Contents
Preface
I've been thinking about how to use AI-related plugins in WordPress to achieve more functions. However, the trouble is that most AI plugins are paid, which makes it difficult for me to experience them. On the other hand, if it is a paid plugin, I guess most individual webmasters will not be very interested (including me), so even if I write a tutorial, it will not make much sense.
Fortunately, after searching for a long time, I finally found a plug-in with a free version that provides enough basic functions: AI Engine, which can provide many functions including site chatbot, text-to-image, image-to-text, generation of article titles, and article summaries. The key is that I see that this plug-in basically has no detailed Chinese tutorial, so I chose it this time!
Introduction to AI Engine
AI Engine It’s a powerful WordPress plugin designed to enhance website functionality through AI technology, specifically integrating OpenAI models such as GPT-3 and GPT-4. This plugin has a variety of useful features, especially in content creation and automation.
Key features:
- Automatically generated content:
AI Engine can help users automatically generate blog posts, article summaries, product descriptions, SEO optimized content, etc. You only need to enter keywords or topics, and the plug-in will automatically generate relevant high-quality text based on the input (how high?).
- Interact with ChatGPT:
The plug-in provides integration with multiple large language models, and can interact with AI directly in the WordPress backend to quickly obtain inspiration and writing suggestions; or communicate with users on the front end of the website and automatically reply to comments and messages according to user needs.
- AI training:
AI Engine allows users to train their own AI models to generate more personalized content based on the specific needs of the website. This is very useful for websites that require a specific tone or style.
- Multi-language support:
The plugin supports multiple languages and can automatically translate content, helping international websites create multilingual versions of pages.
- Fast page generation:
Through simple user input, AI Engine can quickly generate new pages and posts, improving the efficiency of content updates on the website (this should be used with caution, as fast updates without good content are meaningless).
Applicable scenarios:
• Blog content creation
• Automatically generate product descriptions
• AI-powered automated responses for customer interactions
• SEO content optimization
The versatility of AI Engine makes it a powerful assistant for improving the productivity and user experience of WordPress websites, especially for those sites that require frequent content creation.
AI Engine plug-in installation and settings
Installing AI Engine
Install the AI Engine plugin:
Enable the plugin:
Introduction to AI Engine settings
Settings tab
The "Settings" tab is used to configure and manage various system parameters to optimize AI performance based on specific needs and scenarios. The AI Engine settings interface can be accessed from two entrances as shown below:
Environments for AI
The options in the "Environments for AI" section are used to set key information about the language model vendors used by various functions of the entire plug-in. All model versions to be used must be set here (including chat, text-to-image, image-to-text, voice, etc.):
AI Engine supports the following large model manufacturers:
I chose Azure OpenAI because it's accessible in China without any science or magic. If I chose another large model vendor, and my WordPress server happened to be in China, I'd need to use science or magic to ensure that WordPress could access the API address provided by the other large model vendor.
The "Deployment Name" and "Model Version" involved in the "Deployments" section need to correspond to the configuration in the large language model provider. Taking this article as an example, the following "Deployments" is my final configuration:
For the "API Key" and "Endpoint" fields in the image above, refer to the Azure OpenAI "Keys and Endpoints" section:
The "Deployments name" and model version must be consistent with the "Deployment name" and "Model name" in the "Deployment" section of Azure OpenAI:
The reason for requiring consistency is that when AI Engine initiates a request to Azure OpenAI's API, it will use these contents to construct the request URL.
Default Environments for AI
The options in the "Default Environments for AI" section are used to configure the default environment and behavior of the AI runtime, ensuring that the AI can achieve the expected performance in different usage scenarios. The default AI environment parameters are set as shown below:
As its name suggests, GPT-4o-mini is a smaller version of the GPT-4 model that is optimized for specific tasks such as conversational AI. Typically, model designs like GPT-4o-mini prioritize chat-based interactions over advanced multimedia features such as text-to-image (DALL-E) or image-to-text (CLIP) generation.
These high-level features, such as generating images from text or processing images into descriptions, are usually handled by other specialized models (e.g., DALL-E for image generation, CLIP for image understanding, whisper for speech to text, tts-1 for speech synthesis, etc.). Therefore, GPT-4o-mini focuses primarily on language understanding and generation, making it suitable for tasks such as chatting, writing, and answering questions, but not for multimedia generation.
Therefore, Images, Embeddings, and Audio cannot use GPT-4o-mini, which is GPT-4. If you want to set the default AI for these functions, you need to first add dedicated models such as DALL-E-3(h) and CLIP in the previous "Deployments" section.
General and Chatbot
The "General" section configures global system settings, such as language, performance, and error handling, to ensure stable AI operation. The "Chatbot" section focuses on chatbot interaction behavior, covering conversation style, welcome messages, context management, and more, to enhance user experience personalization and conversation coherence. The functions of the General and Chatbot options are shown in the figure below:
Admin Tools
Admin Tools is used to specify whether to fix these four function entrances to the top bar of the background:
Discussions Tag
The "Discussions" tab is typically used to manage and view user interactions within the system. Its functions include:
- Dialogue Management: This tab helps you view historical conversations with users for quick review and reference. For complex issues or multiple conversation topics, the "Discussions" tab allows you to systematically track each user's needs and questions.
- Contextual AssociationBy reviewing previous discussions, AI can provide more precise responses in subsequent conversations, ensuring continuity and accuracy. A user's needs may become increasingly clear over multiple interactions, so the "Discussions" tab provides a better understanding of the overall context.
- Quality ImprovementUsing the "Discussions" tag can help AI train models and improve response capabilities by reviewing and analyzing previous conversations. This also helps identify common user needs or questions, allowing for further system optimization.
At the same time, the "Discussions" label is also in the "Settings"-"Chatbot" section, after the "Discussions" option "Enable" appears:
Chatbots Tags
The options under the "Chatbots" tab allow users to configure the chatbot's model, initial prompts, AI replies, context management, user input processing, error handling, custom commands, file uploads, and appearance settings. These features allow users to flexibly customize the chatbot's behavior and interface.
Mode
AI Model
This option depends on the "Mode" selection in the previous section. If you chose Chat, then select "GPT-4o Mini" here; if you chose Images, then you should select "DALL-E-3(H)" here:
Thresholds
This section can be used to limit what the user can enter at one time:
Appearance
Settings and robot chat interface appearance, content, character avatar, etc.:
When the avatar option is not selected:
When you select Avatar:
Note:Gravatar It is a global avatar service, the full name is Globally Recognized Avatar. It allows users to associate an avatar with their email address. When a user uses the same email address on a website that supports Gravatar (such as WordPress, forums, etc.), Gravatar will automatically display the avatar associated with that address. Users only need to upload their avatar once on the Gravatar platform, and then their avatar will be automatically displayed on all websites that support Gravatar. This service simplifies the process of users setting up personal avatars on multiple websites and provides a unified way to identify online. The Gravatar URL is as follows:https://gravatar.com/Friends who need it can go and register.
Other options
- Functions: You can extend the capabilities of your AI model by installing a “Snippet Vault” that will use these functions to enhance responses and perform specific actions. These functions are called function calls or tools.
- Shortcodes: You can implement chatbot functions in specific locations in the form of shortcodes.
- Actions: You can copy or reset the configuration of the chatbot.
- Themes: The appearance of the chat section can also be changed manually:
- Site-Wide Chatbot: By default, the chatbot is only available in the WordPress backend. You can change the value of the Site-Wide Chatbot option (upper right corner) from "none" to "default". Then the chatbot avatar will appear in the lower right corner:
Click to display the chat dialog box:
However, global activation means that anyone can use your chatbot, which costs money, so be careful. It is generally used by companies to communicate with potential customers, and personal webmasters can use it as they please.
Dashboard
Client Modules and Server Modules. For Server Modules, select according to your actual needs. Don’t check all of them, as this will increase WP’s resource consumption.
Admin Modules:
Usage:
Use of AI tools
As mentioned earlier in this article, in AI Eening, you can display the three AI tools "Content", "Images", and "Playground" in two locations on the WordPress dashboard through the "Admin Tools" and "Admin Modules" options:
Content
The "Content" feature helps users generate, edit, and optimize text content. You can use it to create articles, blog posts, marketing copy, or any other type of text output. It can generate targeted, high-quality content based on user-provided topics, keywords, or style requirements. It can also improve existing text, such as polishing, correcting errors, simplifying, or expanding it. This feature is suitable for rapid conception, content optimization, and improving writing efficiency. The tool interface is shown below:
The effect is as follows:
Of course, this kind of automatically generated content is basically unreadable, so we can further refine the content by manually filling in the title and chapter name:
The more and more detailed the prompts are, and the more accurate titles, chapter names, and excerpts are manually specified, while only the main text is automatically generated, the more the content will suit your needs.
Images
The "Images" feature can generate custom images based on user descriptions. You can enter a detailed text description (calledprompt), AI generates images based on this description. Users can specify image dimensions, such as square or rectangular, and can choose to generate one or more images. The "Images" feature is suitable for creating visual content, such as design concepts, artwork, or illustrating specific scenes. This feature allows for flexible adjustment of details to ensure the output meets user expectations.
In order to use the image generation function, you need to add the DALL-E series model that supports the image generation function in "Settings". Here I take 3 as an example:
After that, you can generate images in the Images tool. The tool operation interface is introduced as shown below:
Playground
The "Playground" tool is a feature-rich interactive platform that allows users to select and test various AI models, adjust parameters, conduct prompt engineering experiments, and view results in real time. It supports multi-turn dialogue, code generation, multi-language processing, and provides API integration examples. This tool is not only suitable for developers and researchers to explore and optimize technology, but also provides an intuitive environment for content creators and educators to learn and demonstrate AI technology. The tool usage is shown in the figure below:
Note: In fact, the so-called templates are just some detailed prompts, so you can also refer to the 4 default templates, write some prompts you often use in advance, and save them as templates for future reuse. The following is a demonstration of actual use:
The effect is OK:
Other integrated features
The integration here mainly refers to the functions integrated into the backend article interface, including naming articles and generating article excerpts. Use the mouse to point to any article, and two functions with "magic wands" at the end of the menu items will appear: "Title" is for naming the article, and "Excerpt" is for generating content excerpts for the article:
Click "Title" to generate recommended article names:
Click "Excerpt" to generate multiple article summaries for you to choose from:
In addition to these two functions, the Images tool will also be integrated soon:
Note: Generating article summaries requires sending the article content to the AI, which then generates a summary based on the content. This consumes a significant amount of tokens, making it a bit of a waste for long articles. This feature is something you should consider carefully. Well, OpenAI 3.5 is free. If you have access to OpenAI, you can try this method (using a worker to build an API proxy yourself). I won't bother with that. Azure OpenAI, while accessible without a science license and with no monthly subscription or pay-per-use, doesn't offer any free credits. You can't have your cake and eat it too.
Summarize
I think the biggest advantage of AI Engine is that the free version provides enough functions and is quite practical. Compared with other plug-ins that often cost $7 or $8 per month, it is already very conscientious.
However, aside from the chatbot, all of AI Engine's other features are merely optional. Whether they're useful and how to use them is a matter of personal preference. For example, if I want to generate text, images, or article summaries, why should I do it in the WordPress backend? Can't I just generate them locally using chatgpt or another model and then upload them to WordPress? Generating them in WordPress would also take up the server's performance.
Therefore, everyone can choose the one that suits them according to their actual needs.
In addition: Although I have tried to introduce these options in detail, there are still some mistakes and omissions. It seems that there are a few that I have not mentioned. Forget it, I am too lazy to add them, and they don’t seem to be important options.