Coverage for src/lilbee/data/extract/__init__.py: 100%

0 statements  

« prev     ^ index     » next       coverage.py v7.15.2, created at 2026-08-14 11:46 +0000

1"""Document extraction and chunking. 

2 

3Everything that turns a raw file into embeddable text lives here: the bridge to 

4xberg's ``extract`` (:mod:`.xberg`), the ingest-facing document/markdown drivers 

5(:mod:`.document`), batching (:mod:`.batch`), tree-aware chunking (:mod:`.chunk`, 

6:mod:`.code_chunker`) and the plugin backends that route OCR, embedding and 

7tokenization through the fleet (:mod:`.backends`). Corpus orchestration (the 

8sync pipeline, discovery, workers) stays in :mod:`lilbee.data.ingest`. 

9"""