ingest_pdfs
Convert PDF course materials to searchable markdown using local OCR engines. Supports categories like lectures, textbooks, homework, and solutions.
Instructions
Render every materials/**/*.pdf to markdown via the selected OCR engine. Idempotent unless force=True.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "ingest_pdfs"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| force | No | Reconvert even if converted/<cat>/<stem>.md exists. | |
| engine | No | OCR engine, run fully in-process. qwen3-vl (default) uses a local Ollama with qwen3-vl:8b and falls back to tesseract automatically when Ollama is unavailable. tesseract needs pytesseract with eng and/or kor traineddata. | qwen3-vl |
| 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. |