Ollama

Run and manage large language models locally or via Ollama Cloud. Generate text completions, conduct chat conversations, and create vector embeddings. Support tool calling (function calling), structured JSON outputs, log probability metadata, and thinking output where supported by the selected model. Manage models by pulling, pushing, creating, copying, deleting, listing local models, checking running models, showing model details, and reading the Ollama server version.

License

This integration is licensed under the FSL-1.1.