metadata update

api/controllers/console/datasets/datasets_segments.py

@@ -88,9 +88,9 @@ class DatasetDocumentSegmentListApi(Resource):
 
         if args["enabled"].lower() != "all":
             if args["enabled"].lower() == "true":
-                query = query.filter(DocumentSegment.enabled == True)
+                query = query.filter(DocumentSegment.enabled == True)  # noqa: E712
             elif args["enabled"].lower() == "false":
-                query = query.filter(DocumentSegment.enabled == False)
+                query = query.filter(DocumentSegment.enabled == False)  # noqa: E712
 
         segments = query.paginate(page=page, per_page=limit, max_per_page=100, error_out=False)
 

api/core/workflow/nodes/knowledge_retrieval/entities.py

@@ -73,6 +73,15 @@ class SingleRetrievalConfig(BaseModel):
     model: ModelConfig
 
 
+class MetadataFilteringCondition(BaseModel):
+    """
+    Metadata Filtering Condition.
+    """
+    
+    logical_operator: Optional[Literal["and", "or"]] = "and"
+    conditions: Optional[list[Condition]] = Field(default=None, deprecated=True)
+
+
 class KnowledgeRetrievalNodeData(BaseNodeData):
     """
     Knowledge retrieval Node Data.
@@ -84,3 +93,5 @@ class KnowledgeRetrievalNodeData(BaseNodeData):
     retrieval_mode: Literal["single", "multiple"]
     multiple_retrieval_config: Optional[MultipleRetrievalConfig] = None
     single_retrieval_config: Optional[SingleRetrievalConfig] = None
+    metadata_filtering_mode: Optional[Literal["disabled", "automatic", "manual"]]  = "disabled"
+    metadata_filtering_conditions: Optional[dict[str, Any]] = None

api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py

@@ -95,8 +95,8 @@ class KnowledgeRetrievalNode(BaseNode[KnowledgeRetrievalNodeData]):
             db.session.query(Document.dataset_id, func.count(Document.id).label("available_document_count"))
             .filter(
                 Document.indexing_status == "completed",
-                Document.enabled == True,
-                Document.archived == False,
+                Document.enabled == True,  # noqa: E712
+                Document.archived == False,  # noqa: E712
                 Document.dataset_id.in_(dataset_ids),
             )
             .group_by(Document.dataset_id)
@@ -221,8 +221,8 @@ class KnowledgeRetrievalNode(BaseNode[KnowledgeRetrievalNodeData]):
                     dataset = Dataset.query.filter_by(id=segment.dataset_id).first()
                     document = Document.query.filter(
                         Document.id == segment.document_id,
-                        Document.enabled == True,
-                        Document.archived == False,
+                        Document.enabled == True,  # noqa: E712
+                        Document.archived == False,  # noqa: E712
                     ).first()
                     if dataset and document:
                         source = {

api/models/dataset.py

@@ -398,6 +398,19 @@ class Document(db.Model):  # type: ignore[name-defined]
         )
 
     @property
+    def uploader(self):
+        user = db.session.query(Account).filter(Account.id == self.created_by).first()
+        return user.name if user else None
+
+    @property
+    def upload_date(self):
+        return self.created_at
+
+    @property
+    def last_update_date(self):
+        return self.updated_at
+
+
     def process_rule_dict(self):
         if self.dataset_process_rule_id:
             return self.dataset_process_rule.to_dict()

api/services/dataset_service.py

@@ -15,6 +15,7 @@ from configs import dify_config
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
+from core.rag.index_processor.constant.built_in_field import BuiltInField
 from core.rag.index_processor.constant.index_type import IndexType
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
 from events.dataset_event import dataset_was_deleted
@@ -687,8 +688,12 @@ class DocumentService:
 
         if document.tenant_id != current_user.current_tenant_id:
             raise ValueError("No permission.")
-
-        document.name = name
+        
+        if dataset.built_in_field_enabled:
+            if document.doc_metadata:
+                document.doc_metadata[BuiltInField.document_name] = name
+        else:
+            document.name = name
 
         db.session.add(document)
         db.session.commit()
@@ -1086,9 +1091,20 @@ class DocumentService:
             doc_form=document_form,
             doc_language=document_language,
         )
+        doc_metadata = {}
+        if dataset.built_in_field_enabled:
+            doc_metadata = {
+                BuiltInField.document_name: name,
+                BuiltInField.uploader: account.name,
+                BuiltInField.upload_date: datetime.datetime.now(datetime.timezone.utc).strftime("%Y-%m-%d %H:%M:%S"),
+                BuiltInField.last_update_date: datetime.datetime.now(datetime.timezone.utc).strftime("%Y-%m-%d %H:%M:%S"),
+                BuiltInField.source: data_source_type,
+            }
         if metadata is not None:
-            document.doc_metadata = metadata.doc_metadata
+            doc_metadata.update(metadata.doc_metadata)
             document.doc_type = metadata.doc_type
+        if doc_metadata:
+            document.doc_metadata = doc_metadata
         return document
 
     @staticmethod

api/services/entities/knowledge_entities/knowledge_entities.py

@@ -129,3 +129,10 @@ class ChildChunkUpdateArgs(BaseModel):
 class MetadataArgs(BaseModel):
     type: Literal["string", "number", "time"]
     name: str
+
+class MetadataValue(BaseModel):
+    name: str
+    value: str
+
+class MetadataValueUpdateArgs(BaseModel):
+    fields: list[MetadataValue]