Compare commits

..

3 Commits

Author SHA1 Message Date
Lorenze Jay
e176ad29d2 cleanup 2024-12-23 10:50:17 -08:00
Lorenze Jay
f3ed4c62ac removed some redundancies 2024-12-23 10:32:09 -08:00
Lorenze Jay
b3185ad90c Feat/docling-support (#1763)
* added tool for docling support

* docling support installation

* use file_paths instead of file_path

* fix import

* organized imports

* run_type docs

* needs to be list

* fixed logic

* logged but file_path is backwards compatible

* use file_paths instead of file_path 2

* added test for multiple sources for file_paths

* fix run-types

* enabling local files to work and type cleanup

* linted

* fix test and types

* fixed run types

* fix types

* renamed to CrewDoclingSource

* linted

* added docs

* resolve conflicts

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
Co-authored-by: Brandon Hancock <brandon@brandonhancock.io>
2024-12-23 13:19:58 -05:00

View File

@@ -71,28 +71,29 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
def _process_file_paths(self) -> List[Path]:
"""Convert file_path to a list of Path objects."""
# Check if old file_path is being used
if hasattr(self, "file_path") and self.file_path is not None:
self._logger.log(
"warning",
"The 'file_path' attribute is deprecated and will be removed in a future version. Please use 'file_paths' instead.",
color="yellow",
)
paths = (
[self.file_path]
if isinstance(self.file_path, (str, Path))
else self.file_path
)
else:
if self.file_paths is None:
raise ValueError("Your source must be provided with a file_paths: []")
elif isinstance(self.file_paths, list) and len(self.file_paths) == 0:
raise ValueError("Empty file_paths are not allowed")
else:
paths = (
[self.file_paths]
if isinstance(self.file_paths, (str, Path))
else self.file_paths
)
self.file_paths = self.file_path
return [self.convert_to_path(path) for path in paths]
if self.file_paths is None:
raise ValueError("Your source must be provided with a file_paths: []")
# Convert single path to list
path_list: List[Union[Path, str]] = (
[self.file_paths]
if isinstance(self.file_paths, (str, Path))
else list(self.file_paths)
if isinstance(self.file_paths, list)
else []
)
if not path_list:
raise ValueError(
"file_path/file_paths must be a Path, str, or a list of these types"
)
return [self.convert_to_path(path) for path in path_list]