From 50ca44c79ffab9e29ecc5e154b4c833cd0893a32 Mon Sep 17 00:00:00 2001
From: Juhee Kim <46583939+juppytt@users.noreply.github.com>
Date: Mon, 4 Sep 2023 08:04:36 +0900
Subject: [PATCH] fix multipart email body retrieval (#9790)

Description:
Gmail message retrieval in GmailGetMessage and GmailSearch returned an
empty string when encountering multipart emails. This change correctly
extracts the email body for multipart emails.

Dependencies: None

@hwchase17 @vowelparrot
---
 libs/langchain/langchain/tools/gmail/get_message.py | 11 ++++++++++-
 libs/langchain/langchain/tools/gmail/search.py      | 11 ++++++++++-
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/libs/langchain/langchain/tools/gmail/get_message.py b/libs/langchain/langchain/tools/gmail/get_message.py
index e1cca7b13..a5f35ba71 100644
--- a/libs/langchain/langchain/tools/gmail/get_message.py
+++ b/libs/langchain/langchain/tools/gmail/get_message.py
@@ -46,7 +46,16 @@ class GmailGetMessage(GmailBaseTool):
         subject = email_msg["Subject"]
         sender = email_msg["From"]
 
-        message_body = email_msg.get_payload()
+        message_body = ""
+        if email_msg.is_multipart():
+            for part in email_msg.walk():
+                ctype = part.get_content_type()
+                cdispo = str(part.get("Content-Disposition"))
+                if ctype == "text/plain" and "attachment" not in cdispo:
+                    message_body = part.get_payload(decode=True).decode("utf-8")
+                    break
+        else:
+            message_body = email_msg.get_payload(decode=True).decode("utf-8")
 
         body = clean_email_body(message_body)
 
diff --git a/libs/langchain/langchain/tools/gmail/search.py b/libs/langchain/langchain/tools/gmail/search.py
index 045834abc..f4de000f5 100644
--- a/libs/langchain/langchain/tools/gmail/search.py
+++ b/libs/langchain/langchain/tools/gmail/search.py
@@ -91,7 +91,16 @@ class GmailSearch(GmailBaseTool):
             subject = email_msg["Subject"]
             sender = email_msg["From"]
 
-            message_body = email_msg.get_payload()
+            message_body = ""
+            if email_msg.is_multipart():
+                for part in email_msg.walk():
+                    ctype = part.get_content_type()
+                    cdispo = str(part.get("Content-Disposition"))
+                    if ctype == "text/plain" and "attachment" not in cdispo:
+                        message_body = part.get_payload(decode=True).decode("utf-8")
+                        break
+            else:
+                message_body = email_msg.get_payload(decode=True).decode("utf-8")
 
             body = clean_email_body(message_body)