Skip to content

The agent engineering platform.

community[patch]: update API ref for AmazonTextractPDFParser (#30468)

ccurmeb60e6f6efa8e
diff --git a/libs/community/langchain_community/document_loaders/parsers/pdf.py b/libs/community/langchain_community/document_loaders/parsers/pdf.py
index 782edddad4..2b53db2873 100644
--- a/libs/community/langchain_community/document_loaders/parsers/pdf.py
+++ b/libs/community/langchain_community/document_loaders/parsers/pdf.py
@@ -1508,6 +1508,11 @@ class AmazonTextractPDFParser(BaseBlobParser):
This helps most LLMs to achieve better accuracy when
processing these texts.
+ ``Document`` objects are returned with metadata that includes the ``source`` and
+ a 1-based index of the page number in ``page``. Note that ``page`` represents
+ the index of the result returned from Textract, not necessarily the as-written
+ page number in the document.
+
"""
def __init__(