From 7fb8b30cc22f7007e56e4e76894cc3f24137135e Mon Sep 17 00:00:00 2001 From: Lynn Date: Mon, 13 Oct 2025 11:11:06 +0800 Subject: [PATCH] fix: decode before format to json (#10506) ### What problem does this PR solve? Decode bytes before format to json. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) --- rag/flow/parser/parser.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/rag/flow/parser/parser.py b/rag/flow/parser/parser.py index 86e039118..b1a34c59b 100644 --- a/rag/flow/parser/parser.py +++ b/rag/flow/parser/parser.py @@ -411,7 +411,7 @@ class Parser(ProcessBase): dispositions = content_disposition.strip().split(";") if dispositions[0].lower() == "attachment": filename = part.get_filename() - payload = part.get_payload(decode=True) + payload = part.get_payload(decode=True).decode(part.get_content_charset()) attachments.append({ "filename": filename, "payload": payload, @@ -448,7 +448,7 @@ class Parser(ProcessBase): for t in msg.attachments: attachments.append({ "filename": t.name, - "payload": t.data # binary + "payload": t.data.decode("utf-8") }) email_content["attachments"] = attachments