Spaces:
Sleeping
Sleeping
Update split_files_to_excel.py
Browse files- split_files_to_excel.py +7 -6
split_files_to_excel.py
CHANGED
@@ -481,16 +481,17 @@ def split_in_df(files):
|
|
481 |
documents = split_doc_in_chunks(files)
|
482 |
df = pd.DataFrame()
|
483 |
for document in documents:
|
|
|
484 |
content = document.page_content
|
485 |
|
486 |
-
metadata = document.metadata
|
487 |
-
metadata_keys = list(metadata.keys())
|
488 |
-
metadata_values = list(metadata.values())
|
489 |
|
490 |
-
doc_data = {'Content': content}
|
491 |
|
492 |
-
for key, value in zip(metadata_keys, metadata_values):
|
493 |
-
|
494 |
|
495 |
df = pd.concat([df, pd.DataFrame([doc_data])], ignore_index=True)
|
496 |
|
|
|
481 |
documents = split_doc_in_chunks(files)
|
482 |
df = pd.DataFrame()
|
483 |
for document in documents:
|
484 |
+
filename = document.metadata['filename']
|
485 |
content = document.page_content
|
486 |
|
487 |
+
# metadata = document.metadata
|
488 |
+
# metadata_keys = list(metadata.keys())
|
489 |
+
# metadata_values = list(metadata.values())
|
490 |
|
491 |
+
doc_data = {'Filename': filename, 'Content': content}
|
492 |
|
493 |
+
# for key, value in zip(metadata_keys, metadata_values):
|
494 |
+
# doc_data[key] = value
|
495 |
|
496 |
df = pd.concat([df, pd.DataFrame([doc_data])], ignore_index=True)
|
497 |
|