Install, add an OpenAI API token, and launch in minutes.
RAG retrieves your content and links to the exact sources.
Posts, Pages, CPTs, WooCommerce, Elementor, and Gutenberg.
RAG combines fast retrieval with controlled generation. The plugin embeds your content, fetches the most relevant passages for each query, then composes an answer that links back to your pages. Readers get clear explanations with citations. Teams get fewer repeat questions and faster discovery across docs, blogs, and product content.
Provide a few details so we can confirm fit and send setup instructions.
No. Install the plugin, paste a basic OpenAI API token, index your content, and add the shortcode or block.
Only the text needed to create embeddings and to generate answers. You choose what to index and can exclude post types, taxonomies, paths, or specific pages.
OpenAI states that API data is not used to train models by default. You control what is sent and can revoke your key at any time.
Most evaluation sites spend only a few dollars ($3-$5). Cost depends on content size and query volume. You can set soft and hard limits in your OpenAI account.
Yes. It works on staging and production. You can export settings and import them to production, then run a quick reindex.
Yes. Use the shortcode or the native block anywhere in your layout.
Yes. Products can be included in the index for AI product search and cited answers.
Posts, Pages, Custom Post Types, and WooCommerce Products. You can also filter by taxonomy, author, or path.
By default, only public content is indexed. You can opt in to restricted content. Answers to restricted items appear only for authenticated users with permission.
