github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-22 14:49:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

community: Include PDF ID in MathPix metadata (#15629)

Browse Source 
- **Description:** Includes the PDF ID in the MathPix document metadata.
This is useful in case you need to re-request a processed PDF from the
MathPix API later.
This commit is contained in:
Chad Norvell 2024-01-07 08:31:53 -08:00 committed by GitHub
parent d2a686b165
commit f6226d464e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
libs/community/langchain_community/document_loaders/pdf.py
View File

@ -518,7 +518,7 @@ class MathpixPDFLoader(BasePDFLoader):
contents = self.get_processed_pdf(pdf_id)
if self.should_clean_pdf:
contents = self.clean_pdf(contents)
metadata = {"source": self.source, "file_path": self.source}
metadata = {"source": self.source, "file_path": self.source, "pdf_id": pdf_id}
return [Document(page_content=contents, metadata=metadata)]