Smartstaff
2,361
edits
Changes
Created page with "==Overview== This article is about the '''+AI Vision''' feature which allows users to upload an image and have the AI answer specific questions regarding the image contents. T..."
==Overview==
This article is about the '''+AI Vision''' feature which allows users to upload an image and have the AI answer specific questions regarding the image contents. This can allow you to gain relevant information about the image without having to open and examine the image yourself. In this article, you will learn how to configure and use '''+AI Vision'''.
'''Note:''' The '''+AI Vision''' feature has an image file size limit for 20MB. Only one image may be uploaded when '''+AI Vision''' is enabled. Supported image formats include PNG, JPEG, JPG, WEBP, and GIF. You will need an OpenAI license to use AI features on SmartSimple. You must be a '''Global Administrator''' to enable this feature. Contact your account manager or SmartSimple Support for further information on billing and implementation.
==Configuration==
In order to configure '''+AI Vision''', we first need to create a custom field that will store the answers to the questions we pose to the AI.
# Create a new custom field with the '''Field Type''' set to “Text Box - Multiple Lines”. Under Caption, enter “AI Vision Text”.
# (Optional) Toggle on '''Label as AI-Generated Content.'''
# Click''' Save'''.<br /> <br /> Next, we will create an upload custom field that will make use of the '''+AI Vision''' feature:<br /><br />
# Create a new custom field with the '''Field Type''' set to “Upload - Multiple Files Storage”.
# Under the File section, toggle on''' Enable +AI Vision'''
# Enter a relevant prompt into the '''+AI Vision Prompt''' field to ask '''+AI Vision''' a question regarding the upload. For example, if you wanted '''+AI Vision''' to provide a short description of the contents of the uploaded image, enter “Describe what the image contains in 100 words or less”.
# Select the “Text Box - Multiple Lines” custom field we created in Step 1 for the '''To Custom Field''' dropdown located under the Value Storage section. This tells '''+AI Vision''' to store the answers to the '''+AI Vision Prompt i'''nto this custom field.
===Use Case: Generate Descriptions for User-Uploaded Images===
As an example, let’s use '''+AI Vision''' to help automate a typical review process that involves user-generated image submissions. Using '''+AI Vision''', reviewers can read text summaries regarding the image submission without having to download or open the image file.
To trigger '''+AI Vision''' and to test our previous configuration, follow these steps: :
# Create or edit a new record
# Upload an image to the upload field that has '''Enable +AI Vision''' toggled on. Wait for the image to complete uploading.
# Click''' Save'''.
The text box field that we created to store answers to '''+AI Vision''' prompts will be populated with an answer.
This means that when a single image is uploaded to any upload field with '''+AI Vision''' enabled, the AI will automatically generate an answer to our prompts. Here are some sample prompts to get you started:
“Does the image contain what was asked for in the submission requirements?”
“Describe the main color composition of the image”
“How well does the image make use of negative space?”
This article is about the '''+AI Vision''' feature which allows users to upload an image and have the AI answer specific questions regarding the image contents. This can allow you to gain relevant information about the image without having to open and examine the image yourself. In this article, you will learn how to configure and use '''+AI Vision'''.
'''Note:''' The '''+AI Vision''' feature has an image file size limit for 20MB. Only one image may be uploaded when '''+AI Vision''' is enabled. Supported image formats include PNG, JPEG, JPG, WEBP, and GIF. You will need an OpenAI license to use AI features on SmartSimple. You must be a '''Global Administrator''' to enable this feature. Contact your account manager or SmartSimple Support for further information on billing and implementation.
==Configuration==
In order to configure '''+AI Vision''', we first need to create a custom field that will store the answers to the questions we pose to the AI.
# Create a new custom field with the '''Field Type''' set to “Text Box - Multiple Lines”. Under Caption, enter “AI Vision Text”.
# (Optional) Toggle on '''Label as AI-Generated Content.'''
# Click''' Save'''.<br /> <br /> Next, we will create an upload custom field that will make use of the '''+AI Vision''' feature:<br /><br />
# Create a new custom field with the '''Field Type''' set to “Upload - Multiple Files Storage”.
# Under the File section, toggle on''' Enable +AI Vision'''
# Enter a relevant prompt into the '''+AI Vision Prompt''' field to ask '''+AI Vision''' a question regarding the upload. For example, if you wanted '''+AI Vision''' to provide a short description of the contents of the uploaded image, enter “Describe what the image contains in 100 words or less”.
# Select the “Text Box - Multiple Lines” custom field we created in Step 1 for the '''To Custom Field''' dropdown located under the Value Storage section. This tells '''+AI Vision''' to store the answers to the '''+AI Vision Prompt i'''nto this custom field.
===Use Case: Generate Descriptions for User-Uploaded Images===
As an example, let’s use '''+AI Vision''' to help automate a typical review process that involves user-generated image submissions. Using '''+AI Vision''', reviewers can read text summaries regarding the image submission without having to download or open the image file.
To trigger '''+AI Vision''' and to test our previous configuration, follow these steps: :
# Create or edit a new record
# Upload an image to the upload field that has '''Enable +AI Vision''' toggled on. Wait for the image to complete uploading.
# Click''' Save'''.
The text box field that we created to store answers to '''+AI Vision''' prompts will be populated with an answer.
This means that when a single image is uploaded to any upload field with '''+AI Vision''' enabled, the AI will automatically generate an answer to our prompts. Here are some sample prompts to get you started:
“Does the image contain what was asked for in the submission requirements?”
“Describe the main color composition of the image”
“How well does the image make use of negative space?”
