How to Connect
- Select Wikipedia as the Source type
- Name the Source: Give your Wikipedia Source a name
- Provide an article URL or title: Enter the full Wikipedia URL (e.g.,
https://en.wikipedia.org/wiki/Example) or the article title - (Optional) Add a Prompt: Provide additional instructions to guide extraction (e.g., focus on the history section, ignore references, prioritize structured data)
- Click Save
Content Processing
Galaxy processes Wikipedia content with:- Text extraction: Extracts article body text, preserving section structure and headings
- Content normalization: Normalizes content for consistency across sources
- Entity extraction: Automatically extracts and normalizes semantic entities including:
- Dates and times (normalized to standard formats)
- Email addresses and URLs
- Measurements, money, and percentages
- Serial numbers and version numbers
- Technical measurements (temperature, pressure, voltage, current, frequency)
Don’t see a source type you’re looking for? We connect to hundreds of systems - reach out to support@getgalaxy.io to request access.