Fix bugs in API (#3204)

### What problem does this PR solve?

Fix bugs in API

### Type of change

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

---------

Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>

api/apps/sdk/chat.py

@@ -264,7 +264,7 @@ def list_chat(tenant_id):
     if not chat:
         return get_error_data_result(message="The chat doesn't exist")
     page_number = int(request.args.get("page", 1))
-    items_per_page = int(request.args.get("page_size", 1024))
+    items_per_page = int(request.args.get("page_size", 30))
     orderby = request.args.get("orderby", "create_time")
     if request.args.get("desc") == "False" or request.args.get("desc") == "false":
         desc = False
@@ -308,4 +308,4 @@ def list_chat(tenant_id):
         res["datasets"] = kb_list
         res["avatar"] = res.pop("icon")
         list_assts.append(res)
-    return get_result(data=list_assts)
+    return get_result(data=list_assts)

api/apps/sdk/dataset.py

@@ -502,7 +502,7 @@ def list(tenant_id):
     if not kbs:
         return get_error_data_result(message="The dataset doesn't exist")
     page_number = int(request.args.get("page", 1))
-    items_per_page = int(request.args.get("page_size", 1024))
+    items_per_page = int(request.args.get("page_size", 30))
     orderby = request.args.get("orderby", "create_time")
     if request.args.get("desc") == "False" or request.args.get("desc") == "false":
         desc = False
@@ -532,4 +532,4 @@ def list(tenant_id):
             new_key = key_mapping.get(key, key)
             renamed_data[new_key] = value
         renamed_list.append(renamed_data)
-    return get_result(data=renamed_list)
+    return get_result(data=renamed_list)

api/apps/sdk/doc.py

@@ -386,16 +386,16 @@ def list_docs(dataset_id, tenant_id):
         required: false
         description: Filter by document ID.
       - in: query
-        name: offset
+        name: page
         type: integer
         required: false
         default: 1
         description: Page number.
       - in: query
-        name: limit
+        name: page_size
         type: integer
         required: false
-        default: 1024
+        default: 30
         description: Number of items per page.
       - in: query
         name: orderby
@@ -460,7 +460,7 @@ def list_docs(dataset_id, tenant_id):
         return get_error_data_result(message=f"You don't own the document {name}.")
     page = int(request.args.get("page", 1))
     keywords = request.args.get("keywords", "")
-    page_size = int(request.args.get("page_size", 1024))
+    page_size = int(request.args.get("page_size", 30))
     orderby = request.args.get("orderby", "create_time")
     if request.args.get("desc") == "False":
         desc = False
@@ -741,13 +741,13 @@ def list_chunks(tenant_id, dataset_id, document_id):
         required: true
         description: ID of the document.
       - in: query
-        name: offset
+        name: page
         type: integer
         required: false
         default: 1
         description: Page number.
       - in: query
-        name: limit
+        name: page_size
         type: integer
         required: false
         default: 30
@@ -1323,7 +1323,7 @@ def retrieval_test(tenant_id):
     if "question" not in req:
         return get_error_data_result("`question` is required.")
     page = int(req.get("page", 1))
-    size = int(req.get("page_size", 1024))
+    size = int(req.get("page_size", 30))
     question = req["question"]
     doc_ids = req.get("document_ids", [])
     if not isinstance(doc_ids, list):
@@ -1401,4 +1401,4 @@ def retrieval_test(tenant_id):
                 message="No chunk found! Check the chunk status please!",
                 code=RetCode.DATA_ERROR,
             )
-        return server_error_response(e)
+        return server_error_response(e)

api/apps/sdk/session.py

@@ -322,7 +322,7 @@ def list(chat_id,tenant_id):
     id = request.args.get("id")
     name = request.args.get("name")
     page_number = int(request.args.get("page", 1))
-    items_per_page = int(request.args.get("page_size", 1024))
+    items_per_page = int(request.args.get("page_size", 30))
     orderby = request.args.get("orderby", "create_time")
     if request.args.get("desc") == "False" or request.args.get("desc") == "false":
         desc = False
@@ -391,4 +391,4 @@ def delete(tenant_id,chat_id):
         if not conv:
             return get_error_data_result(message="The chat doesn't own the session")
         ConversationService.delete_by_id(id)
-    return get_result()
+    return get_result()

sdk/python/ragflow_sdk/modules/chat.py

@@ -57,7 +57,7 @@ class Chat(Base):
             return Session(self.rag, res['data'])
         raise Exception(res["message"])
 
-    def list_sessions(self,page: int = 1, page_size: int = 1024, orderby: str = "create_time", desc: bool = True,
+    def list_sessions(self,page: int = 1, page_size: int = 30, orderby: str = "create_time", desc: bool = True,
                       id: str = None, name: str = None) -> List[Session]:
         res = self.get(f'/chats/{self.id}/sessions',{"page": page, "page_size": page_size, "orderby": orderby, "desc": desc, "id": id, "name": name} )
         res = res.json()

sdk/python/ragflow_sdk/modules/dataset.py

@@ -48,7 +48,7 @@ class DataSet(Base):
             return doc_list
         raise Exception(res.get("message"))
 
-    def list_documents(self, id: str = None, keywords: str = None, page: int =1, page_size: int = 1024, orderby: str = "create_time", desc: bool = True):
+    def list_documents(self, id: str = None, keywords: str = None, page: int =1, page_size: int = 30, orderby: str = "create_time", desc: bool = True):
         res = self.get(f"/datasets/{self.id}/documents",params={"id": id,"keywords": keywords,"page": page,"page_size": page_size,"orderby": orderby,"desc": desc})
         res = res.json()
         documents = []

sdk/python/ragflow_sdk/ragflow.py

@@ -76,7 +76,7 @@ class RAGFlow:
             return _list[0]
         raise Exception("Dataset %s not found" % name)
 
-    def list_datasets(self, page: int = 1, page_size: int = 1024, orderby: str = "create_time", desc: bool = True,
+    def list_datasets(self, page: int = 1, page_size: int = 30, orderby: str = "create_time", desc: bool = True,
                       id: str = None, name: str = None) -> \
             List[DataSet]:
         res = self.get("/datasets",
@@ -142,7 +142,7 @@ class RAGFlow:
         if res.get("code") != 0:
             raise Exception(res["message"])
 
-    def list_chats(self, page: int = 1, page_size: int = 1024, orderby: str = "create_time", desc: bool = True,
+    def list_chats(self, page: int = 1, page_size: int = 30, orderby: str = "create_time", desc: bool = True,
                       id: str = None, name: str = None) -> List[Chat]:
         res = self.get("/chats",{"page": page, "page_size": page_size, "orderby": orderby, "desc": desc, "id": id, "name": name})
         res = res.json()
@@ -154,12 +154,12 @@ class RAGFlow:
         raise Exception(res["message"])
 
 
-    def retrieve(self, dataset_ids, document_ids=None, question="", page=1, page_size=1024, similarity_threshold=0.2, vector_similarity_weight=0.3, top_k=1024, rerank_id:str=None, keyword:bool=False, ):
+    def retrieve(self, dataset_ids, document_ids=None, question="", page=1, page_size=30, similarity_threshold=0.2, vector_similarity_weight=0.3, top_k=1024, rerank_id:str=None, keyword:bool=False, ):
             if document_ids is None:
                 document_ids = []
             data_json ={
-                "offset": page,
-                "limit": page_size,
+                "page": page,
+                "page_size": page_size,
                 "similarity_threshold": similarity_threshold,
                 "vector_similarity_weight": vector_similarity_weight,
                 "top_k": top_k,

sdk/python/test/t_document.py

@@ -45,7 +45,7 @@ def test_list_documents_in_dataset_with_success(get_api_key_fixture):
     blob = b"Sample document content for test."
     document_infos = [{"displayed_name": "test.txt","blob":blob}]
     ds.upload_documents(document_infos)
-    ds.list_documents(keywords="test", page=0, page_size=12)
+    ds.list_documents(keywords="test", page=1, page_size=12)