warn for invalid keys for components

changelog/6966.improvement.md

@@ -0,0 +1 @@
+Added warning for when an option is provided for a [component](components.mdx) that is not listed as a key in the defaults for that component.

rasa/nlu/components.py

@@ -91,13 +91,35 @@ def validate_requirements(component_names: List[Optional[Text]]) -> None:
         )
 
 
+def validate_component_keys(
+    component: "Component", component_config: Dict[Text, Any]
+) -> None:
+    """Validates that all keys for a component are valid.
+
+    Args:
+        component: The component class
+        component_config: The user-provided config for the component in the pipeline
+    """
+    component_name = component_config.get("name")
+    allowed_keys = set(component.defaults.keys())
+    provided_keys = set(component_config.keys())
+    provided_keys = (key for key in provided_keys if key != "name")
+    list_separator = "\n- "
+    for key in provided_keys:
+        if key not in allowed_keys:
+            rasa.shared.utils.io.raise_warning(
+                f"You have provided an invalid key `{key}` for component `{component_name}` in your pipeline. "
+                f"Valid options for `{component_name}` are:\n- "
+                f"{list_separator.join(allowed_keys)}"
+            )
+
+
 def validate_empty_pipeline(pipeline: List["Component"]) -> None:
     """Ensures the pipeline is not empty.
 
     Args:
         pipeline: the list of the :class:`rasa.nlu.components.Component`.
     """
-
     if len(pipeline) == 0:
         raise InvalidConfigError(
             "Can not train an empty pipeline. "

rasa/nlu/model.py

@@ -161,13 +161,13 @@ def _build_pipeline(
         self, cfg: RasaNLUModelConfig, component_builder: ComponentBuilder
     ) -> List[Component]:
         """Transform the passed names of the pipeline components into classes."""
-
         pipeline = []
 
         # Transform the passed names of the pipeline components into classes
-        for i in range(len(cfg.pipeline)):
-            component_cfg = cfg.for_component(i)
+        for index, pipeline_component in enumerate(cfg.pipeline):
+            component_cfg = cfg.for_component(index)
             component = component_builder.create_component(component_cfg, cfg)
+            components.validate_component_keys(component, cfg.pipeline[index])
             pipeline.append(component)
 
         if not self.skip_validation:

tests/nlu/test_components.py

@@ -7,6 +7,7 @@
 from rasa.nlu.components import Component, ComponentBuilder, find_unavailable_packages
 from rasa.nlu.config import InvalidConfigError, RasaNLUModelConfig
 from rasa.nlu.model import Interpreter, Metadata
+from tests.nlu.conftest import DEFAULT_DATA_PATH
 
 
 @pytest.mark.parametrize("component_class", registry.component_classes)
@@ -98,7 +99,7 @@ async def test_example_component(component_builder: ComponentBuilder, tmp_path:
 
     (trainer, trained, persisted_path) = await train(
         _config,
-        data="./data/examples/rasa/demo-rasa.json",
+        data=DEFAULT_DATA_PATH,
         path=str(tmp_path),
         component_builder=component_builder,
     )
@@ -198,5 +199,19 @@ async def test_validate_requirements_raises_exception_on_component_without_name(
 
     with pytest.raises(InvalidConfigError):
         await train(
-            _config, data="./data/examples/rasa/demo-rasa.json", path=str(tmp_path),
+            _config, data=DEFAULT_DATA_PATH, path=str(tmp_path),
         )
+
+
+async def test_validate_component_keys_raises_warning_on_invalid_key(tmp_path: Path,):
+    _config = RasaNLUModelConfig(
+        # config with a component that does not have a `confidence_threshold ` property
+        {"pipeline": [{"name": "WhitespaceTokenizer", "confidence_threshold": 0.7}]}
+    )
+
+    with pytest.warns(UserWarning) as record:
+        await train(
+            _config, data=DEFAULT_DATA_PATH, path=str(tmp_path),
+        )
+
+    assert "You have provided an invalid key" in record[0].message.args[0]