enh/fix: filter content metadata
This commit is contained in:
@@ -1,10 +1,24 @@
|
||||
from datetime import datetime
|
||||
|
||||
KEYS_TO_EXCLUDE = ["content", "pages", "tables", "paragraphs", "sections", "figures"]
|
||||
|
||||
def stringify_metadata(
|
||||
|
||||
def filter_metadata(metadata: dict[str, any]) -> dict[str, any]:
|
||||
metadata = {
|
||||
key: value for key, value in metadata.items() if key not in KEYS_TO_EXCLUDE
|
||||
}
|
||||
return metadata
|
||||
|
||||
|
||||
def process_metadata(
|
||||
metadata: dict[str, any],
|
||||
) -> dict[str, any]:
|
||||
for key, value in metadata.items():
|
||||
# Remove large fields
|
||||
if key in KEYS_TO_EXCLUDE:
|
||||
del metadata[key]
|
||||
|
||||
# Convert non-serializable fields to strings
|
||||
if (
|
||||
isinstance(value, datetime)
|
||||
or isinstance(value, list)
|
||||
|
||||
Reference in New Issue
Block a user