...
Text completion offers the functionality of sending prompts to OpenAI in textual form and based on the prompt receiving an answer.
Input:
...
Prompt: This is your main input for which you want the AI to give you an answer or output of. This can be a question, an instruction, etc.
...
Best of Completions: This returns the best possible response(s) for your prompt. It defaults to 1. This works with the Number of Completion field to choose the best possible answer from a group of responses.
Response:
...
Map the response to custom field
You can select the text under the choices, and then you can see the JSON Path selected, and then you can save the response into your own user custom field, and then use this response in your flow builder.
Sample Response Data
| Code Block |
|---|
{
"id": "cmpl-6zchlUy0OiAjX91LHOPBcZjuXaDgE",
"object": "text_completion",
"created": 1680144809,
"model": "text-davinci-003",
"choices": [
{
"text": " 1. Understand Your Target Audience - Before you begin any marketing campaign, it’s important to have a clear understanding of who you’re targeting with your message. Researching and understanding your target audience will help you create campaigns specifically tailored to their interests. 2. Leverage Social Media - Social media has become one of the most effective ways to communicate with your target audience. Utilizing social media channels such as Facebook, Twitter, and Instagram can help you build",
"index": 0,
"logprobs": null,
"finish_reason": "length"
}
],
"usage": {
"prompt_tokens": 4,
"completion_tokens": 100,
"total_tokens": 104
}
} |
...
Prompt tokens : The number of tokens used to complete the task.
Best Practices:
Sometimes the completed response you get back seems to be cut off. This is due to the lack of the number of tokens required for the completion of the task. Simply adjusting the value of Max tokens inside the input fields will fix this issue.
It is also advised to adjust values like temperature, the number of completions, best of completions, etc to your use case by means of split testing. Every use case is unique and you should want the best possible utilisation of the resources available.
Image Generation
Image Generation is used to generate images based on the user-input prompts. This feature will generate the best possible image that matches your given prompt.
Input:
...
Prompt : This is your main input for which you want the AI to generate an image for you. This can be a question, an instruction etc.
...
| Note |
|---|
Make sure that the first rows of all columns should be the input fields name such as type, heading, text etc. and none of them should start with a capital letter. |
Embedding Match & Completion Actions
...