You are viewing the docs for Archestra v1.4. View the latest docs
Ollama
Run models on your own server with Ollama, and use them like any cloud model, with no API key. Pull a model with ollama pull <model-name> before you connect it.
Connecting Ollama
- Go to Model Providers → Add API Key and select Ollama.
- Choose Native or OpenAI-compatible transport.
- Set Base URL to your server. Native uses the server root, such as
http://model-server:11434; OpenAI-compatible useshttp://model-server:11434/v1. - Leave API Key blank for a local server, or enter the credential required by your deployment.
- Click Test & Create.
The server's pulled models appear under Models. Add one key entry per server. If Archestra runs in Docker and Ollama runs on the host, use host.docker.internal instead of localhost where your container runtime supports it.
| Transport | Proxy URL | Use |
|---|---|---|
| Native | https://<archestra-host>/v1/ollama-native | Ollama /api/chat and generation parameters |
| OpenAI-compatible | https://<archestra-host>/v1/ollama | Chat Completions, Embeddings, and Model Router |
Native model IDs cannot be used through the Model Router. For that endpoint, connect the OpenAI-compatible transport and use ollama:<model-id>.
Generation Parameters
Under Models, edit a native model and set Model parameters, including num_, num_, temperature, and thinking. Empty fields inherit Ollama's defaults. The OpenAI-compatible transport does not carry these Ollama-specific options.
If you cap the server's context with OLLAMA_, also set num_ on the model. The server does not report that global cap to Archestra. Models marked Limited for complex tasks may be less reliable for agents that call tools.
Default endpoints come from ARCHESTRA_ and ARCHESTRA_. Use a per-key Base URL to override them.