AutoIntent documentation#

AutoIntent is an open source tool for automatic configuration of a text classification pipeline for intent prediction.

Note

This project is under active development.

The task of intent detection is one of the main subtasks in creating task-oriented dialogue systems, along with scriptwriting and slot filling. AutoIntent project offers users the following:

  • A convenient library of methods for intent classification that can be used in a sklearn-like “fit-predict” format.

  • An AutoML approach to creating classifiers, where the only thing needed is to upload a set of labeled data.

Example of building an intent classifier in a couple of lines of code:

from autointent import Pipeline, Dataset

dataset = Dataset.from_json(path_to_json)
pipeline = Pipeline.default_optimizer(multilabel=False)
pipeline.fit(dataset)
pipeline.predict(["show me my latest recent transactions"])

Documentation Contents#

Quickstart#

It is recommended to begin with the Quickstart page. It contains overview of our capabilities and basic instructions for working with our library.

Key Concepts#

Key terms and concepts we use throughout our documentation.

User Guides#

A series of notebooks that demonstrate in detail and comprehensively the capabilities of our library and how to use it.

API Reference#

Pay special attention to the sections autointent.modules and autointent.metrics.

Learn AutoIntent#

Some theoretical background on dialogue systems and auto ML.