Scikit LLM: GPT text classification for scikit-learn

Understand the project

Practical overview

Use Scikit LLM when you want to incorporate a GPT classifier into a Python text-analysis workflow using a scikit-learn-style interface.

Python developers using scikit-learn who want to add LLM-based text classification.
Practitioners exploring sentiment labels or other zero-shot categories on text datasets.

Classify text with a GPT zero-shot classifier.
Use a familiar fit-and-predict pattern for LLM-backed text analysis.
Generate sentiment predictions for text labeled positive, negative or neutral in the demonstration.

Before you choose

The project is identified as open source under the MIT license. The documented example requires an OpenAI key and organization ID.

The demonstrated classifier uses OpenAI credentials and names GPT-4 as its model.
The README provides a pip installation command and a Python example, rather than a hosted interface.
The repository identifies Python as its primary language and lists scikit-learn and OpenAI in the project ecosystem.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Use Scikit-LLM’s GPT classifier on its demo text-classification dataset.

Install Scikit-LLM with the command below.
Documented command
```
pip install scikit-llm
```
Import get_classification_dataset, SKLLMConfig, and ZeroShotGPTClassifier from the modules shown in the README.
Set credentials with SKLLMConfig.set_openai_key("") and SKLLMConfig.set_openai_org("").
Load the demo data with X, y = get_classification_dataset(), create ZeroShotGPTClassifier(model="gpt-4"), then call clf.fit(X, y) and clf.predict(X).

The example invokes a GPT zero-shot classifier to predict labels for the demo text dataset, whose labels are positive, negative, and neutral.

Evidence and transparency

Source record details

Source availability: Active
Sources checked: 10 October 2026
Original website title: fnnx-ai/scikit-llm · Official homepage title · retained in its source language