Practical overview
When it fits
Use AutoIntent when a Python project needs intent predictions from text and you want to fit a pipeline from labeled examples.
Who it is for
- Developers adding intent detection to task-oriented dialogue systems.
- Python practitioners building text classifiers from labeled examples.
Documented uses
- Configure and fit an intent classifier using labeled data.
- Reuse a fit-predict pipeline to classify incoming text by intent.
Requirements & limits
The project is open source under the Apache-2.0 license and documents installation with pip.
- The documented example expects labeled data loaded from JSON.
- The project is under active development, with bugs and breaking changes expected.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Set up and fit an intent-classification pipeline
Install AutoIntent, load labeled JSON data, fit a preset pipeline, and request an intent prediction.
Before you start
- Python environment with pip
- Labeled dataset in the JSON format accepted by Dataset.from_json
Steps
Install the library with the command below.
pip install autointentImport
PipelineandDatasetfromautointent.Load the dataset with
Dataset.from_json(path_to_json)and create a pipeline withPipeline.from_preset("classic-light").Fit the pipeline with
pipeline.fit(dataset), then pass text topipeline.predict(...).
Expected outcome
A fitted pipeline that returns a prediction for supplied text.
Guide limitations
- The README does not specify the JSON schema or prediction output format.
- The project is in development; the maintainers warn that bugs and breaking changes are expected.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 14 October 2026
- Original website title
- deeppavlov/AutoIntent · Official homepage title · retained in its source language