ComfyUI Node
Groq LLM
Uses Groq API to generate text from language models with conversation context.
Groq LLM
- api_response
- success
- status_code
- conversation_id
- chat_history
◄model▾►
◄preset▾►
◄system_message►
◄user_input►
◄temperature0.85►
◄max_tokens1024►
◄top_p1.00►
◄seed42►
◄max_retries2►
◄stop►
◄json_modefalse►
◄conversation_id►
Categoryapachellmpack
Inputs (12)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | Select the Large Language Model (LLM) to use. | |
| preset | COMBO | Select a preset or custom prompt for guiding the LLM. | |
| system_message | STRING | Optional system message to guide the LLM's behavior. | |
| user_input | STRING | User input or prompt to generate a response from the LLM. | |
| temperature | FLOAT | 0.850.1–2 | Controls randomness in responses. |
| max_tokens | INT | 10241–131072 | Maximum number of tokens to generate in the response. |
| top_p | FLOAT | 1.000.1–1 | Limits the pool of words the model can choose from based on their combined probability. |
| seed | INT | 420–4294967295 | Seed for random number generation, ensuring reproducibility. |
| max_retries | INT | 21–10 | Maximum number of retries in case of request failure. |
| stop | STRING | Stop generation when the specified sequence is encountered. | |
| json_mode | BOOLEAN | false | Enable JSON mode for structured output. |
| conversation_id | STRING | Unique identifier for the conversation. Leave empty for a new conversation. |
Outputs (5)
| Name | Type | Description |
|---|---|---|
| api_response | STRING | The API response. This is the text generated by the model |
| success | BOOLEAN | Whether the request was successful |
| status_code | STRING | The status code of the request |
| conversation_id | STRING | The unique identifier for the conversation |
| chat_history | STRING | The complete chat history |