Skip to the content
Know your tech before you buy it. Makers: get listed from $49/mo

pyJedAI

pyjedai.readthedocs.io

  • Free plan
  • Windows
  • Linux
  • Self-hosted

What pyJedAI is

pyJedAI is a free, open-source Python framework for entity resolution and link discovery. It accepts structured and semi-structured data, with pandas DataFrames used in its documented workflow. That workflow moves from reading data through block construction and cleaning, entity matching, clustering, and results that include scores and visualizations. The project lists supervised and unsupervised machine-learning methods, and says matching and blocking can use deep learning and natural-language processing. Tutorials cover embedding-based blocking with PyTorch and Gensim vectorizers, followed by nearest-neighbor search with FAISS. Documentation also presents schema matching through Valentine methods such as Similarity Flooding, Cupid, COMA, EmbDI, and SemProp. A geospatial interlinking component includes spatial filtering, initialization, and verification. Installation is documented through PyPI, a local Git checkout, or Docker. pyJedAI supports Linux, Windows, and self-hosting, requires Python 3.8 or later, and offers an API.

Who it suits

It suits developers, IT teams, and research users working with entity resolution, schema matching, or linked data. The project describes itself as suitable for both novice and expert users.

Good to know, and what to watch

  • Free, open-source Apache-2.0 Python library
  • Handles structured and semi-structured data
  • Supervised and unsupervised machine-learning methods
  • Schema matching through several Valentine methods
  • Installation via PyPI, Git checkout, or Docker
  • Requires Python 3.8 or later
  • Windows requires Microsoft Visual C++ 14.0
  • Security support covers version 0.0.x
  • Windows and Linux are the stated tested systems

pyJedAI

Free

Open source

The verdict

pyJedAI combines entity resolution, schema matching, geospatial interlinking, and multiple machine-learning approaches in one Python framework. Its documented installation paths and free open-source licensing make it suitable for teams building their own data-matching workflows.

What the maker publishes

Algorithms
The project lists supervised and unsupervised machine-learning techniques and says its matching and blocking can use deep learning and NLP techniques. source
Embedding tools
A tutorial documents embedding-based blocking with PyTorch and Gensim vectorizers and nearest-neighbor search using FAISS. source
Geospatial feature
The documentation includes a geospatial interlinking component with spatial filtering, initialization, and verification steps. source
Input data
It processes structured and semi-structured data, using pandas DataFrames as input in the documented workflow. source
Installation
The project documents installation from PyPI, local Git checkout, and Docker. source
Intended users
The project describes pyJedAI as intended for both expert and novice users and identifies developers, IT, and science/research audiences in its PyPI classifiers. source
Maker
The project identifies itself as a research project by the AI-Team of the Department of Informatics and Telecommunications at the University of Athens. source
Operating systems
The project says pyJedAI has been tested on Windows and Linux and requires Python 3.8 or later; Windows also requires Microsoft Visual C++ 14.0. source
Purpose
pyJedAI is an open-source Python framework for entity resolution and link discovery. source
Schema matching
The documentation shows pyJedAI schema matching with Valentine methods including Similarity Flooding, Cupid, COMA, EmbDI, and SemProp. source
Security
The repository security policy lists version 0.0.x as supported for security updates and directs users to report bugs through an issue or discussion. source
Support
The project recommends GitHub Discussions for general questions and discussions and links to its issue tracker for bugs. source
Workflow
Its documented workflow covers data reading, block building and cleaning, entity matching, clustering, and results with scores and visualizations. source

Checked against the maker's pages on 4 Oct 2026.