Skip to content

NluImprovementSpecification

Source code in docs_src/capo_lex_models_v2/types/nlu_improvement_specification.py 
13
14
15
16
17
18
19
20
21
22
23
class NluImprovementSpecification(TypedDict, closed=True):
    enabled: "capo_lex_models_v2.types.enabled.Enabled"
    """<p>Determines whether the Assisted NLU feature is enabled for the bot. When set to <code>true</code>, Amazon Lex uses advanced models to improve intent recognition and slot resolution, with the default being <code>false</code>.</p>"""
    assisted_nlu_mode: NotRequired[
        "capo_lex_models_v2.types.assisted_nlu_mode.AssistedNluMode"
    ]
    """<p>Specifies the mode for Assisted NLU operation. Use <code>Primary</code> to make Assisted NLU the primary intent recognition method, or <code>Fallback</code> to use it only when standard NLU confidence is low.</p>"""
    intent_disambiguation_settings: NotRequired[
        "capo_lex_models_v2.types.intent_disambiguation_settings.IntentDisambiguationSettings"
    ]
    """<p>An object containing specifications for the Intent Disambiguation feature within the Assisted NLU settings. These settings determine how the bot handles ambiguous user inputs that could match multiple intents.</p>"""

assisted_nlu_mode instance-attribute 

assisted_nlu_mode: NotRequired[AssistedNluMode]

Specifies the mode for Assisted NLU operation. Use Primary to make Assisted NLU the primary intent recognition method, or Fallback to use it only when standard NLU confidence is low.

enabled instance-attribute 

enabled: Enabled

Determines whether the Assisted NLU feature is enabled for the bot. When set to true, Amazon Lex uses advanced models to improve intent recognition and slot resolution, with the default being false.

intent_disambiguation_settings instance-attribute 

intent_disambiguation_settings: NotRequired[IntentDisambiguationSettings]

An object containing specifications for the Intent Disambiguation feature within the Assisted NLU settings. These settings determine how the bot handles ambiguous user inputs that could match multiple intents.