Skip to main content

Ollama Embedding

Ollama runs embedding models locally or on your own server. Unstract connects to a running Ollama instance over its base URL — no API key required.

Getting started with Ollama​

  1. Install Ollama and start the server.
  2. Pull an embedding model, for example: ollama pull mxbai-embed-large. Browse models at ollama.com/search.

Setting up the Ollama Embedding model in Unstract​

  • Sign in to the Unstract Platform.
  • From the side navigation menu, choose Settings 🞂 Embedding.
  • Click on the New Embedding Profile button.
  • From the list of Embeddings, choose Ollama.
  • Name — a unique name for this adapter instance.
  • Model Name — the pulled model to use (for example mxbai-embed-large).
  • Base URL — where the Ollama server is running (for example http://host.docker.internal:11434 or http://localhost:11434).
  • Leave Max Retries at its default.
  • Click on Test Connection and ensure it succeeds, then click Submit.