Johannes Kaindl Uplink Deutsch

Ollama

Ollama runs local models from the command line. It's lightweight and reliable — and it's what vault-rag uses for embeddings, the small model that powers semantic search.

Steps

  1. Install — download from ollama.com, or brew install ollama. It runs as a background service.
  2. Pull an embedding model — for vault-rag's semantic search:
    ollama pull nomic-embed-text
    
    (vault-rag's default is qwen3-embedding — pull whichever your index was built with; see connect: vault-rag.)
  3. Pull a chat model — only needed for vault-rag's chat feature:
    ollama pull llama3.1
    
  4. The endpoint — Ollama listens on port 11434, OpenAI-compatible. See endpoint & model.

Common pitfalls

  • Enter the endpoint without /v1 (http://localhost:11434) — the plugin adds it. See the /v1 trap.
  • The embedding model in your plugin settings must match the one your index was built with — mismatched models give nonsense results.

→ Want it on your phone too? Use it mobile.