Merge pull request #12971 from tth37/fix_source_indexing

fix: Align backend <source> tag indexing with frontend citation grouping

backend/open_webui/utils/middleware.py

@@ -888,16 +888,20 @@ 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 = ""
-        citated_file_idx = {}
-        for _, source in enumerate(sources, 1):
+        citation_idx = {}
+        for source in sources:
             if "document" in source:
                 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 id="{citated_file_idx[file_id]}">{doc_context}</source>\n'
+                    citation_id = (
+                        doc_meta.get("source", None)
+                        or source.get("source", {}).get("id", None)
+                        or "N/A"
+                    )
+                    if citation_id not in citation_idx:
+                        citation_idx[citation_id] = len(citation_idx) + 1
+                    context_string += f'<source id="{citation_idx[citation_id]}">{doc_context}</source>\n'
 
         context_string = context_string.strip()
         prompt = get_last_user_message(form_data["messages"])

src/lib/components/chat/Messages/Citations.svelte

@@ -83,6 +83,7 @@
 			});
 			return acc;
 		}, []);
+		console.log('citations', citations);
 
 		showRelevance = calculateShowRelevance(citations);
 		showPercentage = shouldShowPercentage(citations);