Results for “book-cover”

Restores and normalizes footnotes/endnotes in books by extracting from PDF/EPUB, matching anchors, staging markers, and compiling to HTML with assertions.

Upserts a validated MDX book corpus into Supabase via Drizzle, hydrating books, chapters, sections, and chunks tables while preserving stable bookmark anchors and only re-embedding changed content.

Chunks a book into canonical retrieval units with heading-aware structure splitting, recursive token targets, and contextual prefixes for downstream RAG ingestion.