.persist(str(model_path), remote_root_only)
 
     else:
         raise RasaException(

rasa/server.py

@@ -522,12 +522,15 @@ def configure_cors(
     )
 
 
-def add_root_route(app: Sanic) -> None:
+def add_root_route(app: Sanic, is_inspector_enabled: bool = False) -> None:
     """Add '/' route to return hello."""
 
     @app.get("/")
     async def hello(request: Request) -> HTTPResponse:
         """Check if the server is running and responds with the version."""
+        if not is_inspector_enabled:
+            return response.text("Hello from Rasa: " + rasa.__version__)
+
         html_content = f"""
         <html>
             <body>
@@ -688,6 +691,7 @@ def create_app(
     jwt_private_key: Optional[Text] = None,
     jwt_method: Text = "HS256",
     endpoints: Optional[AvailableEndpoints] = None,
+    is_inspector_enabled: bool = False,
 ) -> Sanic:
     """Class representing a Rasa HTTP server."""
     app = Sanic("rasa_server")
@@ -733,7 +737,7 @@ def create_app(
     ) -> HTTPResponse:
         return response.json(exception.error_info, status=exception.status)
 
-    add_root_route(app)
+    add_root_route(app, is_inspector_enabled)
 
     @app.get("/version")
     async def version(request: Request) -> HTTPResponse:

rasa/shared/constants.py

@@ -181,6 +181,12 @@ PROVIDER_CONFIG_KEY = "provider"
 REQUEST_TIMEOUT_CONFIG_KEY = "request_timeout"  # deprecated
 TIMEOUT_CONFIG_KEY = "timeout"
 
+LOGIT_BIAS_CONFIG_KEY = "logit_bias"
+MAX_RETRIES_CONFIG_KEY = "max_retries"
+TEMPERATURE_CONFIG_KEY = "temperature"
+MAX_COMPLETION_TOKENS_CONFIG_KEY = "max_completion_tokens"
+MAX_TOKENS_CONFIG_KEY = "max_tokens"
+
 DEPLOYMENT_NAME_CONFIG_KEY = "deployment_name"
 DEPLOYMENT_CONFIG_KEY = "deployment"
 EMBEDDINGS_CONFIG_KEY = "embeddings"

rasa/shared/providers/_configs/azure_openai_client_config.py

@@ -4,26 +4,28 @@ from typing import Any, Dict, Optional
 import structlog
 
 from rasa.shared.constants import (
-    MODEL_CONFIG_KEY,
-    MODEL_NAME_CONFIG_KEY,
-    OPENAI_API_BASE_CONFIG_KEY,
     API_BASE_CONFIG_KEY,
-    OPENAI_API_TYPE_CONFIG_KEY,
     API_TYPE_CONFIG_KEY,
-    OPENAI_API_VERSION_CONFIG_KEY,
     API_VERSION_CONFIG_KEY,
+    AZURE_API_TYPE,
+    AZURE_OPENAI_PROVIDER,
     DEPLOYMENT_CONFIG_KEY,
     DEPLOYMENT_NAME_CONFIG_KEY,
     ENGINE_CONFIG_KEY,
-    RASA_TYPE_CONFIG_KEY,
     LANGCHAIN_TYPE_CONFIG_KEY,
-    STREAM_CONFIG_KEY,
+    MAX_COMPLETION_TOKENS_CONFIG_KEY,
+    MAX_TOKENS_CONFIG_KEY,
+    MODEL_CONFIG_KEY,
+    MODEL_NAME_CONFIG_KEY,
     N_REPHRASES_CONFIG_KEY,
+    OPENAI_API_BASE_CONFIG_KEY,
+    OPENAI_API_TYPE_CONFIG_KEY,
+    OPENAI_API_VERSION_CONFIG_KEY,
+    PROVIDER_CONFIG_KEY,
+    RASA_TYPE_CONFIG_KEY,
     REQUEST_TIMEOUT_CONFIG_KEY,
+    STREAM_CONFIG_KEY,
     TIMEOUT_CONFIG_KEY,
-    PROVIDER_CONFIG_KEY,
-    AZURE_OPENAI_PROVIDER,
-    AZURE_API_TYPE,
 )
 from rasa.shared.providers._configs.utils import (
     resolve_aliases,
@@ -51,6 +53,8 @@ DEPRECATED_ALIASES_TO_STANDARD_KEY_MAPPING = {
     MODEL_NAME_CONFIG_KEY: MODEL_CONFIG_KEY,
     # Timeout aliases
     REQUEST_TIMEOUT_CONFIG_KEY: TIMEOUT_CONFIG_KEY,
+    # Max tokens aliases
+    MAX_TOKENS_CONFIG_KEY: MAX_COMPLETION_TOKENS_CONFIG_KEY,
 }
 
 REQUIRED_KEYS = [DEPLOYMENT_CONFIG_KEY]

rasa/shared/providers/_configs/openai_client_config.py

@@ -4,23 +4,25 @@ from typing import Any, Dict, Optional
 import structlog
 
 from rasa.shared.constants import (
+    API_BASE_CONFIG_KEY,
+    API_TYPE_CONFIG_KEY,
+    API_VERSION_CONFIG_KEY,
+    LANGCHAIN_TYPE_CONFIG_KEY,
+    MAX_COMPLETION_TOKENS_CONFIG_KEY,
+    MAX_TOKENS_CONFIG_KEY,
     MODEL_CONFIG_KEY,
     MODEL_NAME_CONFIG_KEY,
+    N_REPHRASES_CONFIG_KEY,
     OPENAI_API_BASE_CONFIG_KEY,
-    API_BASE_CONFIG_KEY,
+    OPENAI_API_TYPE,
     OPENAI_API_TYPE_CONFIG_KEY,
-    API_TYPE_CONFIG_KEY,
     OPENAI_API_VERSION_CONFIG_KEY,
-    API_VERSION_CONFIG_KEY,
+    OPENAI_PROVIDER,
+    PROVIDER_CONFIG_KEY,
     RASA_TYPE_CONFIG_KEY,
-    LANGCHAIN_TYPE_CONFIG_KEY,
-    STREAM_CONFIG_KEY,
-    N_REPHRASES_CONFIG_KEY,
     REQUEST_TIMEOUT_CONFIG_KEY,
+    STREAM_CONFIG_KEY,
     TIMEOUT_CONFIG_KEY,
-    PROVIDER_CONFIG_KEY,
-    OPENAI_API_TYPE,
-    OPENAI_PROVIDER,
 )
 from rasa.shared.providers._configs.utils import (
     resolve_aliases,
@@ -46,6 +48,8 @@ DEPRECATED_ALIASES_TO_STANDARD_KEY_MAPPING = {
     OPENAI_API_VERSION_CONFIG_KEY: API_VERSION_CONFIG_KEY,
     # Timeout aliases
     REQUEST_TIMEOUT_CONFIG_KEY: TIMEOUT_CONFIG_KEY,
+    # Max tokens aliases
+    MAX_TOKENS_CONFIG_KEY: MAX_COMPLETION_TOKENS_CONFIG_KEY,
 }
 
 REQUIRED_KEYS = [MODEL_CONFIG_KEY]

rasa/shared/providers/embedding/_base_litellm_embedding_client.py

@@ -70,7 +70,10 @@ class _BaseLiteLLMEmbeddingClient:
     def _embedding_fn_args(self) -> Dict[str, Any]:
         """Returns the arguments to be passed to the embedding function."""
         return {
+            # Parameters set through config, can override drop_params
             **self._litellm_extra_parameters,
+            # Model name is constructed in the LiteLLM format from the provided config
+            # Non-overridable to ensure consistency
             "model": self._litellm_model_name,
         }
 

rasa/shared/providers/llm/_base_litellm_client.py

@@ -85,12 +85,15 @@ class _BaseLiteLLMClient:
     @property
     def _completion_fn_args(self) -> dict:
         return {
-            **self._litellm_extra_parameters,
-            "model": self._litellm_model_name,
             # Since all providers covered by LiteLLM use the OpenAI format, but
             # not all support every OpenAI parameter, raise an exception if
             # provider/model uses unsupported parameter
             "drop_params": False,
+            # All other parameters set through config, can override drop_params
+            **self._litellm_extra_parameters,
+            # Model name is constructed in the LiteLLM format from the provided config
+            # Non-overridable to ensure consistency
+            "model": self._litellm_model_name,
         }
 
     def validate_client_setup(self) -> None:

rasa/shared/utils/llm.py

@@ -5,6 +5,7 @@ from typing import (
     Any,
     Callable,
     Dict,
+    List,
     Optional,
     Text,
     Type,
@@ -187,6 +188,7 @@ def tracker_as_readable_transcript(
     human_prefix: str = USER,
     ai_prefix: str = AI,
     max_turns: Optional[int] = 20,
+    turns_wrapper: Optional[Callable[[List[str]], List[str]]] = None,
 ) -> str:
     """Creates a readable dialogue from a tracker.
 
@@ -195,6 +197,7 @@ def tracker_as_readable_transcript(
         human_prefix: the prefix to use for human utterances
         ai_prefix: the prefix to use for ai utterances
         max_turns: the maximum number of turns to include in the transcript
+        turns_wrapper: optional function to wrap the turns in a custom way
 
     Example:
         >>> tracker = Tracker(
@@ -231,8 +234,11 @@ def tracker_as_readable_transcript(
         elif isinstance(event, BotUttered):
             transcript.append(f"{ai_prefix}: {sanitize_message_for_prompt(event.text)}")
 
-    if max_turns:
-        transcript = transcript[-max_turns:]
+    # turns_wrapper to count multiple utterances by bot/user as single turn
+    if turns_wrapper:
+        transcript = turns_wrapper(transcript)
+    # otherwise, just take the last `max_turns` lines of the transcript
+    transcript = transcript[-max_turns if max_turns is not None else None :]
 
     return "\n".join(transcript)
 

rasa/version.py

@@ -1,3 +1,3 @@
 # this file will automatically be changed,
 # do not add anything but the version number here!
-__version__ = "3.11.13"
+__version__ = "3.11.15"

{rasa_pro-3.11.13.dist-info → rasa_pro-3.11.15.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: rasa-pro
-Version: 3.11.13
+Version: 3.11.15
 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