RAG

When Switching Embeddings Doubles Recall: bge-m3 vs nomic on a Local RAG

2026-07-06 by [Mathias WOLFF]

ai rag embedding bge‑m3 nomic ollama chromadb methodology wazo

On a 100% private local RAG, replacing nomic-embed-text with bge-m3 and dropping runtime FR→EN translation took recall from 0.45 to 0.95 and cut latency by twelve. Measured, not guessed.

Vault knowledge base + AI agent: 7 design decisions for the long run

2026-05-22 by [Mathias WOLFF] (updated: 2026-06-03)

ai agent knowledge‑base obsidian markdown methodology rag

A Markdown knowledge base built to last several years, with an AI agent and vector search. Seven design choices are documented along with their costs.