ollama_generate
Generate text responses from Ollama models by sending prompts, with optional system prompts, streaming, and token/temperature controls.
Instructions
Generate a response from an Ollama model
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"prompt": "<prompt>"
},
"name": "ollama_generate"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Model name (e.g., llama3.2, mistral, deepseek-r1) | llama3.2 |
| prompt | Yes | The prompt to send to the model | |
| stream | No | Stream the response | |
| system | No | System prompt (optional) | |
| max_tokens | No | Maximum tokens to generate | |
| temperature | No | Temperature for sampling (0.0 to 1.0) |