ingest_pdfs
Convert PDF documents in the materials folder to markdown using an OCR engine. Supports forced re-conversion and category filtering.
Instructions
Render every materials/**/*.pdf to markdown via the selected OCR engine. Idempotent unless force=True.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| engine | No | OCR engine. codex-native (default) renders PDFs to PNGs under .paideia-cache/ and returns a manifest so the calling skill can read pages with Codex CLI's bundled vision (no extra API billing for ChatGPT subscribers). qwen3-vl needs a local Ollama with qwen3-vl:8b. tesseract needs pytesseract with eng and/or kor traineddata. | codex-native |
| force | No | Reconvert even if converted/<cat>/<stem>.md exists. | |
| categories | No | Restrict to a subset of the materials subfolders. | |
| project_root | No | Absolute path to the course project root. Defaults to the server's CWD when omitted; set this explicitly if the user has cd'd between courses within the same Codex session. |