MathPix: Include PDF ID in metadata

langchain-ai · Jan 6, 2024 · ec317ab · ec317ab
1 parent d136925
commit ec317ab
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/libs/community/langchain_community/document_loaders/pdf.py b/libs/community/langchain_community/document_loaders/pdf.py
@@ -512,7 +512,7 @@ def load(self) -> List[Document]:
         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)]