From 97fd65bc0861fc4fe1b01c1bf0d57826659dfad9 Mon Sep 17 00:00:00 2001 From: Philippe Prados Date: Wed, 2 Apr 2025 16:43:27 +0200 Subject: [PATCH] Fix empty producer --- .../langchain_community/document_loaders/parsers/pdf.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/libs/community/langchain_community/document_loaders/parsers/pdf.py b/libs/community/langchain_community/document_loaders/parsers/pdf.py index 745498cdcbe..5e4ff7f3225 100644 --- a/libs/community/langchain_community/document_loaders/parsers/pdf.py +++ b/libs/community/langchain_community/document_loaders/parsers/pdf.py @@ -1535,7 +1535,12 @@ class PDFPlumberParser(BaseBlobParser): # The new 'standard' version must use lower case key. if self.metadata_format == "legacy": doc_metadata = ( - doc.metadata # Add parser metdata + { + "producer": "PDFPlumber", + "creator": "PDFPlumber", + "creationdate": "", + } + | doc.metadata # Add parser metdata | { # with more keys "source": blob.source, "file_path": blob.source,