> For the complete documentation index, see [llms.txt](https://docs.datasaur.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.datasaur.ai/advanced/extensions/ml-assisted-labeling.md).
# ML-Assisted Labeling
ML-assisted labeling extension lets you use open-source models, LLMs, or your own models to generate labels automatically.
## Overview
**ML-assisted labeling** helps automate data labeling for NLP projects. It supports open-source models, large language models (LLMs), and custom models for both span-based and row-based labeling tasks.
The extension generates labels automatically, helping reduce manual effort and allowing users to focus on reviewing results.
## Use cases
### Sentiment analysis
Use **ML-assisted labeling** to classify sentiment in reviews or other text data.
1. Create a row labeling project.
2. Click the gear icon from the extension panel on the right to open the **Manage extensions** dialog, and enable the **ML-assisted labeling** extension.
3. Select [**Sentiment Analysis**](/assisted-labeling/ml-assisted-labeling/sentiment-analysis.md) as the service provider.
4. Configure **Target text** and **Target question**.
5. Click **Predict labels**.
6. Review the predicted labels and click **Accept** or **Reject**.
### Span labeling with spaCy
Use the spaCy provider to automatically label entities in text.
1. Create a span labeling project.
2. Click the gear icon from the extension panel on the right to open the **Manage extensions** dialog, and enable the **ML-assisted labeling** extension.
3. Select [**spaCy**](/assisted-labeling/ml-assisted-labeling/spacy.md) as the service provider.
4. Click **Predict labels**.
5. Review the predicted labels and click **Accept** or **Reject**.
{% hint style="info" %}
For more information about other providers, see [Assisted Labeling - ML-Assisted Labeling](/assisted-labeling/ml-assisted-labeling.md).
{% endhint %}
