Use ChatGPT-4 to ask questions of PNG, JPEG, WEBP, and GIF images.
Application
OpenAI
Inputs (what you have)
Name | Description | Data Type | Required? | Example |
Prompt | The question you would like answered about your image(s) | Text(Long) | Required | What is happening in this image? |
Maximum tokens in response | Defaults to 300. The maximum number of tokens that will be used to gerneate a response to your prompt | Number | Optional |
|
File input 1 | The file to be provided to the AI | File | Optional |
|
File input 2 | A second file to be provided to the AI | File | Optional |
|
File input 3 | A third file to be provided to the AI | File | Optional |
|
File Link 1 | A link to a file to be provided to the AI | Link | Optional |
|
File Link 2 | A link to a second file to be provided to the AI | Link | Optional |
|
File Link 3 | A link to a third file to be provided to the AI | Link | Optional |
|
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? | Example |
Generated text | Text content created by artificial intelligence. | Text(Long) | Yes |
|
Outcomes
Name | Description |
Success | This status is selected if text is generated for the file(s) and prompt provided. |
Impossible to Complete | This status is selected in the event of the following scenarios:
|
Requirements
N/A