Update app.py
Browse files
app.py
CHANGED
|
@@ -15,17 +15,16 @@ import os
|
|
| 15 |
hub_token = os.environ["HUGGINGFACE_HUB_TOKEN"]
|
| 16 |
|
| 17 |
def split_pdfs(pdf_docs):
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
pdf_docs: A list of PDF documents.
|
| 22 |
-
|
| 23 |
-
|
| 24 |
A list of lists of PDF documents, where each sublist contains a smaller chunk of the original PDF documents.
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
for pdf_doc in pdf_docs:
|
| 29 |
# Split the PDF document into pages.
|
| 30 |
pdf_reader = PdfReader(pdf_doc)
|
| 31 |
pdf_pages = pdf_reader.pages
|
|
|
|
| 15 |
hub_token = os.environ["HUGGINGFACE_HUB_TOKEN"]
|
| 16 |
|
| 17 |
def split_pdfs(pdf_docs):
|
| 18 |
+
"""Splits a list of PDF documents into smaller chunks.
|
| 19 |
+
|
| 20 |
+
Args:
|
| 21 |
pdf_docs: A list of PDF documents.
|
| 22 |
+
|
| 23 |
+
Returns:
|
| 24 |
A list of lists of PDF documents, where each sublist contains a smaller chunk of the original PDF documents.
|
| 25 |
+
"""
|
| 26 |
+
|
| 27 |
+
pdf_chunks = []
|
|
|
|
| 28 |
# Split the PDF document into pages.
|
| 29 |
pdf_reader = PdfReader(pdf_doc)
|
| 30 |
pdf_pages = pdf_reader.pages
|