Fix: Merge main branch (#10377)

### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: jinhai <haijin.chn@gmail.com>
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com>
Co-authored-by: huangzl <huangzl@shinemo.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Wilmer <33392318@qq.com>
Co-authored-by: Adrian Weidig <adrianweidig@gmx.net>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Liu An <asiro@qq.com>
Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com>
Co-authored-by: BadwomanCraZY <511528396@qq.com>
Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com>
Co-authored-by: Russell Valentine <russ@coldstonelabs.org>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Billy Bao <newyorkupperbay@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com>
Co-authored-by: TensorNull <tensor.null@gmail.com>
Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com>
Co-authored-by: AB <aj@Ajays-MacBook-Air.local>
Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com>
Co-authored-by: He Wang <wanghechn@qq.com>
Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com>
Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box>
Co-authored-by: Stephen Hu <stephenhu@seismic.com>
Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com>
Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com>
Co-authored-by: mxc <mxc@example.com>
Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com>
Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com>
Co-authored-by: mcoder6425 <mcoder64@gmail.com>
Co-authored-by: TeslaZY <TeslaZY@outlook.com>
Co-authored-by: lemsn <lemsn@msn.com>
Co-authored-by: lemsn <lemsn@126.com>
Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com>
Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com>
Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>

api/db/services/document_service.py

@@ -243,6 +243,46 @@ class DocumentService(CommonService):
 
         return int(query.scalar()) or 0
 
+    @classmethod
+    @DB.connection_context()
+    def get_all_doc_ids_by_kb_ids(cls, kb_ids):
+        fields = [cls.model.id]
+        docs = cls.model.select(*fields).where(cls.model.kb_id.in_(kb_ids))
+        docs.order_by(cls.model.create_time.asc())
+        # maybe cause slow query by deep paginate, optimize later
+        offset, limit = 0, 100
+        res = []
+        while True:
+            doc_batch = docs.offset(offset).limit(limit)
+            _temp = list(doc_batch.dicts())
+            if not _temp:
+                break
+            res.extend(_temp)
+            offset += limit
+        return res
+
+    @classmethod
+    @DB.connection_context()
+    def get_all_docs_by_creator_id(cls, creator_id):
+        fields = [
+            cls.model.id, cls.model.kb_id, cls.model.token_num, cls.model.chunk_num, Knowledgebase.tenant_id
+        ]
+        docs = cls.model.select(*fields).join(Knowledgebase, on=(Knowledgebase.id == cls.model.kb_id)).where(
+            cls.model.created_by == creator_id
+        )
+        docs.order_by(cls.model.create_time.asc())
+        # maybe cause slow query by deep paginate, optimize later
+        offset, limit = 0, 100
+        res = []
+        while True:
+            doc_batch = docs.offset(offset).limit(limit)
+            _temp = list(doc_batch.dicts())
+            if not _temp:
+                break
+            res.extend(_temp)
+            offset += limit
+        return res
+
     @classmethod
     @DB.connection_context()
     def insert(cls, doc):
@@ -517,9 +557,6 @@ class DocumentService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_doc_id_by_doc_name(cls, doc_name):
-        """
-        highly rely on the strict deduplication guarantee from Document
-        """
         fields = [cls.model.id]
         doc_id = cls.model.select(*fields) \
             .where(cls.model.name == doc_name)
@@ -681,8 +718,16 @@ class DocumentService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_kb_doc_count(cls, kb_id):
-        return len(cls.model.select(cls.model.id).where(
-            cls.model.kb_id == kb_id).dicts())
+        return cls.model.select().where(cls.model.kb_id == kb_id).count()
+
+    @classmethod
+    @DB.connection_context()
+    def get_all_kb_doc_count(cls):
+        result = {}
+        rows = cls.model.select(cls.model.kb_id, fn.COUNT(cls.model.id).alias('count')).group_by(cls.model.kb_id)
+        for row in rows:
+            result[row.kb_id] = row.count
+        return result
 
     @classmethod
     @DB.connection_context()