Ollama

Run local large language models securely with Ollama.

Overview

Ollama is an open-source tool that allows you to run large language models locally. It is the premier choice for organizations that need strict data privacy or completely offline AI capabilities.

Privacy First

Your data never leaves your environment.

Ease of Use

Execute models with a simple ollama run <model> command.

Configuration

1. Install Ollama

   Download and install the runner from Ollama’s website, and pull a model (e.g., ollama pull llama3).

2. Configure Default URL

   Ollama defaults to running its API engine on localhost port 11434:

   .env

   OLLAMA_BASE_URL="http://localhost:11434"
   DEFAULT_MODEL="llama3"
   

If Arivu is running inside a Docker container, your host might need to be referenced via http://host.docker.internal:11434 instead of localhost.