Source Indexing

To automatically catalog Notion and Google Drive documents, you can run an indexing process that crawls pages and files to extract metadata and classify content. This builds a structured database for efficient retrieval.

Tracking document freshness across a knowledge base involves scanning edit dates and categorizing sources as Fresh, Current, Aging, or Stale. This metadata classification helps prioritize the most relevant and up-to-date information.

Content classification during knowledge management indexing works by analyzing document context to assign one of nine taxonomy types, such as wiki, meeting-notes, or project-docs. This structured classification ensures sources are organized for efficient retrieval.

Yes, you can write indexed metadata from Google Drive directly into a Notion database. The indexing process extracts titles, URLs, and content types, writing the structured catalog results into Notion for centralized access.

To scan for new documents without re-indexing everything, you can perform a refresh operation that checks for new content and updates existing metadata. This ensures your catalog stays current without full re-scanning overhead.

When cataloging knowledge sources, the metadata extracted includes titles, URLs, content types, keywords, edit dates, and freshness ratings. This structured data is written to a database to enable efficient retrieval by other skills.