github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-10 15:06:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update pdf.py comment for PyPDFLoader (#10495)

Browse Source 
PyPDF does not chunk at the character level to my understanding.

Description: PyPDF does not chunk at the character level, but instead
breaks up content by page. Fixup comment

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
This commit is contained in:
Kyle Pancamo 2023-10-05 13:22:40 -05:00 committed by GitHub
parent 4236ae3851
commit 203258b4d6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
libs/langchain/langchain/document_loaders/parsers/pdf.py
View File

@ -13,7 +13,7 @@ if TYPE_CHECKING:
class PyPDFParser(BaseBlobParser): class PyPDFParser(BaseBlobParser):
"""Load `PDF` using `pypdf` and chunk at character level.""" """Load `PDF` using `pypdf`"""
def __init__(self, password: Optional[Union[str, bytes]] = None): def __init__(self, password: Optional[Union[str, bytes]] = None):
self.password = password self.password = password

4
libs/langchain/langchain/document_loaders/pdf.py
View File

@ -135,9 +135,9 @@ class OnlinePDFLoader(BasePDFLoader):
class PyPDFLoader(BasePDFLoader): class PyPDFLoader(BasePDFLoader):
"""Load `PDF using `pypdf` and chunks at character level. """Load PDF using pypdf into list of documents.
Loader also stores page numbers in metadata. Loader chunks by page and stores page numbers in metadata.
""" """
def __init__( def __init__(