[BREAKING CHANGE] GET to POST: enhance document list capability (#7349)

### What problem does this PR solve?

Enhance capability of `list_docs`.

Breaking change: change method from `GET` to `POST`.

### Type of change

- [x] Refactoring
- [x] Enhancement with breaking change

api/db/__init__.py

@@ -49,6 +49,7 @@ class FileType(StrEnum):
     FOLDER = 'folder'
     OTHER = "other"
 
+VALID_FILE_TYPES = {FileType.PDF, FileType.DOC, FileType.VISUAL, FileType.AURAL, FileType.VIRTUAL, FileType.FOLDER, FileType.OTHER}
 
 class LLMType(StrEnum):
     CHAT = 'chat'
@@ -73,6 +74,7 @@ class TaskStatus(StrEnum):
     DONE = "3"
     FAIL = "4"
 
+VALID_TASK_STATUS     = {TaskStatus.UNSTART, TaskStatus.RUNNING, TaskStatus.CANCEL, TaskStatus.DONE, TaskStatus.FAIL}
 
 class ParserType(StrEnum):
     PRESENTATION = "presentation"

api/db/services/document_service.py

@@ -70,7 +70,7 @@ class DocumentService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_by_kb_id(cls, kb_id, page_number, items_per_page,
-                     orderby, desc, keywords):
+                     orderby, desc, keywords, run_status, types):
         if keywords:
             docs = cls.model.select().where(
                 (cls.model.kb_id == kb_id),
@@ -78,13 +78,21 @@ class DocumentService(CommonService):
             )
         else:
             docs = cls.model.select().where(cls.model.kb_id == kb_id)
+
+        if run_status:
+            docs = docs.where(cls.model.run.in_(run_status))
+        if types:
+            docs = docs.where(cls.model.type.in_(types))
+
         count = docs.count()
         if desc:
             docs = docs.order_by(cls.model.getter_by(orderby).desc())
         else:
             docs = docs.order_by(cls.model.getter_by(orderby).asc())
 
-        docs = docs.paginate(page_number, items_per_page)
+
+        if page_number and items_per_page:
+            docs = docs.paginate(page_number, items_per_page)
 
         return list(docs.dicts()), count
 

api/db/services/knowledgebase_service.py

@@ -97,7 +97,7 @@ class KnowledgebaseService(CommonService):
         kb = kbs[0]
 
         # Get all documents in the knowledge base
-        docs, _ = DocumentService.get_by_kb_id(kb_id, 1, 1000, "create_time", True, "")
+        docs, _ = DocumentService.get_by_kb_id(kb_id, 1, 1000, "create_time", True, "", [], [])
 
         # Check parsing status of each document
         for doc in docs:
@@ -226,7 +226,10 @@ class KnowledgebaseService(CommonService):
             cls.model.chunk_num,
             cls.model.parser_id,
             cls.model.parser_config,
-            cls.model.pagerank]
+            cls.model.pagerank,
+            cls.model.create_time,
+            cls.model.update_time
+            ]
         kbs = cls.model.select(*fields).join(Tenant, on=(
             (Tenant.id == cls.model.tenant_id) & (Tenant.status == StatusEnum.VALID.value))).where(
             (cls.model.id == kb_id),