Swapping OpenAI Embeddings for a Local Qwen3 Model

Mon, 14 Sep 2026 00:00:00 +0000

Introduction

I run a local-first knowledge base over my own notes. Markdown and PDFs in a folder get chunked, embedded, and stored in PostgreSQL with pgvector, and semantic search and a RAG chat sit on top. “Local-first” was true for the files and the database. It was not true for the embeddings: every chunk went to OpenAI’s text-embedding-3-small, through OpenRouter, with a pseudonymization layer replacing names and emails before the text left the machine.

Embeddings on Jamie Craane personal blog

Swapping OpenAI Embeddings for a Local Qwen3 Model

Introduction