rasa-pro 3.13.0.dev5__py3-none-any.whl → 3.13.0.dev7__py3-none-any.whl

rasa/core/utils.py

@@ -198,6 +198,9 @@ class AvailableEndpoints:
         model_groups = read_property_config_from_endpoints_file(
             endpoint_file, property_name="model_groups"
         )
+        privacy = read_property_config_from_endpoints_file(
+            endpoint_file, property_name="privacy"
+        )
 
         return cls(
             nlg,
@@ -209,6 +212,7 @@ class AvailableEndpoints:
             event_broker,
             vector_store,
             model_groups,
+            privacy,
         )
 
     def __init__(
@@ -222,6 +226,7 @@ class AvailableEndpoints:
         event_broker: Optional[EndpointConfig] = None,
         vector_store: Optional[EndpointConfig] = None,
         model_groups: Optional[List[Dict[str, Any]]] = None,
+        privacy: Optional[Dict[Text, Any]] = None,
     ) -> None:
         """Create an `AvailableEndpoints` object."""
         self.model = model
@@ -233,6 +238,7 @@ class AvailableEndpoints:
         self.event_broker = event_broker
         self.vector_store = vector_store
         self.model_groups = model_groups
+        self.privacy = privacy
 
     @classmethod
     def get_instance(

rasa/dialogue_understanding/coexistence/llm_based_router.py

@@ -23,11 +23,14 @@ from rasa.engine.recipes.default_recipe import DefaultV1Recipe
 from rasa.engine.storage.resource import Resource
 from rasa.engine.storage.storage import ModelStorage
 from rasa.shared.constants import (
+    LOGIT_BIAS_CONFIG_KEY,
+    MAX_COMPLETION_TOKENS_CONFIG_KEY,
     MODEL_CONFIG_KEY,
     OPENAI_PROVIDER,
     PROMPT_CONFIG_KEY,
     PROVIDER_CONFIG_KEY,
     ROUTE_TO_CALM_SLOT,
+    TEMPERATURE_CONFIG_KEY,
     TIMEOUT_CONFIG_KEY,
 )
 from rasa.shared.core.trackers import DialogueStateTracker
@@ -66,9 +69,11 @@ DEFAULT_LLM_CONFIG = {
     PROVIDER_CONFIG_KEY: OPENAI_PROVIDER,
     MODEL_CONFIG_KEY: DEFAULT_OPENAI_CHAT_MODEL_NAME,
     TIMEOUT_CONFIG_KEY: 7,
-    "temperature": 0.0,
-    "max_tokens": 1,
-    "logit_bias": {str(token_id): 100 for token_id in A_TO_C_TOKEN_IDS_CHATGPT},
+    TEMPERATURE_CONFIG_KEY: 0.0,
+    MAX_COMPLETION_TOKENS_CONFIG_KEY: 1,
+    LOGIT_BIAS_CONFIG_KEY: {
+        str(token_id): 100 for token_id in A_TO_C_TOKEN_IDS_CHATGPT
+    },
 }
 
 structlogger = structlog.get_logger()

rasa/dialogue_understanding/commands/clarify_command.py

@@ -117,9 +117,9 @@ class ClarifyCommand(Command):
     @staticmethod
     def regex_pattern() -> str:
         mapper = {
-            CommandSyntaxVersion.v1: r"Clarify\(([\"\'a-zA-Z0-9_, ]*)\)",
+            CommandSyntaxVersion.v1: r"Clarify\(([\"\'a-zA-Z0-9_, -]*)\)",
             CommandSyntaxVersion.v2: (
-                r"""^[\s\W\d]*disambiguate flows (["'a-zA-Z0-9_, ]*)['"`]*$"""
+                r"""^[\s\W\d]*disambiguate flows (["'a-zA-Z0-9_, -]*)['"`]*$"""
             ),
         }
         return mapper.get(

rasa/dialogue_understanding/commands/knowledge_answer_command.py

@@ -65,7 +65,7 @@ class KnowledgeAnswerCommand(FreeFormAnswerCommand):
         """Converts the command to a DSL string."""
         mapper = {
             CommandSyntaxVersion.v1: "SearchAndReply()",
-            CommandSyntaxVersion.v2: "provide info",
+            CommandSyntaxVersion.v2: "search and reply",
         }
         return mapper.get(
             CommandSyntaxManager.get_syntax_version(),
@@ -81,7 +81,7 @@ class KnowledgeAnswerCommand(FreeFormAnswerCommand):
     def regex_pattern() -> str:
         mapper = {
             CommandSyntaxVersion.v1: r"SearchAndReply\(\)",
-            CommandSyntaxVersion.v2: r"""^[\s\W\d]*provide info['"`]*$""",
+            CommandSyntaxVersion.v2: r"""^[\s\W\d]*search and reply['"`]*$""",
         }
         return mapper.get(
             CommandSyntaxManager.get_syntax_version(),

rasa/dialogue_understanding/generator/constants.py

@@ -1,5 +1,5 @@
 from rasa.shared.constants import (
-    MAX_TOKENS_CONFIG_KEY,
+    MAX_COMPLETION_TOKENS_CONFIG_KEY,
     MODEL_CONFIG_KEY,
     OPENAI_PROVIDER,
     PROVIDER_CONFIG_KEY,
@@ -15,7 +15,7 @@ DEFAULT_LLM_CONFIG = {
     PROVIDER_CONFIG_KEY: OPENAI_PROVIDER,
     MODEL_CONFIG_KEY: DEFAULT_OPENAI_CHAT_MODEL_NAME_ADVANCED,
     TEMPERATURE_CONFIG_KEY: 0.0,
-    MAX_TOKENS_CONFIG_KEY: DEFAULT_OPENAI_MAX_GENERATED_TOKENS,
+    MAX_COMPLETION_TOKENS_CONFIG_KEY: DEFAULT_OPENAI_MAX_GENERATED_TOKENS,
     TIMEOUT_CONFIG_KEY: 7,
 }
 

rasa/dialogue_understanding/generator/llm_based_command_generator.py

@@ -527,7 +527,7 @@ class LLMBasedCommandGenerator(
         either contain a StartFlowCommand or a SetSlot command
         for the current collect step.
         """
-        return self.config.get(KEY_MINIMIZE_NUM_CALLS, False) and (
+        return self.config.get(KEY_MINIMIZE_NUM_CALLS, True) and (
             self._prior_commands_contain_start_flow(prior_commands)
             or self._prior_commands_contain_set_slot_for_active_collect_step(
                 prior_commands, flows, tracker

rasa/dialogue_understanding/generator/prompt_templates/command_prompt_v2_gpt_4o_2024_11_20_template.jinja2

@@ -1,5 +1,5 @@
 ## Task Description
-Your task is to analyze the current conversation context and generate a list of actions to start new business processes that we call flows, to extract slots, or respond to small talk and knowledge requests.
+Your task is to analyze the current conversation context and generate a list of actions to start new business processes that we call flows, to extract slots, or respond to off-topic and knowledge requests.
 
 ---
 
@@ -12,31 +12,52 @@ Use the following structured data:
 ---
 
 ## Available Actions:
-* `start flow flow_name`: Starting a flow. For example, `start flow transfer_money` or `start flow list_contacts`.
-* `set slot slot_name slot_value`: Slot setting. For example, `set slot transfer_money_recipient Freddy`. Can be used to correct and change previously set values.
-* `cancel flow`: Cancelling the current flow.
-* `disambiguate flows flow_name1 flow_name2 ... flow_name_n`: Disambiguate which flow should be started when user input is ambiguous by listing the potential flows as options. For example, `disambiguate flows list_contacts add_contact remove_contact ...` if the user just wrote "contacts".
-* `provide info`: Responding to the user's questions by supplying relevant information, such as answering FAQs or explaining services.
-* `offtopic reply`: Responding to casual or social user messages that are unrelated to any flows, engaging in friendly conversation and addressing off-topic remarks.
-* `hand over`: Handing over to a human, in case the user seems frustrated or explicitly asks to speak to one.
+* `start flow flow_name`: Start a flow. For example, `start flow transfer_money` or `start flow list_contacts`.
+* `set slot slot_name slot_value`: Set a slot for the active flow. For example, `set slot transfer_money_recipient Freddy`. Can be used to correct and change previously set values.
+* `disambiguate flows flow_name1 flow_name2 ... flow_name_n`: When a message could refer to multiple flows, list the possible flows as options to clarify. Example: `disambiguate flows list_contacts add_contact remove_contact`.
+* `search and reply`: Provide a response from the knowledge base to address the user’s inquiry when no flows fit, including domain knowledge, FAQs, and all off-topic or social messages.
+* `cancel flow`: Cancel the current flow if the user requests it.
 
 ---
 
-## General Tips
+## General Instructions
+### Start Flow
+* Only start a flow if the user's message is clear and fully addressed by that flow's description and purpose.
+* Pay close attention to exact wording and scope in the flow description — do not assume or “stretch” the intended use of a flow.
+### Set Slot
 * Do not fill slots with abstract values or placeholders.
 * For categorical slots try to match the user message with allowed slot values. Use "other" if you cannot match it.
 * Set the boolean slots based on the user response. Map positive responses to `True`, and negative to `False`.
 * Extract text slot values exactly as provided by the user. Avoid assumptions, format changes, or partial extractions.
+### Disambiguate Flows
+* Use `disambiguate flows` when the user's message matches multiple flows and you cannot decide which flow is most appropriate.
+* If the user message is short and not precise enough to start a flow or `search and reply`, disambiguate.
+* If a single flow is a strong/plausible fit, prefer starting that flow directly.
+* If a user's message unambiguously and distinctly matches multiple flows, start all relevant flows at once (rather than disambiguating).
+### Search and Reply
+* Only start `search and reply` if the user intent is clear.
+* Flow Priority: If you are unsure between starting a flow or `search and reply`, always prioritize starting a flow.
+### Cancel Flow
+* Do not cancel any flow unless the user explicitly requests it.
+* Multiple flows can be started without cancelling the previous, if the user wants to pursue multiple processes.
+### General Tips
 * Only use information provided by the user.
-* Use clarification in ambiguous cases.
-* Multiple flows can be started. If a user wants to digress into a second flow, you do not need to cancel the current flow.
-* Do not cancel the flow unless the user explicitly requests it.
 * Strictly adhere to the provided action format.
 * Focus on the last message and take it one step at a time.
 * Use the previous conversation steps only to aid understanding.
 
 ---
 
+## Decision Rule Table
+| Condition                                             | Action             |
+|-------------------------------------------------------|--------------------|
+| Flow perfectly matches user's message                 | start flow         |
+| Multiple flows are equally strong, relevant matches   | disambiguate flows |
+| User's message is unclear or imprecise                | disambiguate flows |
+| No flow fits at all, but knowledge base may help      | search and reply   |
+
+---
+
 ## Current State
 {% if current_flow != None %}Use the following structured data:
 ```json

rasa/dialogue_understanding/generator/single_step/compact_llm_command_generator.py

@@ -47,7 +47,7 @@ from rasa.shared.constants import (
     AWS_BEDROCK_PROVIDER,
     AZURE_OPENAI_PROVIDER,
     EMBEDDINGS_CONFIG_KEY,
-    MAX_TOKENS_CONFIG_KEY,
+    MAX_COMPLETION_TOKENS_CONFIG_KEY,
     PROMPT_TEMPLATE_CONFIG_KEY,
     ROUTE_TO_CALM_SLOT,
     TEMPERATURE_CONFIG_KEY,
@@ -81,7 +81,7 @@ DEFAULT_LLM_CONFIG = {
     PROVIDER_CONFIG_KEY: OPENAI_PROVIDER,
     MODEL_CONFIG_KEY: MODEL_NAME_GPT_4O_2024_11_20,
     TEMPERATURE_CONFIG_KEY: 0.0,
-    MAX_TOKENS_CONFIG_KEY: DEFAULT_OPENAI_MAX_GENERATED_TOKENS,
+    MAX_COMPLETION_TOKENS_CONFIG_KEY: DEFAULT_OPENAI_MAX_GENERATED_TOKENS,
     TIMEOUT_CONFIG_KEY: 7,
 }
 

rasa/hooks.py

@@ -12,7 +12,7 @@ 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
 
@@ -80,7 +80,7 @@ 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):

rasa/keys

@@ -0,0 +1 @@
+{"segment": "CcvVD1I68Nkkxrv93cIqv1twIwrwG8nz", "sentry": "a283f1fde04347b099c8d729109dd450@o251570"}

rasa/llm_fine_tuning/paraphrasing/conversation_rephraser.py

@@ -11,10 +11,12 @@ from rasa.llm_fine_tuning.paraphrasing.rephrased_user_message import (
 )
 from rasa.shared.constants import (
     LLM_CONFIG_KEY,
+    MAX_COMPLETION_TOKENS_CONFIG_KEY,
     MODEL_CONFIG_KEY,
     MODEL_NAME_CONFIG_KEY,
     PROMPT_TEMPLATE_CONFIG_KEY,
     PROVIDER_CONFIG_KEY,
+    TEMPERATURE_CONFIG_KEY,
     TIMEOUT_CONFIG_KEY,
 )
 from rasa.shared.exceptions import ProviderClientAPIException
@@ -39,8 +41,8 @@ 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 os
 import sys
 
+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

@@ -532,8 +532,7 @@ 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

@@ -278,6 +278,7 @@ def start_training_process(
                 "--keep-local-model-copy",
                 "--remote-storage",
                 config.SERVER_MODEL_REMOTE_STORAGE,
+                "--remote-root-only",
             ]
         )
 

rasa/model_training.py

@@ -160,6 +160,7 @@ 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).
 
@@ -187,6 +188,8 @@ 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`.
@@ -269,6 +272,7 @@ 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 {}),
         )
@@ -284,6 +288,7 @@ 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/nlu/extractors/crf_entity_extractor.py

@@ -1,9 +1,11 @@
 from __future__ import annotations
 
 import logging
+import shutil
 import typing
 from collections import OrderedDict
 from enum import Enum
+from pathlib import Path
 from typing import Any, Callable, Dict, List, Optional, Text, Tuple, Type
 
 import numpy as np
@@ -43,6 +45,10 @@ if typing.TYPE_CHECKING:
 
 CONFIG_FEATURES = "features"
 
+TAGGERS_DIR = "taggers"
+CRFSUITE_MODEL_FILE_NAME = "model.crfsuite"
+PLAIN_CRF_MODEL_FILE_NAME = "model.txt"
+
 
 class CRFToken:
     def __init__(
@@ -419,19 +425,11 @@ class CRFEntityExtractor(GraphComponent, EntityExtractorMixin):
         """Loads trained component (see parent class for full docstring)."""
         try:
             with model_storage.read_from(resource) as model_dir:
-                dataset = rasa.shared.utils.io.read_json_file(
-                    model_dir / "crf_dataset.json"
-                )
                 crf_order = rasa.shared.utils.io.read_json_file(
                     model_dir / "crf_order.json"
                 )
 
-                dataset = [
-                    [CRFToken.create_from_dict(token_data) for token_data in sub_list]
-                    for sub_list in dataset
-                ]
-
-                entity_taggers = cls.train_model(dataset, config, crf_order)
+                entity_taggers = cls._load_taggers(model_dir, config)
 
                 entity_extractor = cls(config, model_storage, resource, entity_taggers)
                 entity_extractor.crf_order = crf_order
@@ -443,19 +441,71 @@ class CRFEntityExtractor(GraphComponent, EntityExtractorMixin):
             )
             return cls(config, model_storage, resource)
 
+    @classmethod
+    def _load_taggers(
+        cls, model_dir: Path, config: Dict[Text, Any]
+    ) -> Dict[str, "CRF"]:
+        """
+        Load taggers from model directory that persists trained binary
+        `model.crfsuite` files.
+        """
+
+        import pycrfsuite
+        import sklearn_crfsuite
+
+        # Get tagger directories
+        taggers_base = model_dir / TAGGERS_DIR
+        if not taggers_base.exists():
+            return {}
+
+        taggers_dirs = [
+            directory for directory in taggers_base.iterdir() if directory.is_dir()
+        ]
+
+        entity_taggers: Dict[str, "CRF"] = {}
+
+        for tagger_dir in taggers_dirs:
+            # Instantiate sklearns CRF wrapper for the pycrfsuite's Tagger
+            entity_tagger = sklearn_crfsuite.CRF(
+                algorithm="lbfgs",
+                # coefficient for L1 penalty
+                c1=config["L1_c"],
+                # coefficient for L2 penalty
+                c2=config["L2_c"],
+                # stop earlier
+                max_iterations=config["max_iterations"],
+                # include transitions that are possible, but not observed
+                all_possible_transitions=True,
+            )
+
+            # Load pycrfsuite tagger from the persisted binary model.crfsuite file
+            entity_tagger._tagger = pycrfsuite.Tagger()
+            entity_tagger._tagger.open(str(tagger_dir / CRFSUITE_MODEL_FILE_NAME))
+
+            entity_taggers[tagger_dir.name] = entity_tagger
+
+        return entity_taggers
+
     def persist(self, dataset: List[List[CRFToken]]) -> None:
         """Persist this model into the passed directory."""
         with self._model_storage.write_to(self._resource) as model_dir:
-            data_to_store = [
-                [token.to_dict() for token in sub_list] for sub_list in dataset
-            ]
-
-            rasa.shared.utils.io.dump_obj_as_json_to_file(
-                model_dir / "crf_dataset.json", data_to_store
-            )
             rasa.shared.utils.io.dump_obj_as_json_to_file(
                 model_dir / "crf_order.json", self.crf_order
             )
+            if self.entity_taggers is not None:
+                for tag_name, entity_tagger in self.entity_taggers.items():
+                    # Create the directories for storing the CRF model
+                    tagger_dir = model_dir / TAGGERS_DIR / tag_name
+                    tagger_dir.mkdir(parents=True, exist_ok=True)
+                    # Create a plain text version of the CRF model
+                    entity_tagger.tagger_.dump(
+                        str(tagger_dir / PLAIN_CRF_MODEL_FILE_NAME)
+                    )
+                    # Persist binary version of the model.crfsuite
+                    shutil.copy2(
+                        src=entity_tagger.modelfile.name,
+                        dst=tagger_dir / CRFSUITE_MODEL_FILE_NAME,
+                    )
 
     @classmethod
     def _crf_tokens_to_features(

rasa/plugin.py

@@ -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

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

@@ -197,7 +197,10 @@ 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"