converting to pydantic-settings

python/ebook_search/ingest.py

@@ -79,17 +79,17 @@ def ingest_configured_paths(session: Session, config: EbookSearchConfig) -> int:
         path = Path(library_path).expanduser()
         logger.info("ebook_ingest_path_start path=%s", path)
         if path.is_file() and path.suffix.lower() == ".epub":
-            count += int(ingest_file(session, path))
+            count += int(ingest_file(session, path, config))
         elif path.is_dir():
             for epub_path in sorted(path.rglob("*.epub")):
-                count += int(ingest_file(session, epub_path))
+                count += int(ingest_file(session, epub_path, config))
         else:
             logger.warning("ebook_ingest_path_missing path=%s", path)
     logger.info("ebook_ingest_paths_complete changed_files=%s configured_paths=%s", count, len(config.library_paths))
     return count
 
 
-def ingest_file(session: Session, path: Path) -> bool:
+def ingest_file(session: Session, path: Path, config: EbookSearchConfig) -> bool:
     """Ingest one EPUB file. Return True when the database changed."""
     resolved_path = path.expanduser().resolve()
     logger.info("ebook_ingest_file_start path=%s", resolved_path)
@@ -134,7 +134,7 @@ def ingest_file(session: Session, path: Path) -> bool:
         )
         session.add(chapter)
         session.flush()
-        chunk_index = add_chapter_chunks(session, source, chapter, parsed_chapter, chunk_index)
+        chunk_index = add_chapter_chunks(session, source, chapter, parsed_chapter, chunk_index, config)
 
     session.flush()
     logger.info(
@@ -160,10 +160,15 @@ def add_chapter_chunks(
     chapter: EbookChapter,
     parsed_chapter: ParsedChapter,
     chunk_index: int,
+    config: EbookSearchConfig,
 ) -> int:
     """Add chunk rows for one parsed chapter and return the next chunk index."""
     page_label = parsed_chapter.page_labels[0] if parsed_chapter.page_labels else None
-    for text_chunk in chunk_text(parsed_chapter.text):
+    for text_chunk in chunk_text(
+        parsed_chapter.text,
+        chunk_tokens=config.chunk_tokens,
+        overlap_tokens=config.chunk_overlap,
+    ):
         session.add(
             EbookChunk(
                 source_id=source.id,