From d8a7e9c660a0c5115c578fd092aee70b8f2bccaf Mon Sep 17 00:00:00 2001
From: Alexander Grimm <agrimm@ailio.de>
Date: Mon, 7 Apr 2025 11:33:29 +0000
Subject: [PATCH 1/2] fix: correct document citation

---
 backend/open_webui/utils/middleware.py | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/backend/open_webui/utils/middleware.py b/backend/open_webui/utils/middleware.py
index badae9906..5e6f286a0 100644
--- a/backend/open_webui/utils/middleware.py
+++ b/backend/open_webui/utils/middleware.py
@@ -897,12 +897,14 @@ async def process_chat_payload(request, form_data, user, metadata, model):
     # If context is not empty, insert it into the messages
     if len(sources) > 0:
         context_string = ""
-        for source_idx, source in enumerate(sources):
+        citated_file_idx = {}
+        for _, source in enumerate(sources, 1):
             if "document" in source:
-                for doc_idx, doc_context in enumerate(source["document"]):
-                    context_string += (
-                        f'<source id="{source_idx + 1}">{doc_context}</source>\n'
-                    )
+                for doc_context, doc_meta in zip(source["document"], source['metadata']):
+                    file_id = doc_meta.get('file_id')
+                    if file_id not in citated_file_idx:
+                        citated_file_idx[file_id] = len(citated_file_idx) + 1
+                    context_string += f"<source><source_id>{citated_file_idx[file_id]}</source_id><source_context>{doc_context}</source_context></source>\n"
 
         context_string = context_string.strip()
         prompt = get_last_user_message(form_data["messages"])

From 1e7a36478bc4cf36caa85f4944740fbfeef3d7e7 Mon Sep 17 00:00:00 2001
From: Alexander Grimm <agrimm@ailio.de>
Date: Mon, 7 Apr 2025 14:07:27 +0200
Subject: [PATCH 2/2] ~ update to latest change

---
 backend/open_webui/utils/middleware.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/backend/open_webui/utils/middleware.py b/backend/open_webui/utils/middleware.py
index 5e6f286a0..2c6728955 100644
--- a/backend/open_webui/utils/middleware.py
+++ b/backend/open_webui/utils/middleware.py
@@ -904,7 +904,9 @@ async def process_chat_payload(request, form_data, user, metadata, model):
                     file_id = doc_meta.get('file_id')
                     if file_id not in citated_file_idx:
                         citated_file_idx[file_id] = len(citated_file_idx) + 1
-                    context_string += f"<source><source_id>{citated_file_idx[file_id]}</source_id><source_context>{doc_context}</source_context></source>\n"
+                    context_string += (
+                        f'<source id="{citated_file_idx[file_id]}">{doc_context}</source>\n'
+                    )
 
         context_string = context_string.strip()
         prompt = get_last_user_message(form_data["messages"])