Note: This is a minimal fork of HKUNLP/instructor-embedding created solely to fix installation issues within the Talemate project.

This fork exists only to resolve installation issues when using instructor-embedding with Talemate. There are no plans to maintain this fork beyond ensuring it remains functional for Talemate's needs.

• Python 3.10+ compatibility (supports 3.10, 3.11, 3.12, 3.13)
• Dependency conflicts that prevented clean installation in modern Python environments
• Migrated to pyproject.toml with Poetry support

pip install git+https://github.com/vegu-ai-tools/instructor-embedding.git

For all usage documentation, model details, and API reference, please see:

• Original Repository
• Original README

Apache License 2.0 (same as original project)

If you use this in research, please cite the original authors:

@inproceedings{INSTRUCTOR,
  title={One Embedder, Any Task: Instruction-Finetuned Text Embeddings},
  author={Su, Hongjin and Shi, Weijia and Kasai, Jungo and Wang, Yizhong and Hu, Yushi and  Ostendorf, Mari and Yih, Wen-tau and Smith, Noah A. and  Zettlemoyer, Luke and Yu, Tao},
  url={https://arxiv.org/abs/2212.09741},
  year={2022},
}