intellectronica/battle-of-the-semantics

GraphRag vs Embeddings

22
/ 100
Experimental

Implements a comparative benchmark between Microsoft's GraphRag (which uses LLM-driven entity extraction to build knowledge graphs) and traditional embedding-based similarity search for RAG systems. GraphRag trades chunking simplicity for deeper semantic understanding through structured entity relationships, enabling more accurate context retrieval in complex reasoning scenarios. The analysis is presented as a Jupyter notebook with video walkthrough, directly comparing retrieval quality and relevance across both indexing methodologies.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 1 / 25
Community 15 / 25

How are scores calculated?

Stars

16

Forks

4

Language

Jupyter Notebook

License

Last pushed

Jul 14, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/intellectronica/battle-of-the-semantics"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.