{"id":9807,"date":"2026-06-04T12:55:15","date_gmt":"2026-06-04T12:55:15","guid":{"rendered":"https:\/\/demo.themeinprogress.eu\/tip-next-post-pro\/?page_id=9807"},"modified":"2026-08-24T11:59:20","modified_gmt":"2026-08-24T11:59:20","slug":"how-to-configure-and-use-the-ai-engine","status":"publish","type":"page","link":"https:\/\/demo.themeinprogress.eu\/tip-next-post-pro\/documentation-pro-version\/how-to-configure-and-use-the-ai-engine\/","title":{"rendered":"How to configure and use the AI Engine"},"content":{"rendered":"
Important:<\/b> This feature is not included with the Personal plan<\/b><\/div>\n
Note:<\/b> Some screenshots may show a different plugin name, but the interface and settings are also valid for TIP Next Post Pro<\/strong><\/div>\n

How does it work?<\/h3>\n

This option, available only for WordPress posts, uses embeddings to analyze your site content and automatically select the most relevant posts for the previous\/secondary and next\/primary navigation positions.<\/p>\n

Unlike other available search\/navigation methods, which rely on traditional approaches such as categories, tags, titles, or keywords to identify suitable content, this system is able to understand the overall meaning of texts and identify truly relevant connections between articles.<\/p>\n

The system identifies relevant posts by comparing embeddings using a cosine similarity algorithm, which measures how close two pieces of content are from a semantic perspective.<\/p>\n

The most relevant result is used as the next\/primary post<\/strong>, while the second most relevant result is used as the previous\/secondary post<\/strong>.<\/p>\n

This feature will not be available while the activation plugin<\/a> is installed on your website.<\/p>\n

If you are using the activation plugin, please complete the license activation process and remove it once the license has been correctly activated.<\/p>\n

What are embeddings?<\/h3>\n

Embeddings are numerical representations of textual content. In practice, each article is transformed into a vector, that is, a sequence of numbers that describes its meaning.<\/p>\n

This allows the system to compare content at a semantic level: texts that are similar in meaning will have similar numerical representations, even if they use different words.<\/p>\n

Why use embeddings?<\/h3>\n

Using embeddings allows you to overcome the limitations of methods based solely on keywords, categories, tags, or article titles.<\/p>\n

In particular, it prevents articles in the same category from always leading visitors to the same content, improving the variety and quality of navigation suggestions.<\/p>\n

By analyzing the content of each post, suggestions become more accurate because they take into account context and meaning, allowing the plugin to recommend truly related content even when articles do not share identical terms or belong to the same categories.<\/p>\n

This approach improves the quality of post navigation and remains effective even on sites with a large number of contents.<\/p>\n

How to get started<\/h3>\n

To begin, you need to select a provider or source for the embeddings used by the AI Engine.<\/p>\n

You can use OpenAI APIs, which require an API key and active credits, choose a local model using Ollama, which requires a more advanced setup and configuration, or reuse compatible embeddings already generated by another supported ThemeinProgress plugin.<\/p>\n

\"\"<\/a>
Select the AI provider from the available options<\/figcaption><\/figure>\n

Note:<\/strong> If you are already using Internal Linking of Related Contents Pro<\/strong> or TIP Related Posts Pro<\/strong>, you can select one of these plugins as the embeddings provider to reuse existing embeddings instead of generating them again.<\/p>\n

This allows both plugins to share the same embeddings database and avoids duplicate processing and storage.<\/p>\n

\"\"<\/a>
Use embeddings generated by another compatible TIP plugin<\/figcaption><\/figure>\n

Regarding OpenAI, you can generate a new API key by following these steps:<\/p>\n

    \n
  1. Go to the OpenAI website<\/a> and log into your account<\/li>\n
  2. Click the “Create API key” button<\/li>\n
  3. Enter an optional name for the key<\/li>\n
  4. Click “Create” to confirm and copy the API key<\/li>\n<\/ol>\n

    It is important to store the API key securely, as it will not be possible to view it again later.<\/p>\n

    Once you have the API key, you will need to purchase credits to use it within your site.<\/p>\n

    Credits can be purchased using the payment methods supported by the platform.<\/p>\n

    In most cases, a valid payment card is required; the availability of prepaid cards or other methods may vary depending on the country and account configuration.<\/p>\n

    If you do not have access to a traditional card, you can consider alternatives such as Revolut, which allows you to generate virtual cards usable for this type of purchase.<\/p>\n

    This is a commonly adopted solution, but it is always recommended to verify compatibility with your account.<\/p>\n

    OpenAI supports long content through automatic chunking, but extremely long articles may require many API calls and can fail due to server timeout, rate limits, or runtime constraints. Articles above tens of thousands of words should be considered edge cases.<\/em><\/p>\n

    Embeddings generation<\/h3>\n

    Once the provider has been selected, you can choose a compatible embeddings model directly from the plugin settings.<\/p>\n

    \"\"<\/a>
    Select an OpenAI embeddings model<\/figcaption><\/figure>\n

    OpenAI provides different embeddings models depending on the balance you want between cost, performance, and storage usage.<\/p>\n