to select · Esc to close

Ollama

Run chat, vision and model discovery against a local or hosted Ollama-compatible API.

Capabilities

CapabilityIdentifier
Chat completionai.chat
Vision messagesai.vision
Model discoveryai.models

Configuration

FieldTypeRequiredNotes
Server URL urlYesBase URL of the Ollama API, without /api.
API key secretpasswordNoSent as a Bearer token for hosted Ollama-compatible services.
Default model textYesDefault: llama3.2
Timeout numberYesDefault: 60

About

Connect GrowRig features to any Ollama-compatible API. The built-in runtime supports chat, vision messages containing Ollama image payloads, and model discovery. Create separate instances for local, cloud, or remote GPU servers.

The optional API key is encrypted at rest and is never returned to the browser. The connection test calls GET /api/version.

Integrations are configured as instances under Control panel → Integrations. Secret fields are AES-GCM encrypted with a local key beside the Grow Core database and are never returned by the API.