Wikipedia Block

The Wikipedia block lets workflows tap into the world's largest encyclopedia. Search for pages, fetch concise summaries, retrieve full article content, or pull a random article — useful whenever you need factual, reference-grade context for downstream reasoning or output.

Overview

When to Use

• Fetch a quick summary of a topic to feed an Agent block as grounding context
• Search Wikipedia for candidate pages matching a query before retrieving one
• Retrieve the full content of a specific article for detailed analysis or extraction
• Surface a random article for discovery, quizzes, or content-generation prompts
• Enrich a workflow with authoritative reference data without managing an API key

Configuration

Operation

Dropdown selecting what the block does. Options: Get Page Summary (wikipedia_summary), Search Pages (wikipedia_search), Get Page Content (wikipedia_content), and Random Page (wikipedia_random). Defaults to Get Page Summary.

Page Title

Required for the Get Page Summary and Get Page Content operations. The exact title of the Wikipedia article (e.g., "Python programming language").

Search Query

Required for the Search Pages operation. The search terms used to find matching articles.

Max Results

Optional for the Search Pages operation. Caps how many search results are returned (e.g., 10).

Inputs & Outputs

• Inputs:

  • operation (string) — Operation to perform (wikipedia_summary, wikipedia_search, wikipedia_content, or wikipedia_random)
  • pageTitle (string) — Wikipedia page title; required for Get Page Summary and Get Page Content
  • query (string) — Search query terms; required for Search Pages
  • searchLimit (number) — Maximum number of search results to return; optional, defaults to 10, max 50

• Outputs:

  • summary (json) — Page summary data: title, extract, description, thumbnail, content_urls, pageid (returned by Get Page Summary)
  • searchResults (json) — Array of matching Wikipedia pages, each with title, excerpt, and URL (returned by Search Pages)
  • totalHits (number) — Total number of search results found (returned by Search Pages)
  • content (json) — Full HTML content and metadata of the page: html, revision, timestamp (returned by Get Page Content)
  • randomPage (json) — Random page data: title, extract, description, thumbnail, content_urls, pageid (returned by Random Page)

Tools

• Wikipedia Page Summary (wikipedia_summary) — Fetches a concise summary and metadata for a named Wikipedia article via the REST API (/page/summary/{title}). Params: pageTitle (required).
• Wikipedia Search (wikipedia_search) — Searches Wikipedia by keyword using the OpenSearch API and returns a ranked list of matching pages. Params: query (required), searchLimit (optional, default 10, max 50).
• Wikipedia Page Content (wikipedia_content) — Retrieves the full HTML content of a specific Wikipedia article via the REST API (/page/html/{title}). Params: pageTitle (required).
• Wikipedia Random Page (wikipedia_random) — Returns a randomly selected Wikipedia article summary via the REST API (/page/random/summary). No params required.

YAML Example

wikipedia_lookup:
  type: wikipedia
  name: "Wikipedia"
  inputs:
    operation: "wikipedia_summary"
    pageTitle: "{{start.input}}"
  connections:
    outgoing:
      - target: next-block-id