Testing Your Assistant

These docs are for version 1.x of Rasa Open Source.

User Guide

NLU

Core

Conversation Design

API Reference

Migrate from (beta)

Reference

Versions

viewing: 1.10.21

Testing Your Assistant

End-to-End Testing

Rasa Open Source lets you test dialogues end-to-end by running through test conversations and making sure that both NLU and Core make correct predictions.

Evaluating an NLU Model

A standard technique in machine learning is to keep some data separate as a test set.

Comparing NLU Pipelines

By passing multiple pipeline configurations to the CLI, Rasa will run a comparative examination between the pipelines.

Intent Classification

The evaluation script will produce a report, confusion matrix, and confidence histogram for your model.

Response Selection

The evaluation script will produce a combined report for all response selector models in your pipeline.

Entity Extraction

The CRFEntityExtractor is the only entity extractor which you train using your own data.

Entity Scoring

To evaluate entity extraction we apply a simple tag-based approach.

Evaluating a Core Model

You can evaluate your trained model on a set of test stories by using the evaluate script.

Comparing Core Configurations

To choose a configuration for your core model, you want to measure how well Rasa Core will generalise to conversations which it hasn’t seen before.