Document inspection

Trapo processes local PDFs and images and presents page previews alongside extracted text, bounding boxes, spans, and diagnostics. Local persistence retains document data and the history of ingestion runs.

Implementations

The Agus Works prototype used Python, FastAPI, DuckDB, and local document readers including Docling, MinerU, and Infinity Parser2. It stored file hashes, structured output, chunks, and page regions. The subsequent workbench uses a Rust server, a React interface, PDFium rendering, local persistence, and runtime and model loading. Its repository retains the name baidu-unlimited-ocr-portable.

Processing state

The workbench persists OCR stream events before broadcasting them. After a refresh, the interface reconstructs completed activity and continues receiving new events. Page-region anchors connect extracted spans to the document preview.

Development scope

The project uses existing OCR models and runtimes for ingestion and inspection. Graph extraction and graph-based retrieval remain planned extensions.

Demonstrations

Sources

  1. Trapo · Python ingestion and inspection prototype
    Agus Works · GitHubSource preview
  2. Trapo · portable Rust and React workbench
    bangonkali · GitHubSource preview
  3. Unlimited OCR · demonstration repository
    bangonkali · GitHubSource preview
  4. Hugging Face · learning activity
    Hugging Face · bangonkaliSource preview