Send a prompt to the Ollama API running on this server.
Start a new conversation or select one from the sidebar.
Download a new model from the Ollama library. Browse available models at ollama.com/library
Controls randomness in responses. Lower values make output more focused and deterministic.
Controls diversity via nucleus sampling. Use with temperature for fine-tuned control.
Limits vocabulary to top K tokens. Higher values increase variety.
Maximum number of tokens to generate in the response.
Penalizes repetition. Higher values reduce repeated phrases.
Random seed for reproducible outputs. Use -1 for random.
Size of the context window in tokens.
The base URL for the Ollama API server.
Enable streaming responses for real-time output.
Timeout in seconds for API requests.