LinkTransformer

Spec sheet

Purpose

LinkTransformer is a Python package for record linkage using transformer models.Read 9 Oct 2026 · linktransformer.github.io

Product

LinkTransformer is a Python package for semantic record linkage, candidate retrieval, row transformation, clustering, and text classification over tabular data.Read 4 Oct 2026 · github.com

Integrations

The site describes integrations with Hugging Face Hub, OpenAI models, and Hugging Face models.Read 9 Oct 2026 · linktransformer.github.io

Support

The site invites users to contribute through the repository and raise issues with feature requests.Read 9 Oct 2026 · linktransformer.github.io

License

The repository states that the project is licensed under the MIT License.Read 4 Oct 2026 · github.com

Coming soon

The site lists FAISS GPU, cuDF, cuML, and cuGraph integration as coming soon.Read 9 Oct 2026 · linktransformer.github.io

Custom training

Users can train record linkage models on their own data or fine-tune pretrained Hugging Face models.Read 9 Oct 2026 · linktransformer.github.io

Data operations

It supports dataframe deduplication, clustering, and merges.Read 9 Oct 2026 · linktransformer.github.io

Installation

The site gives `pip install linktransformer` as the installation command.Read 9 Oct 2026 · linktransformer.github.io

Learning resources

The repository links tutorials for record linkage, training a model, and text classification, plus a Hugging Face demo app.Read 4 Oct 2026 · github.com

Model sharing

The package integrates with Hugging Face Hub for uploading and downloading models.Read 9 Oct 2026 · linktransformer.github.io

Model support

It supports models from Hugging Face Hub and OpenAI embedding models.Read 9 Oct 2026 · linktransformer.github.io

Open source

The project repository states that LinkTransformer is licensed under the MIT License.Read 9 Oct 2026 · github.com

Requirements

The package listing states that Python 3.11 or later is required.Read 9 Oct 2026 · pypi.org

Support and contribution

The website invites users to collaborate, and the repository says issues and pull requests are welcome.Read 4 Oct 2026 · github.com

Text classification

It can classify dataframe rows with OpenAI and Hugging Face models, including binary and multiclass classification.Read 9 Oct 2026 · linktransformer.github.io

Upcoming capabilities

The website lists hard-negative mining, GPU and RAPIDS integrations, convenience wrappers, and vision or multimodal support as coming soon.Read 4 Oct 2026 · linktransformer.github.io

Use cases

The maker’s website describes dataframe operations including deduplication, clustering, and multilingual merges.Read 4 Oct 2026 · linktransformer.github.io

Where Specifiction places it

• Data Deduplication Software#25 of 276.7