← All articles

#rag

3 articles

All articles tagged "rag" : self-hosted AI fixes, setups, and architecture notes.

A No-Vector RAG That Works: The Architecture, Decision by Decision

A No-Vector RAG That Works: The Architecture, Decision by Decision

The complete design of the retrieval system my local models run on: Markdown files, one JSON index, full-body BM25 chunked per section, served to agents over MCP. No vector database, no embeddings. Here is every decision and the reason behind it, with the external evidence that backs each one.

Read article →
I almost bolted a vector database onto a knowledge base that did not need one. My own benchmark told me to, then told me the opposite, both times with total confidence, both times because I had quietly chosen the test queries. Here is the path from the standard 2026 RAG playbook to the number that finally told the truth, and why the retriever that won is a hundred lines of standard library.
sovereign-aiself-hostedengineering-honestybenchmarking

I Rigged My Own RAG Benchmark. Twice.

I almost bolted a vector database onto a knowledge base that did not need one. My own benchmark told me to, then told me the opposite, both times with total confidence, both times because I had quietly chosen the test queries. Here is the path from the standard 2026 RAG playbook to the number that finally told the truth, and why the retriever that won is a hundred lines of standard library.
Giving a local 8B model persistent memory and retrieval good enough to replace a cloud assistant for daily coding. The architecture is mem0 plus a RAG knowledge base over ChromaDB. The honest part is the two bugs that made the first version forget you and answer the wrong question with full confidence.
mcpollamaqwenself-hostedsovereign-aiengineering-honestyagents

A Second Brain for a Local Model, and the Two Bugs That Made It Useless First

Giving a local 8B model persistent memory and retrieval good enough to replace a cloud assistant for daily coding. The architecture is mem0 plus a RAG knowledge base over ChromaDB. The honest part is the two bugs that made the first version forget you and answer the wrong question with full confidence.