Skip to content
Series
1 posts

Groundlane 實戰系列

Notes on designing and using Groundlane, a self-hosted research and scraping tool — a companion case study to the search-and-scraping series.

Groundlane Series Part 6: The Document Toolkit — effort Dial, Field-Aware Chunking, and Confidence Routing

document_parse gains an effort parameter (fast/standard/deep) unifying anydoc WASM, OCR.space, and Docling VLM into a single dial; document_chunk's fieldAware mode extracts field names from table headers and metadata to solve RAG attribute conflation; document_smart_parse now returns a confidence score so agents decide whether to upgrade.