Vragen.ai

Vragen.ai keeps your WordPress content in sync with a vragen.ai knowledge base. Whenever a post is published, updated, trashed or deleted, the plugin queues a background job (via Action Scheduler) that creates, updates or removes the matching document in vragen.ai.

Features:

• Automatic sync on publish/update/trash/delete for the post types you choose.
• Background processing through Action Scheduler, large sites stay responsive.
• Bulk synchronisation of all published content from the settings screen.
• WP-CLI command (wp vragenai sync) for scripted/initial imports.
• PDF attachments (directly attached media and ACF file fields) are passed to vragen.ai for server-side text extraction.
• Multilingual support for WPML and Polylang: all translations of a post are merged into a single document, tagged with every language it is available in.
• Embed a vragen.ai deployment (page, popup or popover) with the Vragen.ai block, or load one site-wide from the settings screen.
• Replace the native WordPress search with semantic search from vragen.ai (optional), with automatic fallback to the built-in search if the API is unavailable.
• Show related content for the current post with the Vragen.ai related-content block or the [vragenai_related] shortcode.
• Filters (vragenai_should_index_post, vragenai_document_attributes, vragenai_native_search_options) to customise indexing and search.

The admin UI is available in English and Dutch, following your site language.

External services

This plugin connects to the vragen.ai knowledge base API. This connection is the sole purpose of the plugin: it is required to index your content so it can be searched and answered through vragen.ai. The service is operated by SWIS (https://swis.nl) on behalf of Vragen.ai (https://vragen.ai).

The API is reached at the endpoint configured for your account, https://{customer}.vragen.ai/api/v1 by default (the root domain can be changed with the VRAGENAI_API_DOMAIN constant).

When you publish, update, trash or delete content of an enabled post type and when you run a bulk synchronisation the plugin sends the following to that endpoint:

• the post title, public URL and rendered content;
• metadata: author display name, post type, post format, language(s), publish/modified dates, taxonomy terms and the featured-image URL;
• the URLs and MIME types of attached PDF files, so vragen.ai can fetch and extract their text server-side (the file contents themselves are not uploaded by the plugin);
• your configured customer name and API token (sent as a Bearer authorization header).

In addition, while the settings screen is open the plugin contacts the API at most once per hour to verify the connection.

No data is sent until you enter a customer name and API token. The plugin makes no other external requests.

• Service homepage: https://vragen.ai/
• Privacy Policy: https://vragen.ai/privacy-statement