This demo showcases a premium RAG (Retrieval-Augmented Generation) experience, comparing a base LLM with a ZeroEntropy-enhanced model. It uses ZeroEntropy for world-class retrieval and Ollama for private, local generation and Langfuse for metrics, traces and prompts management.
Fast MLX port of ZeroEntropy zerank-2 cross-encoder reranker. 10x faster than PyTorch MPS on Apple Silicon. bf16, validated.
Semantic search over your Gmail, from inside Claude Code. Embeds your full inbox with zembed-1 and reranks with zerank-2 — finds emails by meaning, not keywords.
Add a description, image, and links to the zeroentropy topic page so that developers can more easily learn about it.
To associate your repository with the zeroentropy topic, visit your repo's landing page and select "manage topics."