AI Chatbot Logo Limb AI Chatbot
for WordPress
Sign In

Knowledge Base

Use Chatbot → Knowledge Base to teach the assistant from your real content: WordPress posts and pages, single URLs, uploads, sitemap-discovered pages, curated Q&A, or manual notes. Each addition is a source you configure; then you run Learn so the model can use it in replies. You can enable Playground next to the Knowledge Base heading to chat in the admin and verify answers without loading the front end.

Settings

Under Knowledge Base → Settings you configure embedding models, vector storage, and search behavior—do this before ingesting sources if the UI requires it (for example, when the chat provider is not OpenAI or Gemini).

Embedding models

Choose one of the two providers that support embeddings for your content: OpenAI or Google Gemini. After you choose a provider, the API key and model fields appear.

This works like Chatbot → AI Settings, but AI Settings lists more providers overall. Embeddings turn text and other content into vectors (numeric representations) so the system can run similarity search. Only OpenAI and Gemini are supported for embeddings in the knowledge base.

If AI Settings already uses OpenAI or Gemini as the chat provider, you are not asked for a separate embedding provider here. If you use any other provider for chat, you must finish embedding model setup (provider, key, and model) under Knowledge Base before you can add and ingest knowledge.

Vector storage

Supported options: Local (default), Pinecone, and OpenAI. OpenAI vector storage fits best when OpenAI is already your chat provider in AI Settings.

  • Local (default): Vectors are stored in the WordPress database. No extra setup. Best for smaller knowledge bases—typically up to about 10,000 items.
  • Pinecone: Hosted vector database, common at larger scale. Add your Pinecone API key in the Pinecone section.
  • OpenAI: Optional hosted vector storage from OpenAI; pairs cleanly when your chat provider in AI Settings is OpenAI.

When to scale up: Local storage is a strong default under roughly 10,000 knowledge items. Beyond that, Pinecone is usually the better fit.

Search settings

  • Similarity threshold: Minimum similarity score (0–100%) for a retrieved snippet to count as a match.
  • Minimum similar results: Minimum number of similar knowledge items to retrieve for the model when building a reply.
  • Show knowledge sources: When enabled, lists the sources referenced under each assistant message.

Adding knowledge

  • Click Add Knowledge.
  • Choose a source type (see the source-type sections below).
  • Set options and visibility for that source.
  • Click Learn and wait for ingestion to finish.
  • Turn on Playground beside the Knowledge Base heading and ask questions that should use the new knowledge (see Learning and verification below).

You can add many sources over time; repeat the same flow for each new one.

Knowledge source types

When you add knowledge, choose one source type. Each type has its own section below: WordPress content sources, Advanced Custom Fields (ACF) Support, JetEngine Support, WordPress Media Library Support, URL knowledge sources, Sitemap knowledge sources, Q&A knowledge sources, and Manual knowledge sources.

WordPress content sources

Add a WordPress source when you want the assistant to learn from content already on your site. First choose a post type (posts, pages, or a custom post type), then choose which posts or items to include—either by selecting them manually or by applying filters such as taxonomies, date range, or author.

After the post type and items are set, the Content Collection section appears. There you choose what data to collect from each included item: core post fields (title, content, excerpt, and so on), taxonomies, and—on PRO—native post meta, ACF, and JetEngine fields. Run Learn when the source is configured.

Custom Meta

On PRO, the Custom Meta group in Content Collection lets you include native WordPress post meta for the posts, pages, or custom post type entries you already selected. Choose the post type and items first, then open Custom Meta and select which meta keys to collect for those objects.

Advanced Custom Fields (ACF) Support

PRO lets you include Advanced Custom Fields (ACF) data when you build a WordPress knowledge source. ACF field values are tied to the post type you choose and the posts, pages, or custom post type entries you include in that source—not to a separate knowledge source type.

Requirements: PRO and the Advanced Custom Fields plugin active on your site.

How to add ACF fields to the knowledge base

In Chatbot → Knowledge Base, add a WordPress source. Select the post type, then choose which posts or items to index (manually or with filters). When that scope is set, the Content Collection section appears.

In Content Collection, open the ACF fields group and select which ACF fields to collect for the included content. The list reflects fields available for the post type you selected. Configure core post fields and taxonomies in the same section if needed, then run Learn.

If you change the post type, included items, or ACF field selection, update the source and run Learn again so the knowledge base stays in sync.

JetEngine Support

PRO supports JetEngine custom fields for content you index with a WordPress knowledge source. JetEngine fields are connected to the post type you select and the posts or items included in that source.

Requirements: PRO and JetEngine installed and active on your site.

How to add JetEngine fields to the knowledge base

In Chatbot → Knowledge Base, add a WordPress source. Choose the post type and which posts or items to include. After that, use Content Collection to define what is collected from each entry.

In Content Collection, open the JetEngine fields group and select which JetEngine custom fields to index for those objects. Available fields match the post type and scope you configured. Run Learn when setup is complete.

JetEngine support is part of the WordPress source workflow on PRO; you do not add a separate JetEngine-only knowledge source type.

WordPress Media Library Support

You can import knowledge from documents stored in the WordPress Media Library without adding them as posts or pages. In Chatbot → Knowledge Base, choose the File source under Supported sources, then pick files from the media library and run Learn.

Supported file types: PDF, TXT, DOC, and DOCX.

How to add Media Library files to the knowledge base

When adding knowledge, open Supported sources and select the File source type (WordPress Media Library). Click Select from Media Library, choose one or more supported documents, confirm your selection, then run Learn. The assistant indexes the text extracted from those files.

Upload new documents to Media → Library in WordPress first if they are not already in the library. After you add or replace files, update the knowledge source and run Learn again so answers stay current.

URL knowledge sources

  • Paste a single public page URL. The source is fetched and learned from that address.

Sitemap knowledge sources

  • Paste your XML sitemap URL.
  • Click Fetch URLs, then choose which discovered links to learn.

Q&A knowledge sources

  • Create question-and-answer pairs you want the assistant to follow.
  • One answer can be tied to several similar phrasings of the same question.

Manual knowledge sources

  • Use the rich text editor to paste or write content with or without formatting.

Visibility (roles)

Every source has a visibility control: limit which user roles receive that knowledge in chat. That gives you role-based access to different parts of what the model knows.

Learning and verification

When a source is configured, click Learn. An interactive progress view shows ingestion status.

Where to test: On the same Knowledge Base screen, switch on Playground next to the page heading. The playground opens there so you can prompt the assistant and confirm it uses what you just learned.