Hi there! For rasa 2.x there was this script from Intents & Entities: Understanding the Rasa NLU Pipeline : from rasa.cli.utils import get_validated_path from rasa.model import get_model, get_model_subdirectories from rasa.core.interpreter import RasaNLUInterpreter from rasa.shared.nlu.training_data.message import Message def load_interpreter(model_dir, model): path_str = str(pathlib.Path(model_dir) / model) model = get_validated_path(path_str, "model") model_path = get_model(model) _, nlu_model = get_model_subdirectories(model_path) return RasaNLUInterpreter(nlu_model) # Loads the model mod = load_interpreter(model_dir, model) # Parses new text msg = Message({TEXT: text}) for p in interpreter.interpreter.pipeline: p.process(msg) print(msg.as_dict()) We could see the pipeline efect on a sentence. Do you know if there is something like it to 3.x ? Thanks a lot

NLU pipeline - Inspecting the Message-object yourself

anoopshrma (Anoop Sharma) March 15, 2023, 11:20am 2

Topic		Replies	Views
How to use a trained supervised_embeddings NLU pipeline to get the embedding of a user-inputted message? Rasa Open Source	2	1830	July 18, 2024
Using nlu model with Interpreter.load in Rasa 3.0 Rasa Open Source	13	6619	December 12, 2022
NLU Pipeline Debugging --- how to get and use an instance from a Rasa NLU Pipeline Rasa Open Source	3	860	May 16, 2022
USE INTERPRETER TO PREIDICT INTENT AND ENTITIES FOR BATCH OF SENTENCES! Rasa Open Source	3	621	July 21, 2022
Script to parse message with NLU pipeline Rasa Open Source	3	398	December 20, 2021