Loading...
Loading...
Found 2 Skills
Ranked (BM-25) retrieval over already-extracted text (output of `pdf-to-markdown`/`pdf-to-text`). For a specific term you can name, a bounded `grep -C "term" file | head` is leaner — use that first. Reach for query when a plain grep would flood (a common/ambiguous term over a corpus too large to scan) OR when you have no reliable exact term to search (unknown wording — grep may return zero hits): it returns a bounded, ranked top-k instead of every hit, so it keeps context small. Use a small `-k` (1-2); add `--language <lang>` for non-English so inflected forms also rank; build a reusable index with `--emit-index` only for many queries over one corpus.
Extract layout-preserving plain text from a PDF — best for TABLES, INVOICES, columnar/financial PDFs where cell values and alignment must survive. Parse each PDF ONCE to a file. To find a specific fact, prefer a bounded `grep -n -i -C2 "term" file | head`. Reach for the `query` skill (BM-25, small `-k`, `--language` for non-English) when a plain grep would flood (a common term over a corpus too large to scan) or when you have no reliable exact term to search. Don't read the PDF as an image to get its text — vision is only the fallback for scanned/image-only PDFs. Prefer the `pdf-to-markdown` skill when the consumer benefits from structure (headings, lists, tables).