appmixer.ai.mistral.SendPrompt
Send Prompt
1.0.0
Public
| Field | Type | Description |
|---|---|---|
| Instructions | textarea | The system instructions that the assistant uses. For example 'Be precise and concise.' |
| Prompt | textarea | The text input that the model will use to generate a response. |
| Model | text | Insert model ID or select a model to use for the request, for example mistral-small-latest. |
| Conversation ID | text | The unique identifier of the conversation. If provided, the model's response will be saved and used to continue the conversation in subsequent prompts with the same ID. If not provided, a new conversation is started each time. |
| Temperature | number | Controls the randomness of the model, usually between 0.0 and 1.0. Lower values make the output more focused and deterministic, higher values more creative. |
| Max Tokens | number | The maximum number of completion tokens returned by the API. The total length of input tokens and generated tokens is limited by the model's context length. |
| Top P | number | Nucleus sampling threshold, valued between 0 and 1. We generally recommend altering this or temperature but not both. |
| Random Seed | number | The seed to use for random sampling. If set, different calls with the same seed will produce deterministic results. |
| Safe Prompt | toggle | Whether to inject a safety prompt before all conversations. |
| Field | Type | Description |
|---|---|---|
| Answer | string | - |
| Prompt | string | - |
| ID | string | - |
| Model | string | - |
| Created Timestamp | integer | - |
| Finish Reason | string | - |
| Usage | object | - |