github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-29 07:19:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

add missing source field to pymupdf output (#2110)

Browse Source 
To be consistent with other loaders for use with the `Sources` vector
workflows.
This commit is contained in:
Tim Asp
2023-03-28 13:22:05 -07:00
committed by GitHub
parent a554e94a1a
commit b25dbcb5b3
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
langchain/document_loaders/pdf.py
View File

@@ -156,6 +156,7 @@ class PyMuPDFLoader(BasePDFLoader):
page_content=page.get_text(**kwargs).encode("utf-8"), page_content=page.get_text(**kwargs).encode("utf-8"),
metadata=dict( metadata=dict(
{ {
"source": file_path,
"file_path": file_path, "file_path": file_path,
"page_number": page.number + 1, "page_number": page.number + 1,
"total_pages": len(doc), "total_pages": len(doc),