feat: Add summary index for knowledge. (#31625)

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: Yansong Zhang <916125788@qq.com>
Co-authored-by: hj24 <mambahj24@gmail.com>
Co-authored-by: CodingOnStar <hanxujiang@dify.ai>
Co-authored-by: CodingOnStar <hanxujiang@dify.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

api/controllers/service_api/dataset/document.py

@@ -45,6 +45,7 @@ from services.entities.knowledge_entities.knowledge_entities import (
     Segmentation,
 )
 from services.file_service import FileService
+from services.summary_index_service import SummaryIndexService
 
 
 class DocumentTextCreatePayload(BaseModel):
@@ -508,6 +509,12 @@ class DocumentListApi(DatasetApiResource):
         )
         documents = paginated_documents.items
 
+        DocumentService.enrich_documents_with_summary_index_status(
+            documents=documents,
+            dataset=dataset,
+            tenant_id=tenant_id,
+        )
+
         response = {
             "data": marshal(documents, document_fields),
             "has_more": len(documents) == query_params.limit,
@@ -612,6 +619,16 @@ class DocumentApi(DatasetApiResource):
         if metadata not in self.METADATA_CHOICES:
             raise InvalidMetadataError(f"Invalid metadata value: {metadata}")
 
+        # Calculate summary_index_status if needed
+        summary_index_status = None
+        has_summary_index = dataset.summary_index_setting and dataset.summary_index_setting.get("enable") is True
+        if has_summary_index and document.need_summary is True:
+            summary_index_status = SummaryIndexService.get_document_summary_index_status(
+                document_id=document_id,
+                dataset_id=dataset_id,
+                tenant_id=tenant_id,
+            )
+
         if metadata == "only":
             response = {"id": document.id, "doc_type": document.doc_type, "doc_metadata": document.doc_metadata_details}
         elif metadata == "without":
@@ -646,6 +663,8 @@ class DocumentApi(DatasetApiResource):
                 "display_status": document.display_status,
                 "doc_form": document.doc_form,
                 "doc_language": document.doc_language,
+                "summary_index_status": summary_index_status,
+                "need_summary": document.need_summary if document.need_summary is not None else False,
             }
         else:
             dataset_process_rules = DatasetService.get_process_rules(dataset_id)
@@ -681,6 +700,8 @@ class DocumentApi(DatasetApiResource):
                 "display_status": document.display_status,
                 "doc_form": document.doc_form,
                 "doc_language": document.doc_language,
+                "summary_index_status": summary_index_status,
+                "need_summary": document.need_summary if document.need_summary is not None else False,
             }
 
         return response