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/console/datasets/datasets_document.py

@@ -45,6 +45,7 @@ from models.dataset import DocumentPipelineExecutionLog
 from services.dataset_service import DatasetService, DocumentService
 from services.entities.knowledge_entities.knowledge_entities import KnowledgeConfig, ProcessRule, RetrievalModel
 from services.file_service import FileService
+from tasks.generate_summary_index_task import generate_summary_index_task
 
 from ..app.error import (
     ProviderModelCurrentlyNotSupportError,
@@ -103,6 +104,10 @@ class DocumentRenamePayload(BaseModel):
     name: str
 
 
+class GenerateSummaryPayload(BaseModel):
+    document_list: list[str]
+
+
 class DocumentBatchDownloadZipPayload(BaseModel):
     """Request payload for bulk downloading documents as a zip archive."""
 
@@ -125,6 +130,7 @@ register_schema_models(
     RetrievalModel,
     DocumentRetryPayload,
     DocumentRenamePayload,
+    GenerateSummaryPayload,
     DocumentBatchDownloadZipPayload,
 )
 
@@ -312,6 +318,13 @@ class DatasetDocumentListApi(Resource):
 
         paginated_documents = db.paginate(select=query, page=page, per_page=limit, max_per_page=100, error_out=False)
         documents = paginated_documents.items
+
+        DocumentService.enrich_documents_with_summary_index_status(
+            documents=documents,
+            dataset=dataset,
+            tenant_id=current_tenant_id,
+        )
+
         if fetch:
             for document in documents:
                 completed_segments = (
@@ -797,6 +810,7 @@ class DocumentApi(DocumentResource):
                 "display_status": document.display_status,
                 "doc_form": document.doc_form,
                 "doc_language": document.doc_language,
+                "need_summary": document.need_summary if document.need_summary is not None else False,
             }
         else:
             dataset_process_rules = DatasetService.get_process_rules(dataset_id)
@@ -832,6 +846,7 @@ class DocumentApi(DocumentResource):
                 "display_status": document.display_status,
                 "doc_form": document.doc_form,
                 "doc_language": document.doc_language,
+                "need_summary": document.need_summary if document.need_summary is not None else False,
             }
 
         return response, 200
@@ -1255,3 +1270,137 @@ class DocumentPipelineExecutionLogApi(DocumentResource):
             "input_data": log.input_data,
             "datasource_node_id": log.datasource_node_id,
         }, 200
+
+
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/generate-summary")
+class DocumentGenerateSummaryApi(Resource):
+    @console_ns.doc("generate_summary_for_documents")
+    @console_ns.doc(description="Generate summary index for documents")
+    @console_ns.doc(params={"dataset_id": "Dataset ID"})
+    @console_ns.expect(console_ns.models[GenerateSummaryPayload.__name__])
+    @console_ns.response(200, "Summary generation started successfully")
+    @console_ns.response(400, "Invalid request or dataset configuration")
+    @console_ns.response(403, "Permission denied")
+    @console_ns.response(404, "Dataset not found")
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @cloud_edition_billing_rate_limit_check("knowledge")
+    def post(self, dataset_id):
+        """
+        Generate summary index for specified documents.
+
+        This endpoint checks if the dataset configuration supports summary generation
+        (indexing_technique must be 'high_quality' and summary_index_setting.enable must be true),
+        then asynchronously generates summary indexes for the provided documents.
+        """
+        current_user, _ = current_account_with_tenant()
+        dataset_id = str(dataset_id)
+
+        # Get dataset
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+
+        # Check permissions
+        if not current_user.is_dataset_editor:
+            raise Forbidden()
+
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        # Validate request payload
+        payload = GenerateSummaryPayload.model_validate(console_ns.payload or {})
+        document_list = payload.document_list
+
+        if not document_list:
+            from werkzeug.exceptions import BadRequest
+
+            raise BadRequest("document_list cannot be empty.")
+
+        # Check if dataset configuration supports summary generation
+        if dataset.indexing_technique != "high_quality":
+            raise ValueError(
+                f"Summary generation is only available for 'high_quality' indexing technique. "
+                f"Current indexing technique: {dataset.indexing_technique}"
+            )
+
+        summary_index_setting = dataset.summary_index_setting
+        if not summary_index_setting or not summary_index_setting.get("enable"):
+            raise ValueError("Summary index is not enabled for this dataset. Please enable it in the dataset settings.")
+
+        # Verify all documents exist and belong to the dataset
+        documents = DocumentService.get_documents_by_ids(dataset_id, document_list)
+
+        if len(documents) != len(document_list):
+            found_ids = {doc.id for doc in documents}
+            missing_ids = set(document_list) - found_ids
+            raise NotFound(f"Some documents not found: {list(missing_ids)}")
+
+        # Dispatch async tasks for each document
+        for document in documents:
+            # Skip qa_model documents as they don't generate summaries
+            if document.doc_form == "qa_model":
+                logger.info("Skipping summary generation for qa_model document %s", document.id)
+                continue
+
+            # Dispatch async task
+            generate_summary_index_task.delay(dataset_id, document.id)
+            logger.info(
+                "Dispatched summary generation task for document %s in dataset %s",
+                document.id,
+                dataset_id,
+            )
+
+        return {"result": "success"}, 200
+
+
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/summary-status")
+class DocumentSummaryStatusApi(DocumentResource):
+    @console_ns.doc("get_document_summary_status")
+    @console_ns.doc(description="Get summary index generation status for a document")
+    @console_ns.doc(params={"dataset_id": "Dataset ID", "document_id": "Document ID"})
+    @console_ns.response(200, "Summary status retrieved successfully")
+    @console_ns.response(404, "Document not found")
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id, document_id):
+        """
+        Get summary index generation status for a document.
+
+        Returns:
+        - total_segments: Total number of segments in the document
+        - summary_status: Dictionary with status counts
+          - completed: Number of summaries completed
+          - generating: Number of summaries being generated
+          - error: Number of summaries with errors
+          - not_started: Number of segments without summary records
+        - summaries: List of summary records with status and content preview
+        """
+        current_user, _ = current_account_with_tenant()
+        dataset_id = str(dataset_id)
+        document_id = str(document_id)
+
+        # Get dataset
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+
+        # Check permissions
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        # Get summary status detail from service
+        from services.summary_index_service import SummaryIndexService
+
+        result = SummaryIndexService.get_document_summary_status_detail(
+            document_id=document_id,
+            dataset_id=dataset_id,
+        )
+
+        return result, 200