ComfyUI Node
Griptape Agent Config: Ollama Drivers
Ollama Prompt Driver. Use local models with Ollama. Available at https://ollama.com
Griptape Agent Config: Ollama Drivers
- CONFIG
◄base_urlhttp://127.0.0.1►
◄port11434►
◄prompt_model_commentPrompt Driver►
◄model—►
◄max_attempts_on_fail2►
◄temperature0.10►
◄seed10342349342►
◄use_native_toolstrue►
◄max_tokens-1►
◄min_p0.10►
◄top_k40►
◄keep_alive240►
◄embedding_model_commentEmbedding Driver►
◄embedding_model—►
CategoryGriptape/Agent Configs
Inputs (14)
| Name | Type | Default | Description |
|---|---|---|---|
| base_url | STRING | http://127.0.0.1 | The base URL of the Ollama server |
| port | STRING | 11434 | The port of the Ollama server |
| prompt_model_commentopt | STRING | Prompt Driver | — |
| modelopt | STRING | The prompt model to use | |
| max_attempts_on_failopt | INT | 21–100 | Maximum attempts on failure |
| temperatureopt | FLOAT | 0.100–1 | Temperature for sampling |
| seedopt | INT | 10342349342 | Seed for random number generation |
| use_native_toolsopt | BOOLEAN | true | Use native tools for the LLM. |
| max_tokensopt | INT | -1 | Maximum tokens to generate. If <=0, it will use the default based on the tokenizer. |
| min_popt | FLOAT | 0.100–1 | Minimum probability for sampling. Lower values will be more random. |
| top_kopt | INT | 40 | Top k for sampling. Lower values are more deterministic. |
| keep_aliveopt | INT | 240 | Seconds to keep the connection alive |
| embedding_model_commentopt | STRING | Embedding Driver | — |
| embedding_modelopt | STRING | The embedding model to use |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| CONFIG | CONFIG | — |