Generate a response with GPT3.5 turbo
Uses ChatGPT 3.5 with 120k input context and 4k output context to generate human-like responses to a given prompt or question.
Common use cases
- Generative AI
Application
- OpenAI GPT
Inputs (what you have)
| Name | Description | Data Type | Required? |
|---|---|---|---|
| Prompt | The prompt to generate completions for. Input will be truncated if it exceeds the limit set by the API | Text(Long) | Yes |
| System message | The message which sets the context and expectations for a conversation with the AI | Text(Long) | No |
| Temperature | Sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic | Number w/ decimals | No |
| Maximum length | The maximum number of tokens to generate in the completion. Increasing maximum length will decrease the amount of tokens available to the prompt | Integer | No |
| Frequency penalty | A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim | Number w/ decimals | No |
| Presence penalty | A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics | Number w/ decimals | No |
Note: the value of inputs can either be a set value in the configuration of the Wrk Action within the Wrkflow, or a variable from the Data library section. These variables in the Data library section are the outputs of previous Wrk Actions in the Wrkflow.
Outputs (what you get)
| Name | Description | Data Type | Required |
|---|---|---|---|
| Generated text | Text content created by artificial intelligence. | Text(Long) | Required |