chore: annotate kwargs across BaseChunker class hierarchy (#116)

* chore: add missing type hint for HybridChunker.chunk

Signed-off-by: Eugene <[email protected]>

* chore: apply typing to whole hierarchy

Signed-off-by: Panos Vagenas <[email protected]>

---------

Signed-off-by: Eugene <[email protected]>
Signed-off-by: Panos Vagenas <[email protected]>
Co-authored-by: Panos Vagenas <[email protected]>

Author: Fogapod

docling_core/transforms/chunker/base.py

@@ -51,7 +51,7 @@ class BaseChunker(BaseModel, ABC):
     delim: str = DFLT_DELIM
 
     @abstractmethod
-    def chunk(self, dl_doc: DLDocument, **kwargs) -> Iterator[BaseChunk]:
+    def chunk(self, dl_doc: DLDocument, **kwargs: Any) -> Iterator[BaseChunk]:
         """Chunk the provided document.
 
         Args:

docling_core/transforms/chunker/hybrid_chunker.py

@@ -6,7 +6,7 @@
 """Hybrid chunker implementation leveraging both doc structure & token awareness."""
 
 import warnings
-from typing import Iterable, Iterator, Optional, Union
+from typing import Any, Iterable, Iterator, Optional, Union
 
 from pydantic import BaseModel, ConfigDict, PositiveInt, TypeAdapter, model_validator
 from typing_extensions import Self
@@ -231,7 +231,7 @@ def _merge_chunks_with_matching_metadata(self, chunks: list[DocChunk]):
 
         return output_chunks
 
-    def chunk(self, dl_doc: DoclingDocument, **kwargs) -> Iterator[BaseChunk]:
+    def chunk(self, dl_doc: DoclingDocument, **kwargs: Any) -> Iterator[BaseChunk]:
         r"""Chunk the provided document.
 
         Args:

pyproject.toml

@@ -136,6 +136,7 @@ module = [
     "jsonref.*",
     "jsonschema.*",
     "requests.*",
+    "semchunk.*",
     "tabulate.*",
     "transformers.*",
     "yaml.*",