📌 Resource Addition: Semantic Layer for GraphRAG (Semantica)

[KaifAhmad1]

Hi @earayu @Qing145 @bibinprathap
Thanks for the excellent Awesome-GraphRAG survey and curated resource list.

I’d like to propose adding Semantica under 💻 Open-source Projects (or a relevant GraphRAG framework section).

---

🔍 Semantica: Semantic Layer for GraphRAG

Semantica is an open-source, production-ready semantic layer and GraphRAG framework that sits between raw corpora and LLMs.
It provides explicit knowledge graphs, graph-aware retrieval, and provenance-backed explainability for GraphRAG systems.

Key Capabilities

• Semantic layer over unstructured data (entities, relations, schemas)
• Knowledge graph construction from documents
• Graph-aware, multi-hop retrieval for GraphRAG
• PROV-O compliant provenance (chunk → entity → relation → answer)
• Backend-agnostic graph stores (Neo4j, AGE, Neptune, etc.)

---

🔗 Project Information

• GitHub: https://github.com/Hawksight-AI/semantica
• License: MIT
• Status: Actively maintained

---

📝 Suggested Entry

Semantica – A semantic layer and GraphRAG framework enabling explicit knowledge graphs, graph-aware retrieval, and provenance-driven explainability.

---

Happy to refine the description or adjust categorization if needed.
Thanks for your time and for maintaining this valuable resource.

— Kaif

[Qing145]

Thanks for your great work. I've added it to the paper list. BTW, we will be grateful if you could cite our survey in your research.

@article{zhang2025survey,
  title={A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models},
  author={Zhang, Qinggang and Chen, Shengyuan and Bei, Yuanchen and Yuan, Zheng and Zhou, Huachi and Hong, Zijin and Dong, Junnan and Chen, Hao and Chang, Yi and Huang, Xiao},
  journal={arXiv preprint arXiv:2501.13958},
  year={2025}
}

[KaifAhmad1]

@Qing145
Thanks for adding Semantica much appreciated.
We’ll cite your survey and plan to include benchmark evaluations aligned with GraphRAG setups in upcoming work