From 14ee51aeadee5ecf45a5ac6b99be248f2e76bd30 Mon Sep 17 00:00:00 2001
From: Jyong <76649700+JohnJyong@users.noreply.github.com>
Date: Thu, 9 Jan 2025 20:21:25 +0800
Subject: [PATCH] Feat/add knowledge include all filter (#12537)

---
 api/controllers/console/datasets/datasets.py   | 4 ++--
 api/controllers/service_api/dataset/dataset.py | 5 ++++-
 api/services/dataset_service.py                | 4 ++--
 3 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/api/controllers/console/datasets/datasets.py b/api/controllers/console/datasets/datasets.py
index 2da45a7bb6..386e45c58e 100644
--- a/api/controllers/console/datasets/datasets.py
+++ b/api/controllers/console/datasets/datasets.py
@@ -52,12 +52,12 @@ class DatasetListApi(Resource):
         # provider = request.args.get("provider", default="vendor")
         search = request.args.get("keyword", default=None, type=str)
         tag_ids = request.args.getlist("tag_ids")
-
+        include_all = request.args.get("include_all", default="false").lower() == "true"
         if ids:
             datasets, total = DatasetService.get_datasets_by_ids(ids, current_user.current_tenant_id)
         else:
             datasets, total = DatasetService.get_datasets(
-                page, limit, current_user.current_tenant_id, current_user, search, tag_ids
+                page, limit, current_user.current_tenant_id, current_user, search, tag_ids, include_all
             )
 
         # check embedding setting
diff --git a/api/controllers/service_api/dataset/dataset.py b/api/controllers/service_api/dataset/dataset.py
index d6a3beb6b8..49acdd693a 100644
--- a/api/controllers/service_api/dataset/dataset.py
+++ b/api/controllers/service_api/dataset/dataset.py
@@ -31,8 +31,11 @@ class DatasetListApi(DatasetApiResource):
         # provider = request.args.get("provider", default="vendor")
         search = request.args.get("keyword", default=None, type=str)
         tag_ids = request.args.getlist("tag_ids")
+        include_all = request.args.get("include_all", default="false").lower() == "true"
 
-        datasets, total = DatasetService.get_datasets(page, limit, tenant_id, current_user, search, tag_ids)
+        datasets, total = DatasetService.get_datasets(
+            page, limit, tenant_id, current_user, search, tag_ids, include_all
+        )
         # check embedding setting
         provider_manager = ProviderManager()
         configurations = provider_manager.get_configurations(tenant_id=current_user.current_tenant_id)
diff --git a/api/services/dataset_service.py b/api/services/dataset_service.py
index 82433b64ff..dac0a6a772 100644
--- a/api/services/dataset_service.py
+++ b/api/services/dataset_service.py
@@ -71,7 +71,7 @@ from tasks.sync_website_document_indexing_task import sync_website_document_inde
 
 class DatasetService:
     @staticmethod
-    def get_datasets(page, per_page, tenant_id=None, user=None, search=None, tag_ids=None):
+    def get_datasets(page, per_page, tenant_id=None, user=None, search=None, tag_ids=None, include_all=False):
         query = Dataset.query.filter(Dataset.tenant_id == tenant_id).order_by(Dataset.created_at.desc())
 
         if user:
@@ -86,7 +86,7 @@ class DatasetService:
                 else:
                     return [], 0
             else:
-                if user.current_role != TenantAccountRole.OWNER:
+                if user.current_role != TenantAccountRole.OWNER or not include_all:
                     # show all datasets that the user has permission to access
                     if permitted_dataset_ids:
                         query = query.filter(