Liferay AI capabilities
How To articles are not official guidelines or officially supported documentation. They are community-contributed content and may not always reflect the latest updates to Liferay DXP. We welcome your feedback to improve How To articles!
While we make every effort to ensure this Knowledge Base is accurate, it may not always reflect the most recent updates or official guidelines.We appreciate your understanding and encourage you to reach out with any feedback or concerns.
Legacy Article
You are viewing an article from our legacy "FastTrack"
publication program, made available for informational purposes. Articles
in this program were published without a requirement for independent
editing or verification and are provided"as is" without
guarantee.
Before using any information from this article, independently verify its
suitability for your situation and project.
Issue
- We would like to gain more information about Liferay's AI capabilities.
Environment
- Liferay DXP Quarterly releases
Resolution
- Liferay DXP integrates with external AI systems to enhance and accelerate your content creation and management processes. See more: https://learn.liferay.com/w/dxp/ai
- The AI Creator feature in Liferay leverages OpenAI models to generate images and text.
- Specifically, it uses the
gpt-3.5-turbo model for text generation and dall-e-2 for image generation.
- After the feature is enabled in Liferay, each time a user initiates a text or image generation request, Liferay sends an API call to the appropriate OpenAI endpoint.
- This call includes the user’s prompt and configuration details, which are transmitted to OpenAI’s servers for processing.
- If you are using Liferay Cloud (PaaS or SaaS), the call is made from Liferay’s cloud backend infrastructure to OpenAI.
- The specific API endpoints being accessed are found in the code here.
- Once a request is sent to OpenAI, the handling of that data by OpenAI depends on how your account is configured.
- You can read more about their data retention policies here:
- Once OpenAI processes the request, the generated output (text or image) is returned to Liferay and displayed in the UI.
- At that point, it is up to the user to decide whether or not to store the generated content by saving or publishing it in Liferay.
Did this article resolve your issue ?