improve the OCR pipeline processing and outputs formatting

2026-07-19 19:54:53 +02:00
parent d375db47c3
commit 1cf1c6eeab
30 changed files with 3838 additions and 3900 deletions
--- a/src/ocr_pipeline/postprocess/init.py
+++ b/src/ocr_pipeline/postprocess/init.py
@@ -2,7 +2,7 @@ from __future__ import annotations

 from .chunk import SemanticChunker, TextChunk, chunk_text
 from .clean import CleanResult, clean_text
-from .entities import Entity, SciSpacyNER, extract_entities, summarize_entities
+from .entities import Entity, ScientificEntityRecognizer, extract_entities, summarize_entities

 __all__ = [
    "clean_text",
@@ -13,5 +13,5 @@ __all__ = [
    "extract_entities",
    "summarize_entities",
    "Entity",
-    "SciSpacyNER",
+    "ScientificEntityRecognizer",
 ]