# Owlen Ollama

This crate provides an implementation of the `owlen-core::Provider` trait for the [Ollama](https://ollama.ai) backend.

It allows Owlen to communicate with a local Ollama instance, sending requests and receiving responses from locally-run large language models. You can also target [Ollama Cloud](https://docs.ollama.com/cloud) by pointing the provider at `https://ollama.com` (or `https://api.ollama.com`) and providing an API key through your Owlen configuration (or the `OLLAMA_API_KEY` / `OLLAMA_CLOUD_API_KEY` environment variables). The client automatically adds the required Bearer authorization header when a key is supplied, accepts either host without rewriting, and expands inline environment references like `$OLLAMA_API_KEY` if you prefer not to check the secret into your config file. The generated configuration now includes both `providers.ollama` and `providers.ollama-cloud` entries—switch between them by updating `general.default_provider`.

## Configuration

To use this provider, you need to have Ollama installed and running. The default address is `http://localhost:11434`. You can configure this in your `config.toml` if your Ollama instance is running elsewhere.