wiki_ingest_ocrlisted

# LLM Wiki — Ingest Local OCR Skill (wiki_ingest_ocr) > **CLI (read first):** This skill drives the `magi` CLI (MAGI research workspace tool, assumed installed on PATH). If unsure of your surroundings, run `magi sync` first to locate the workspace. For the full syntax of any command: `magi <command> --help`. This skill handles converting external PDF documents (especially academic papers or scanned articles inside `inbox/` or custom local paths) into high-fidelity clean Markdown using the local OCR model configured in `config.yaml` (default: `glm-ocr` at 130 DPI). > **Figures are handled automatically.** Both the PDF path (`magi ingest ocr`) and the TeX path (`magi ingest tex`) extract figures into an `images/` folder beside the output Markdown and embed them inline (``). Figure files are prefixed with the document slug, so multiple papers can share one `raw/<type>/images/` folder without collisions. Vector figures and `.pdf`/`.eps` sources are rasterised to PNG. You do **not** need to handle figures manually. When the user asks to ingest PDFs using local OCR (or runs the command without a path): 1. **Resolve Ingestion Targets**: * If a specific file path is provided, process that target. * If NO target is provided, automatically scan the `inbox/` directory for any `.pdf`, `.md`, or `.tex` files. * If `inbox/` contains multiple target files, you **MUST** loop through all of them and process them one by one in a batch.