diff --git a/agent/templates/sql_assistant.json b/agent/templates/sql_assistant.json
index 6e7140196..6c6030f67 100644
--- a/agent/templates/sql_assistant.json
+++ b/agent/templates/sql_assistant.json
@@ -578,7 +578,7 @@
                     {
                         "data": {
                             "form": {
-                                "text": "Searches for relevant database creation statements.\n\nIt should label with a knowledgebase to which the schema is dumped in. You could use \" General \" as parsing method, \" 2 \" as chunk size and \" ; \"  as delimiter."
+                                "text": "Searches for relevant database creation statements.\n\nIt should label with a dataset to which the schema is dumped in. You could use \" General \" as parsing method, \" 2 \" as chunk size and \" ; \"  as delimiter."
                             },
                             "label": "Note",
                             "name": "Note Schema"
diff --git a/agent/test/dsl_examples/retrieval_categorize_and_generate.json b/agent/test/dsl_examples/retrieval_categorize_and_generate.json
index ed6866ae5..2b8dfb779 100644
--- a/agent/test/dsl_examples/retrieval_categorize_and_generate.json
+++ b/agent/test/dsl_examples/retrieval_categorize_and_generate.json
@@ -65,7 +65,7 @@
                     "component_name": "Agent",
                     "params": {
                       "llm_id": "deepseek-chat",
-                      "sys_prompt": "You are an intelligent assistant. Please summarize the content of the knowledge base to answer the question. Please list the data in the knowledge base and answer in detail. When all knowledge base content is irrelevant to the question, your answer must include the sentence \"The answer you are looking for is not found in the knowledge base!\" Answers need to consider chat history.\n      Here is the knowledge base:\n      {retrieval:0@formalized_content}\n      The above is the knowledge base.",
+                      "sys_prompt": "You are an intelligent assistant. Please summarize the content of the dataset to answer the question. Please list the data in the knowledge base and answer in detail. When all knowledge base content is irrelevant to the question, your answer must include the sentence \"The answer you are looking for is not found in the knowledge base!\" Answers need to consider chat history.\n      Here is the knowledge base:\n      {retrieval:0@formalized_content}\n      The above is the knowledge base.",
                       "temperature": 0.2
                     }
                 },
diff --git a/api/apps/chunk_app.py b/api/apps/chunk_app.py
index 0e874e230..26df98148 100644
--- a/api/apps/chunk_app.py
+++ b/api/apps/chunk_app.py
@@ -348,7 +348,7 @@ async def retrieval_test():
                     break
             else:
                 return get_json_result(
-                    data=False, message='Only owner of knowledgebase authorized for this operation.',
+                    data=False, message='Only owner of dataset authorized for this operation.',
                     code=RetCode.OPERATING_ERROR)
 
         e, kb = KnowledgebaseService.get_by_id(kb_ids[0])
diff --git a/api/apps/dialog_app.py b/api/apps/dialog_app.py
index 0f5aebe0b..d2aad88ee 100644
--- a/api/apps/dialog_app.py
+++ b/api/apps/dialog_app.py
@@ -65,7 +65,7 @@ async def set_dialog():
 
     if not is_create:
         if not req.get("kb_ids", []) and not prompt_config.get("tavily_api_key") and "{knowledge}" in prompt_config['system']:
-            return get_data_error_result(message="Please remove `{knowledge}` in system prompt since no knowledge base / Tavily used here.")
+            return get_data_error_result(message="Please remove `{knowledge}` in system prompt since no dataset / Tavily used here.")
 
         for p in prompt_config["parameters"]:
             if p["optional"]:
diff --git a/api/apps/document_app.py b/api/apps/document_app.py
index ba1f6e7db..3c37b5eec 100644
--- a/api/apps/document_app.py
+++ b/api/apps/document_app.py
@@ -70,7 +70,7 @@ async def upload():
 
     e, kb = KnowledgebaseService.get_by_id(kb_id)
     if not e:
-        raise LookupError("Can't find this knowledgebase!")
+        raise LookupError("Can't find this dataset!")
     if not check_kb_team_permission(kb, current_user.id):
         return get_json_result(data=False, message="No authorization.", code=RetCode.AUTHENTICATION_ERROR)
 
@@ -99,7 +99,7 @@ async def web_crawl():
         return get_json_result(data=False, message="The URL format is invalid", code=RetCode.ARGUMENT_ERROR)
     e, kb = KnowledgebaseService.get_by_id(kb_id)
     if not e:
-        raise LookupError("Can't find this knowledgebase!")
+        raise LookupError("Can't find this dataset!")
     if check_kb_team_permission(kb, current_user.id):
         return get_json_result(data=False, message="No authorization.", code=RetCode.AUTHENTICATION_ERROR)
 
@@ -169,10 +169,10 @@ async def create():
     try:
         e, kb = KnowledgebaseService.get_by_id(kb_id)
         if not e:
-            return get_data_error_result(message="Can't find this knowledgebase!")
+            return get_data_error_result(message="Can't find this dataset!")
 
         if DocumentService.query(name=req["name"], kb_id=kb_id):
-            return get_data_error_result(message="Duplicated document name in the same knowledgebase.")
+            return get_data_error_result(message="Duplicated document name in the same dataset.")
 
         kb_root_folder = FileService.get_kb_folder(kb.tenant_id)
         if not kb_root_folder:
@@ -219,7 +219,7 @@ async def list_docs():
         if KnowledgebaseService.query(tenant_id=tenant.tenant_id, id=kb_id):
             break
     else:
-        return get_json_result(data=False, message="Only owner of knowledgebase authorized for this operation.", code=RetCode.OPERATING_ERROR)
+        return get_json_result(data=False, message="Only owner of dataset authorized for this operation.", code=RetCode.OPERATING_ERROR)
     keywords = request.args.get("keywords", "")
 
     page_number = int(request.args.get("page", 0))
@@ -293,7 +293,7 @@ async def get_filter():
         if KnowledgebaseService.query(tenant_id=tenant.tenant_id, id=kb_id):
             break
     else:
-        return get_json_result(data=False, message="Only owner of knowledgebase authorized for this operation.", code=RetCode.OPERATING_ERROR)
+        return get_json_result(data=False, message="Only owner of dataset authorized for this operation.", code=RetCode.OPERATING_ERROR)
 
     keywords = req.get("keywords", "")
 
@@ -343,7 +343,7 @@ async def metadata_summary():
         if KnowledgebaseService.query(tenant_id=tenant.tenant_id, id=kb_id):
             break
     else:
-        return get_json_result(data=False, message="Only owner of knowledgebase authorized for this operation.", code=RetCode.OPERATING_ERROR)
+        return get_json_result(data=False, message="Only owner of dataset authorized for this operation.", code=RetCode.OPERATING_ERROR)
 
     try:
         summary = DocumentService.get_metadata_summary(kb_id)
@@ -365,7 +365,7 @@ async def metadata_update():
         if KnowledgebaseService.query(tenant_id=tenant.tenant_id, id=kb_id):
             break
     else:
-        return get_json_result(data=False, message="Only owner of knowledgebase authorized for this operation.", code=RetCode.OPERATING_ERROR)
+        return get_json_result(data=False, message="Only owner of dataset authorized for this operation.", code=RetCode.OPERATING_ERROR)
 
     selector = req.get("selector", {}) or {}
     updates = req.get("updates", []) or []
@@ -454,7 +454,7 @@ async def change_status():
                 continue
             e, kb = KnowledgebaseService.get_by_id(doc.kb_id)
             if not e:
-                result[doc_id] = {"error": "Can't find this knowledgebase!"}
+                result[doc_id] = {"error": "Can't find this dataset!"}
                 continue
             if not DocumentService.update_by_id(doc_id, {"status": str(status)}):
                 result[doc_id] = {"error": "Database error (Document update)!"}
@@ -562,7 +562,7 @@ async def rename():
 
             for d in DocumentService.query(name=req["name"], kb_id=doc.kb_id):
                 if d.name == req["name"]:
-                    return get_data_error_result(message="Duplicated document name in the same knowledgebase.")
+                    return get_data_error_result(message="Duplicated document name in the same dataset.")
 
             if not DocumentService.update_by_id(req["doc_id"], {"name": req["name"]}):
                 return get_data_error_result(message="Database error (Document rename)!")
diff --git a/api/apps/file2document_app.py b/api/apps/file2document_app.py
index 84975ab1d..f410e8a17 100644
--- a/api/apps/file2document_app.py
+++ b/api/apps/file2document_app.py
@@ -68,7 +68,7 @@ async def convert():
                     e, kb = KnowledgebaseService.get_by_id(kb_id)
                     if not e:
                         return get_data_error_result(
-                            message="Can't find this knowledgebase!")
+                            message="Can't find this dataset!")
                     e, file = FileService.get_by_id(id)
                     if not e:
                         return get_data_error_result(
diff --git a/api/apps/kb_app.py b/api/apps/kb_app.py
index 5d3dee0b9..42afd73e6 100644
--- a/api/apps/kb_app.py
+++ b/api/apps/kb_app.py
@@ -93,19 +93,19 @@ async def update():
         if not KnowledgebaseService.query(
                 created_by=current_user.id, id=req["kb_id"]):
             return get_json_result(
-                data=False, message='Only owner of knowledgebase authorized for this operation.',
+                data=False, message='Only owner of dataset authorized for this operation.',
                 code=RetCode.OPERATING_ERROR)
 
         e, kb = KnowledgebaseService.get_by_id(req["kb_id"])
         if not e:
             return get_data_error_result(
-                message="Can't find this knowledgebase!")
+                message="Can't find this dataset!")
 
         if req["name"].lower() != kb.name.lower() \
                 and len(
             KnowledgebaseService.query(name=req["name"], tenant_id=current_user.id, status=StatusEnum.VALID.value)) >= 1:
             return get_data_error_result(
-                message="Duplicated knowledgebase name.")
+                message="Duplicated dataset name.")
 
         del req["kb_id"]
         connectors = []
@@ -162,12 +162,12 @@ def detail():
                 break
         else:
             return get_json_result(
-                data=False, message='Only owner of knowledgebase authorized for this operation.',
+                data=False, message='Only owner of dataset authorized for this operation.',
                 code=RetCode.OPERATING_ERROR)
         kb = KnowledgebaseService.get_detail(kb_id)
         if not kb:
             return get_data_error_result(
-                message="Can't find this knowledgebase!")
+                message="Can't find this dataset!")
         kb["size"] = DocumentService.get_total_size_by_kb_id(kb_id=kb["id"],keywords="", run_status=[], types=[])
         kb["connectors"] = Connector2KbService.list_connectors(kb_id)
 
@@ -232,7 +232,7 @@ async def rm():
             created_by=current_user.id, id=req["kb_id"])
         if not kbs:
             return get_json_result(
-                data=False, message='Only owner of knowledgebase authorized for this operation.',
+                data=False, message='Only owner of dataset authorized for this operation.',
                 code=RetCode.OPERATING_ERROR)
 
         def _rm_sync():
diff --git a/api/apps/sdk/chat.py b/api/apps/sdk/chat.py
index 8c9619555..3e0213aed 100644
--- a/api/apps/sdk/chat.py
+++ b/api/apps/sdk/chat.py
@@ -92,7 +92,7 @@ async def create(tenant_id):
     req["tenant_id"] = tenant_id
     # prompt more parameter
     default_prompt = {
-        "system": """You are an intelligent assistant. Please summarize the content of the knowledge base to answer the question. Please list the data in the knowledge base and answer in detail. When all knowledge base content is irrelevant to the question, your answer must include the sentence "The answer you are looking for is not found in the knowledge base!" Answers need to consider chat history.
+        "system": """You are an intelligent assistant. Please summarize the content of the dataset to answer the question. Please list the data in the dataset and answer in detail. When all dataset content is irrelevant to the question, your answer must include the sentence "The answer you are looking for is not found in the dataset!" Answers need to consider chat history.
       Here is the knowledge base:
       {knowledge}
       The above is the knowledge base.""",
diff --git a/api/apps/sdk/doc.py b/api/apps/sdk/doc.py
index a5c120d31..d5859e892 100644
--- a/api/apps/sdk/doc.py
+++ b/api/apps/sdk/doc.py
@@ -237,7 +237,7 @@ async def update_doc(tenant_id, dataset_id, document_id):
         return get_error_data_result(message="You don't own the dataset.")
     e, kb = KnowledgebaseService.get_by_id(dataset_id)
     if not e:
-        return get_error_data_result(message="Can't find this knowledgebase!")
+        return get_error_data_result(message="Can't find this dataset!")
     doc = DocumentService.query(kb_id=dataset_id, id=document_id)
     if not doc:
         return get_error_data_result(message="The dataset doesn't own the document.")
diff --git a/api/apps/sdk/files.py b/api/apps/sdk/files.py
index 8bac19ccd..9587d0f15 100644
--- a/api/apps/sdk/files.py
+++ b/api/apps/sdk/files.py
@@ -744,7 +744,7 @@ async def convert(tenant_id):
                     e, kb = KnowledgebaseService.get_by_id(kb_id)
                     if not e:
                         return get_json_result(
-                            message="Can't find this knowledgebase!", code=RetCode.NOT_FOUND)
+                            message="Can't find this dataset!", code=RetCode.NOT_FOUND)
                     e, file = FileService.get_by_id(id)
                     if not e:
                         return get_json_result(
diff --git a/api/apps/sdk/session.py b/api/apps/sdk/session.py
index 34ae6b1ca..1d9b59b26 100644
--- a/api/apps/sdk/session.py
+++ b/api/apps/sdk/session.py
@@ -998,7 +998,7 @@ async def retrieval_test_embedded():
                     tenant_ids.append(tenant.tenant_id)
                     break
             else:
-                return get_json_result(data=False, message="Only owner of knowledgebase authorized for this operation.",
+                return get_json_result(data=False, message="Only owner of dataset authorized for this operation.",
                                        code=RetCode.OPERATING_ERROR)
 
         e, kb = KnowledgebaseService.get_by_id(kb_ids[0])
diff --git a/api/db/joint_services/user_account_service.py b/api/db/joint_services/user_account_service.py
index 48937653e..6ab7d8774 100644
--- a/api/db/joint_services/user_account_service.py
+++ b/api/db/joint_services/user_account_service.py
@@ -153,7 +153,7 @@ def delete_user_data(user_id: str) -> dict:
             done_msg += "Start to delete owned tenant.\n"
             tenant_id = owned_tenant[0]["tenant_id"]
             kb_ids = KnowledgebaseService.get_kb_ids(usr.id)
-            # step1.1 delete knowledgebase related file and info
+            # step1.1 delete dataset related file and info
             if kb_ids:
                 # step1.1.1 delete files in storage, remove bucket
                 for kb_id in kb_ids:
@@ -182,7 +182,7 @@ def delete_user_data(user_id: str) -> dict:
                                          search.index_name(tenant_id), kb_ids)
                 done_msg += f"- Deleted {r} chunk records.\n"
                 kb_delete_res = KnowledgebaseService.delete_by_ids(kb_ids)
-                done_msg += f"- Deleted {kb_delete_res} knowledgebase records.\n"
+                done_msg += f"- Deleted {kb_delete_res} dataset records.\n"
                 # step1.1.4 delete agents
                 agent_delete_res = delete_user_agents(usr.id)
                 done_msg += f"- Deleted {agent_delete_res['agents_deleted_count']} agent, {agent_delete_res['version_deleted_count']} versions records.\n"
@@ -258,7 +258,7 @@ def delete_user_data(user_id: str) -> dict:
                     # step2.1.5 delete document record
                     doc_delete_res = DocumentService.delete_by_ids([d['id'] for d in created_documents])
                     done_msg += f"- Deleted {doc_delete_res} documents.\n"
-                    # step2.1.6 update knowledge base doc&chunk&token cnt
+                    # step2.1.6 update dataset doc&chunk&token cnt
                     for kb_id, doc_num in kb_doc_info.items():
                         KnowledgebaseService.decrease_document_num_in_delete(kb_id, doc_num)
 
diff --git a/api/db/services/document_service.py b/api/db/services/document_service.py
index 1f0d8b248..8308ae4fb 100644
--- a/api/db/services/document_service.py
+++ b/api/db/services/document_service.py
@@ -1082,12 +1082,12 @@ def doc_upload_and_parse(conversation_id, file_objs, user_id):
 
     e, dia = DialogService.get_by_id(conv.dialog_id)
     if not dia.kb_ids:
-        raise LookupError("No knowledge base associated with this conversation. "
-                          "Please add a knowledge base before uploading documents")
+        raise LookupError("No dataset associated with this conversation. "
+                          "Please add a dataset before uploading documents")
     kb_id = dia.kb_ids[0]
     e, kb = KnowledgebaseService.get_by_id(kb_id)
     if not e:
-        raise LookupError("Can't find this knowledgebase!")
+        raise LookupError("Can't find this dataset!")
 
     embd_mdl = LLMBundle(kb.tenant_id, LLMType.EMBEDDING, llm_name=kb.embd_id, lang=kb.language)
 
diff --git a/api/db/services/file_service.py b/api/db/services/file_service.py
index d5a8535ef..8cc5aa37a 100644
--- a/api/db/services/file_service.py
+++ b/api/db/services/file_service.py
@@ -94,11 +94,11 @@ class FileService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_kb_id_by_file_id(cls, file_id):
-        # Get knowledge base IDs associated with a file
+        # Get dataset IDs associated with a file
         # Args:
         #     file_id: File ID
         # Returns:
-        #     List of dictionaries containing knowledge base IDs and names
+        #     List of dictionaries containing dataset IDs and names
         kbs = (
             cls.model.select(*[Knowledgebase.id, Knowledgebase.name])
             .join(File2Document, on=(File2Document.file_id == file_id))
@@ -247,7 +247,7 @@ class FileService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_kb_folder(cls, tenant_id):
-        # Get knowledge base folder for tenant
+        # Get dataset folder for tenant
         # Args:
         #     tenant_id: Tenant ID
         # Returns:
@@ -263,7 +263,7 @@ class FileService(CommonService):
     @classmethod
     @DB.connection_context()
     def new_a_file_from_kb(cls, tenant_id, name, parent_id, ty=FileType.FOLDER.value, size=0, location=""):
-        # Create a new file from knowledge base
+        # Create a new file from dataset
         # Args:
         #     tenant_id: Tenant ID
         #     name: File name
@@ -292,7 +292,7 @@ class FileService(CommonService):
     @classmethod
     @DB.connection_context()
     def init_knowledgebase_docs(cls, root_id, tenant_id):
-        # Initialize knowledge base documents
+        # Initialize dataset documents
         # Args:
         #     root_id: Root folder ID
         #     tenant_id: Tenant ID
diff --git a/api/db/services/knowledgebase_service.py b/api/db/services/knowledgebase_service.py
index 4499a1984..cef05a0d1 100644
--- a/api/db/services/knowledgebase_service.py
+++ b/api/db/services/knowledgebase_service.py
@@ -30,9 +30,9 @@ from api.utils.api_utils import get_parser_config, get_data_error_result
 
 
 class KnowledgebaseService(CommonService):
-    """Service class for managing knowledge base operations.
+    """Service class for managing dataset operations.
 
-    This class extends CommonService to provide specialized functionality for knowledge base
+    This class extends CommonService to provide specialized functionality for dataset
     management, including document parsing status tracking, access control, and configuration
     management. It handles operations such as listing, creating, updating, and deleting
     knowledge bases, as well as managing their associated documents and permissions.
@@ -41,7 +41,7 @@ class KnowledgebaseService(CommonService):
     - Document parsing status verification
     - Knowledge base access control
     - Parser configuration management
-    - Tenant-based knowledge base organization
+    - Tenant-based dataset organization
 
     Attributes:
         model: The Knowledgebase model class for database operations.
@@ -51,18 +51,18 @@ class KnowledgebaseService(CommonService):
     @classmethod
     @DB.connection_context()
     def accessible4deletion(cls, kb_id, user_id):
-        """Check if a knowledge base can be deleted by a specific user.
+        """Check if a dataset can be deleted by a specific user.
 
-        This method verifies whether a user has permission to delete a knowledge base
-        by checking if they are the creator of that knowledge base.
+        This method verifies whether a user has permission to delete a dataset
+        by checking if they are the creator of that dataset.
 
         Args:
-            kb_id (str): The unique identifier of the knowledge base to check.
+            kb_id (str): The unique identifier of the dataset to check.
             user_id (str): The unique identifier of the user attempting the deletion.
 
         Returns:
-            bool: True if the user has permission to delete the knowledge base,
-                  False if the user doesn't have permission or the knowledge base doesn't exist.
+            bool: True if the user has permission to delete the dataset,
+                  False if the user doesn't have permission or the dataset doesn't exist.
 
         Example:
             >>> KnowledgebaseService.accessible4deletion("kb123", "user456")
@@ -71,10 +71,10 @@ class KnowledgebaseService(CommonService):
         Note:
             - This method only checks creator permissions
             - A return value of False can mean either:
-                1. The knowledge base doesn't exist
-                2. The user is not the creator of the knowledge base
+                1. The dataset doesn't exist
+                2. The user is not the creator of the dataset
         """
-        # Check if a knowledge base can be deleted by a user
+        # Check if a dataset can be deleted by a user
         docs = cls.model.select(
             cls.model.id).where(cls.model.id == kb_id, cls.model.created_by == user_id).paginate(0, 1)
         docs = docs.dicts()
@@ -85,7 +85,7 @@ class KnowledgebaseService(CommonService):
     @classmethod
     @DB.connection_context()
     def is_parsed_done(cls, kb_id):
-        # Check if all documents in the knowledge base have completed parsing
+        # Check if all documents in the dataset have completed parsing
         #
         # Args:
         #     kb_id: Knowledge base ID
@@ -96,13 +96,13 @@ class KnowledgebaseService(CommonService):
         from common.constants import TaskStatus
         from api.db.services.document_service import DocumentService
 
-        # Get knowledge base information
+        # Get dataset information
         kbs = cls.query(id=kb_id)
         if not kbs:
             return False, "Knowledge base not found"
         kb = kbs[0]
 
-        # Get all documents in the knowledge base
+        # Get all documents in the dataset
         docs, _ = DocumentService.get_by_kb_id(kb_id, 1, 1000, "create_time", True, "", [], [])
 
         # Check parsing status of each document
@@ -119,9 +119,9 @@ class KnowledgebaseService(CommonService):
     @classmethod
     @DB.connection_context()
     def list_documents_by_ids(cls, kb_ids):
-        # Get document IDs associated with given knowledge base IDs
+        # Get document IDs associated with given dataset IDs
         # Args:
-        #     kb_ids: List of knowledge base IDs
+        #     kb_ids: List of dataset IDs
         # Returns:
         #     List of document IDs
         doc_ids = cls.model.select(Document.id.alias("document_id")).join(Document, on=(cls.model.id == Document.kb_id)).where(
@@ -235,11 +235,11 @@ class KnowledgebaseService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_kb_ids(cls, tenant_id):
-        # Get all knowledge base IDs for a tenant
+        # Get all dataset IDs for a tenant
         # Args:
         #     tenant_id: Tenant ID
         # Returns:
-        #     List of knowledge base IDs
+        #     List of dataset IDs
         fields = [
             cls.model.id,
         ]
@@ -250,11 +250,11 @@ class KnowledgebaseService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_detail(cls, kb_id):
-        # Get detailed information about a knowledge base
+        # Get detailed information about a dataset
         # Args:
         #     kb_id: Knowledge base ID
         # Returns:
-        #     Dictionary containing knowledge base details
+        #     Dictionary containing dataset details
         fields = [
             cls.model.id,
             cls.model.embd_id,
@@ -294,13 +294,13 @@ class KnowledgebaseService(CommonService):
     @classmethod
     @DB.connection_context()
     def update_parser_config(cls, id, config):
-        # Update parser configuration for a knowledge base
+        # Update parser configuration for a dataset
         # Args:
         #     id: Knowledge base ID
         #     config: New parser configuration
         e, m = cls.get_by_id(id)
         if not e:
-            raise LookupError(f"knowledgebase({id}) not found.")
+            raise LookupError(f"dataset({id}) not found.")
 
         def dfs_update(old, new):
             # Deep update of nested configuration
@@ -325,7 +325,7 @@ class KnowledgebaseService(CommonService):
     def delete_field_map(cls, id):
         e, m = cls.get_by_id(id)
         if not e:
-            raise LookupError(f"knowledgebase({id}) not found.")
+            raise LookupError(f"dataset({id}) not found.")
 
         m.parser_config.pop("field_map", None)
         cls.update_by_id(id, {"parser_config": m.parser_config})
@@ -335,7 +335,7 @@ class KnowledgebaseService(CommonService):
     def get_field_map(cls, ids):
         # Get field mappings for knowledge bases
         # Args:
-        #     ids: List of knowledge base IDs
+        #     ids: List of dataset IDs
         # Returns:
         #     Dictionary of field mappings
         conf = {}
@@ -347,7 +347,7 @@ class KnowledgebaseService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_by_name(cls, kb_name, tenant_id):
-        # Get knowledge base by name and tenant ID
+        # Get dataset by name and tenant ID
         # Args:
         #     kb_name: Knowledge base name
         #     tenant_id: Tenant ID
@@ -365,9 +365,9 @@ class KnowledgebaseService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_all_ids(cls):
-        # Get all knowledge base IDs
+        # Get all dataset IDs
         # Returns:
-        #     List of all knowledge base IDs
+        #     List of all dataset IDs
         return [m["id"] for m in cls.model.select(cls.model.id).dicts()]
 
 
@@ -471,7 +471,7 @@ class KnowledgebaseService(CommonService):
     @classmethod
     @DB.connection_context()
     def accessible(cls, kb_id, user_id):
-        # Check if a knowledge base is accessible by a user
+        # Check if a dataset is accessible by a user
         # Args:
         #     kb_id: Knowledge base ID
         #     user_id: User ID
@@ -488,12 +488,12 @@ class KnowledgebaseService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_kb_by_id(cls, kb_id, user_id):
-        # Get knowledge base by ID and user ID
+        # Get dataset by ID and user ID
         # Args:
         #     kb_id: Knowledge base ID
         #     user_id: User ID
         # Returns:
-        #     List containing knowledge base information
+        #     List containing dataset information
         kbs = cls.model.select().join(UserTenant, on=(UserTenant.tenant_id == Knowledgebase.tenant_id)
                                       ).where(cls.model.id == kb_id, UserTenant.user_id == user_id).paginate(0, 1)
         kbs = kbs.dicts()
@@ -502,12 +502,12 @@ class KnowledgebaseService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_kb_by_name(cls, kb_name, user_id):
-        # Get knowledge base by name and user ID
+        # Get dataset by name and user ID
         # Args:
         #     kb_name: Knowledge base name
         #     user_id: User ID
         # Returns:
-        #     List containing knowledge base information
+        #     List containing dataset information
         kbs = cls.model.select().join(UserTenant, on=(UserTenant.tenant_id == Knowledgebase.tenant_id)
                                       ).where(cls.model.name == kb_name, UserTenant.user_id == user_id).paginate(0, 1)
         kbs = kbs.dicts()
diff --git a/api/db/services/pipeline_operation_log_service.py b/api/db/services/pipeline_operation_log_service.py
index c3c333665..9b344d006 100644
--- a/api/db/services/pipeline_operation_log_service.py
+++ b/api/db/services/pipeline_operation_log_service.py
@@ -121,7 +121,7 @@ class PipelineOperationLogService(CommonService):
         else:
             ok, kb_info = KnowledgebaseService.get_by_id(document.kb_id)
             if not ok:
-                raise RuntimeError(f"Cannot find knowledge base {document.kb_id} for referred_document {referred_document_id}")
+                raise RuntimeError(f"Cannot find dataset {document.kb_id} for referred_document {referred_document_id}")
 
             tenant_id = kb_info.tenant_id
             title = document.parser_id
diff --git a/api/db/services/task_service.py b/api/db/services/task_service.py
index d9b6d29ed..065d2376d 100644
--- a/api/db/services/task_service.py
+++ b/api/db/services/task_service.py
@@ -76,7 +76,7 @@ class TaskService(CommonService):
         """Retrieve detailed task information by task ID.
 
         This method fetches comprehensive task details including associated document,
-        knowledge base, and tenant information. It also handles task retry logic and
+        dataset, and tenant information. It also handles task retry logic and
         progress updates.
 
         Args:
diff --git a/docs/guides/chat/set_chat_variables.md b/docs/guides/chat/set_chat_variables.md
index 89e786262..00f1a58c7 100644
--- a/docs/guides/chat/set_chat_variables.md
+++ b/docs/guides/chat/set_chat_variables.md
@@ -51,9 +51,9 @@ Your answers should follow a professional and {style} style.
 
 ...
 
-Here is the dataset:
+Here is the knowledge base:
 {knowledge}
-The above is the dataset.
+The above is the knowledge base.
 ```
 
 :::tip NOTE
diff --git a/docs/references/http_api_reference.md b/docs/references/http_api_reference.md
index 69f842b23..ec3b265a8 100644
--- a/docs/references/http_api_reference.md
+++ b/docs/references/http_api_reference.md
@@ -5355,6 +5355,6 @@ or
 ```json
 {
     "code": 404,
-    "message": "Can't find this knowledgebase!"
+    "message": "Can't find this dataset!"
 }
 ```
diff --git a/rag/benchmark.py b/rag/benchmark.py
index 05de7d788..100fc32d5 100644
--- a/rag/benchmark.py
+++ b/rag/benchmark.py
@@ -283,7 +283,7 @@ if __name__ == '__main__':
     print('*****************RAGFlow Benchmark*****************')
     parser = argparse.ArgumentParser(usage="benchmark.py <max_docs> <kb_id> <dataset> <dataset_path> [<miracl_corpus_path>])", description='RAGFlow Benchmark')
     parser.add_argument('max_docs', metavar='max_docs', type=int, help='max docs to evaluate')
-    parser.add_argument('kb_id', metavar='kb_id', help='knowledgebase id')
+    parser.add_argument('kb_id', metavar='kb_id', help='dataset id')
     parser.add_argument('dataset', metavar='dataset', help='dataset name, shall be one of ms_marco_v1.1(https://huggingface.co/datasets/microsoft/ms_marco), trivia_qa(https://huggingface.co/datasets/mandarjoshi/trivia_qa>), miracl(https://huggingface.co/datasets/miracl/miracl')
     parser.add_argument('dataset_path', metavar='dataset_path', help='dataset path')
     parser.add_argument('miracl_corpus_path', metavar='miracl_corpus_path', nargs='?', default="", help='miracl corpus path. Only needed when dataset is miracl')
diff --git a/rag/svr/task_executor.py b/rag/svr/task_executor.py
index 1a0c51600..70406244d 100644
--- a/rag/svr/task_executor.py
+++ b/rag/svr/task_executor.py
@@ -888,7 +888,7 @@ async def do_handle_task(task):
     if task_type == "raptor":
         ok, kb = KnowledgebaseService.get_by_id(task_dataset_id)
         if not ok:
-            progress_callback(prog=-1.0, msg="Cannot found valid knowledgebase for RAPTOR task")
+            progress_callback(prog=-1.0, msg="Cannot found valid dataset for RAPTOR task")
             return
 
         kb_parser_config = kb.parser_config
@@ -940,7 +940,7 @@ async def do_handle_task(task):
     elif task_type == "graphrag":
         ok, kb = KnowledgebaseService.get_by_id(task_dataset_id)
         if not ok:
-            progress_callback(prog=-1.0, msg="Cannot found valid knowledgebase for GraphRAG task")
+            progress_callback(prog=-1.0, msg="Cannot found valid dataset for GraphRAG task")
             return
 
         kb_parser_config = kb.parser_config
diff --git a/rag/utils/infinity_conn.py b/rag/utils/infinity_conn.py
index 8297323e2..1ac2f7b33 100644
--- a/rag/utils/infinity_conn.py
+++ b/rag/utils/infinity_conn.py
@@ -521,7 +521,7 @@ class InfinityConnection(DocStoreConnection):
             try:
                 table_instance = db_instance.get_table(table_name)
             except Exception:
-                logger.warning(f"Table not found: {table_name}, this knowledge base isn't created in Infinity. Maybe it is created in other document engine.")
+                logger.warning(f"Table not found: {table_name}, this dataset isn't created in Infinity. Maybe it is created in other document engine.")
                 continue
             kb_res, _ = table_instance.output(["*"]).filter(f"id = '{chunkId}'").to_df()
             logger.debug(f"INFINITY get table: {str(table_list)}, result: {str(kb_res)}")
diff --git a/sdk/python/test/test_http_api/test_chat_assistant_management/test_create_chat_assistant.py b/sdk/python/test/test_http_api/test_chat_assistant_management/test_create_chat_assistant.py
index 1255762b5..741339744 100644
--- a/sdk/python/test/test_http_api/test_chat_assistant_management/test_create_chat_assistant.py
+++ b/sdk/python/test/test_http_api/test_chat_assistant_management/test_create_chat_assistant.py
@@ -225,7 +225,7 @@ class TestChatAssistantCreate:
                 assert res["data"]["prompt"]["show_quote"] is True
                 assert (
                     res["data"]["prompt"]["prompt"]
-                    == 'You are an intelligent assistant. Please summarize the content of the knowledge base to answer the question. Please list the data in the knowledge base and answer in detail. When all knowledge base content is irrelevant to the question, your answer must include the sentence "The answer you are looking for is not found in the knowledge base!" Answers need to consider chat history.\n      Here is the knowledge base:\n      {knowledge}\n      The above is the knowledge base.'
+                    == 'You are an intelligent assistant. Please summarize the content of the dataset to answer the question. Please list the data in the dataset and answer in detail. When all dataset content is irrelevant to the question, your answer must include the sentence "The answer you are looking for is not found in the dataset!" Answers need to consider chat history.\n      Here is the knowledge base:\n      {knowledge}\n      The above is the knowledge base.'
                 )
         else:
             assert res["message"] == expected_message
diff --git a/sdk/python/test/test_http_api/test_chat_assistant_management/test_update_chat_assistant.py b/sdk/python/test/test_http_api/test_chat_assistant_management/test_update_chat_assistant.py
index e22862eb5..8da986503 100644
--- a/sdk/python/test/test_http_api/test_chat_assistant_management/test_update_chat_assistant.py
+++ b/sdk/python/test/test_http_api/test_chat_assistant_management/test_update_chat_assistant.py
@@ -222,7 +222,7 @@ class TestChatAssistantUpdate:
                 assert res["data"]["prompt"][0]["show_quote"] is True
                 assert (
                     res["data"]["prompt"][0]["prompt"]
-                    == 'You are an intelligent assistant. Please summarize the content of the knowledge base to answer the question. Please list the data in the knowledge base and answer in detail. When all knowledge base content is irrelevant to the question, your answer must include the sentence "The answer you are looking for is not found in the knowledge base!" Answers need to consider chat history.\n      Here is the knowledge base:\n      {knowledge}\n      The above is the knowledge base.'
+                    == 'You are an intelligent assistant. Please summarize the content of the dataset to answer the question. Please list the data in the dataset and answer in detail. When all dataset content is irrelevant to the question, your answer must include the sentence "The answer you are looking for is not found in the dataset!" Answers need to consider chat history.\n      Here is the knowledge base:\n      {knowledge}\n      The above is the knowledge base.'
                 )
         else:
             assert expected_message in res["message"]
diff --git a/test/testcases/test_http_api/test_chat_assistant_management/test_create_chat_assistant.py b/test/testcases/test_http_api/test_chat_assistant_management/test_create_chat_assistant.py
index 5e0591bc0..7a588722c 100644
--- a/test/testcases/test_http_api/test_chat_assistant_management/test_create_chat_assistant.py
+++ b/test/testcases/test_http_api/test_chat_assistant_management/test_create_chat_assistant.py
@@ -226,7 +226,7 @@ class TestChatAssistantCreate:
                 assert res["data"]["prompt"]["show_quote"] is True
                 assert (
                     res["data"]["prompt"]["prompt"]
-                    == 'You are an intelligent assistant. Please summarize the content of the knowledge base to answer the question. Please list the data in the knowledge base and answer in detail. When all knowledge base content is irrelevant to the question, your answer must include the sentence "The answer you are looking for is not found in the knowledge base!" Answers need to consider chat history.\n      Here is the knowledge base:\n      {knowledge}\n      The above is the knowledge base.'
+                    == 'You are an intelligent assistant. Please summarize the content of the dataset to answer the question. Please list the data in the dataset and answer in detail. When all dataset content is irrelevant to the question, your answer must include the sentence "The answer you are looking for is not found in the dataset!" Answers need to consider chat history.\n      Here is the knowledge base:\n      {knowledge}\n      The above is the knowledge base.'
                 )
         else:
             assert res["message"] == expected_message
diff --git a/test/testcases/test_http_api/test_chat_assistant_management/test_update_chat_assistant.py b/test/testcases/test_http_api/test_chat_assistant_management/test_update_chat_assistant.py
index 08f31f413..e17b7c089 100644
--- a/test/testcases/test_http_api/test_chat_assistant_management/test_update_chat_assistant.py
+++ b/test/testcases/test_http_api/test_chat_assistant_management/test_update_chat_assistant.py
@@ -223,7 +223,7 @@ class TestChatAssistantUpdate:
                 assert res["data"]["prompt"][0]["show_quote"] is True
                 assert (
                     res["data"]["prompt"][0]["prompt"]
-                    == 'You are an intelligent assistant. Please summarize the content of the knowledge base to answer the question. Please list the data in the knowledge base and answer in detail. When all knowledge base content is irrelevant to the question, your answer must include the sentence "The answer you are looking for is not found in the knowledge base!" Answers need to consider chat history.\n      Here is the knowledge base:\n      {knowledge}\n      The above is the knowledge base.'
+                    == 'You are an intelligent assistant. Please summarize the content of the dataset to answer the question. Please list the data in the dataset and answer in detail. When all dataset content is irrelevant to the question, your answer must include the sentence "The answer you are looking for is not found in the dataset!" Answers need to consider chat history.\n      Here is the knowledge base:\n      {knowledge}\n      The above is the knowledge base.'
                 )
         else:
             assert expected_message in res["message"]
diff --git a/test/testcases/test_sdk_api/test_chat_assistant_management/test_create_chat_assistant.py b/test/testcases/test_sdk_api/test_chat_assistant_management/test_create_chat_assistant.py
index 033b66d3b..1214bcc41 100644
--- a/test/testcases/test_sdk_api/test_chat_assistant_management/test_create_chat_assistant.py
+++ b/test/testcases/test_sdk_api/test_chat_assistant_management/test_create_chat_assistant.py
@@ -211,7 +211,7 @@ class TestChatAssistantCreate:
                 assert attrgetter("show_quote")(chat_assistant.prompt) is True
                 assert (
                     attrgetter("prompt")(chat_assistant.prompt)
-                    == 'You are an intelligent assistant. Please summarize the content of the knowledge base to answer the question. Please list the data in the knowledge base and answer in detail. When all knowledge base content is irrelevant to the question, your answer must include the sentence "The answer you are looking for is not found in the knowledge base!" Answers need to consider chat history.\n      Here is the knowledge base:\n      {knowledge}\n      The above is the knowledge base.'
+                    == 'You are an intelligent assistant. Please summarize the content of the dataset to answer the question. Please list the data in the dataset and answer in detail. When all dataset content is irrelevant to the question, your answer must include the sentence "The answer you are looking for is not found in the dataset!" Answers need to consider chat history.\n      Here is the knowledge base:\n      {knowledge}\n      The above is the knowledge base.'
                 )
 
 
diff --git a/test/testcases/test_sdk_api/test_chat_assistant_management/test_update_chat_assistant.py b/test/testcases/test_sdk_api/test_chat_assistant_management/test_update_chat_assistant.py
index 4f55de8d7..bae5bb6bf 100644
--- a/test/testcases/test_sdk_api/test_chat_assistant_management/test_update_chat_assistant.py
+++ b/test/testcases/test_sdk_api/test_chat_assistant_management/test_update_chat_assistant.py
@@ -202,7 +202,7 @@ class TestChatAssistantUpdate:
                         "empty_response": "Sorry! No relevant content was found in the knowledge base!",
                         "opener": "Hi! I'm your assistant. What can I do for you?",
                         "show_quote": True,
-                        "prompt": 'You are an intelligent assistant. Please summarize the content of the knowledge base to answer the question. Please list the data in the knowledge base and answer in detail. When all knowledge base content is irrelevant to the question, your answer must include the sentence "The answer you are looking for is not found in the knowledge base!" Answers need to consider chat history.\n      Here is the knowledge base:\n      {knowledge}\n      The above is the knowledge base.',
+                        "prompt": 'You are an intelligent assistant. Please summarize the content of the dataset to answer the question. Please list the data in the dataset and answer in detail. When all dataset content is irrelevant to the question, your answer must include the sentence "The answer you are looking for is not found in the dataset!" Answers need to consider chat history.\n      Here is the knowledge base:\n      {knowledge}\n      The above is the knowledge base.',
                     },
                 )
                 assert str(updated_chat.prompt) == str(excepted_value), str(updated_chat)
diff --git a/test/testcases/test_web_api/test_dialog_app/test_dialog_edge_cases.py b/test/testcases/test_web_api/test_dialog_app/test_dialog_edge_cases.py
index 9536a1e35..bbbc00d65 100644
--- a/test/testcases/test_web_api/test_dialog_app/test_dialog_edge_cases.py
+++ b/test/testcases/test_web_api/test_dialog_app/test_dialog_edge_cases.py
@@ -21,7 +21,7 @@ from common import create_dialog, delete_dialog, get_dialog, update_dialog
 class TestDialogEdgeCases:
     @pytest.mark.p2
     def test_create_dialog_with_tavily_api_key(self, WebApiAuth):
-        """Test creating dialog with Tavily API key instead of knowledge base"""
+        """Test creating dialog with Tavily API key instead of dataset"""
         payload = {
             "name": "tavily_dialog",
             "prompt_config": {"system": "You are a helpful assistant. Use this knowledge: {knowledge}", "parameters": [{"key": "knowledge", "optional": True}], "tavily_api_key": "test_tavily_key"},
diff --git a/test/testcases/test_web_api/test_document_app/test_create_document.py b/test/testcases/test_web_api/test_document_app/test_create_document.py
index ba31bd4f2..df804487b 100644
--- a/test/testcases/test_web_api/test_document_app/test_create_document.py
+++ b/test/testcases/test_web_api/test_document_app/test_create_document.py
@@ -60,7 +60,7 @@ class TestDocumentCreate:
     def test_invalid_kb_id(self, WebApiAuth):
         res = create_document(WebApiAuth, {"name": "ragflow_test.txt", "kb_id": "invalid_kb_id"})
         assert res["code"] == 102, res
-        assert res["message"] == "Can't find this knowledgebase!", res
+        assert res["message"] == "Can't find this dataset!", res
 
     @pytest.mark.p3
     def test_filename_special_characters(self, WebApiAuth, add_dataset_func):
diff --git a/test/testcases/test_web_api/test_document_app/test_list_documents.py b/test/testcases/test_web_api/test_document_app/test_list_documents.py
index ce973fd33..885a0e9d0 100644
--- a/test/testcases/test_web_api/test_document_app/test_list_documents.py
+++ b/test/testcases/test_web_api/test_document_app/test_list_documents.py
@@ -51,7 +51,7 @@ class TestDocumentsList:
         "kb_id, expected_code, expected_message",
         [
             ("", 101, 'Lack of "KB ID"'),
-            ("invalid_dataset_id", 103, "Only owner of knowledgebase authorized for this operation."),
+            ("invalid_dataset_id", 103, "Only owner of dataset authorized for this operation."),
         ],
     )
     def test_invalid_dataset_id(self, WebApiAuth, kb_id, expected_code, expected_message):
diff --git a/test/testcases/test_web_api/test_document_app/test_upload_documents.py b/test/testcases/test_web_api/test_document_app/test_upload_documents.py
index b2b36d570..f7880cea5 100644
--- a/test/testcases/test_web_api/test_document_app/test_upload_documents.py
+++ b/test/testcases/test_web_api/test_document_app/test_upload_documents.py
@@ -136,7 +136,7 @@ class TestDocumentsUpload:
         fp = create_txt_file(tmp_path / "ragflow_test.txt")
         res = upload_documents(WebApiAuth, {"kb_id": "invalid_kb_id"}, [fp])
         assert res["code"] == 100, res
-        assert res["message"] == """LookupError("Can't find this knowledgebase!")""", res
+        assert res["message"] == """LookupError("Can't find this dataset!")""", res
 
     @pytest.mark.p2
     def test_duplicate_files(self, WebApiAuth, add_dataset_func, tmp_path):
diff --git a/test/testcases/test_web_api/test_kb_app/test_detail_kb.py b/test/testcases/test_web_api/test_kb_app/test_detail_kb.py
index a3c0f82b1..bb895d923 100644
--- a/test/testcases/test_web_api/test_kb_app/test_detail_kb.py
+++ b/test/testcases/test_web_api/test_kb_app/test_detail_kb.py
@@ -50,4 +50,4 @@ class TestDatasetsDetail:
         payload = {"kb_id": "d94a8dc02c9711f0930f7fbc369eab6d"}
         res = detail_kb(WebApiAuth, payload)
         assert res["code"] == 103, res
-        assert "Only owner of knowledgebase authorized for this operation." in res["message"], res
+        assert "Only owner of dataset authorized for this operation." in res["message"], res
diff --git a/test/testcases/test_web_api/test_kb_app/test_update_kb.py b/test/testcases/test_web_api/test_kb_app/test_update_kb.py
index 6b4fea84a..3afdb630b 100644
--- a/test/testcases/test_web_api/test_kb_app/test_update_kb.py
+++ b/test/testcases/test_web_api/test_kb_app/test_update_kb.py
@@ -111,7 +111,7 @@ class TestDatasetUpdate:
         payload = {"name": name, "description": "", "parser_id": "naive", "kb_id": kb_id}
         res = update_kb(WebApiAuth, payload)
         assert res["code"] == 102, res
-        assert res["message"] == "Duplicated knowledgebase name.", res
+        assert res["message"] == "Duplicated dataset name.", res
 
     @pytest.mark.p3
     def test_name_case_insensitive(self, WebApiAuth, add_datasets_func):
@@ -120,7 +120,7 @@ class TestDatasetUpdate:
         payload = {"name": name, "description": "", "parser_id": "naive", "kb_id": kb_id}
         res = update_kb(WebApiAuth, payload)
         assert res["code"] == 102, res
-        assert res["message"] == "Duplicated knowledgebase name.", res
+        assert res["message"] == "Duplicated dataset name.", res
 
     @pytest.mark.p2
     def test_avatar(self, WebApiAuth, add_dataset_func, tmp_path):
diff --git a/web/src/locales/en.ts b/web/src/locales/en.ts
index 8750fe8a0..88bfc3da5 100644
--- a/web/src/locales/en.ts
+++ b/web/src/locales/en.ts
@@ -939,7 +939,7 @@ Example: Virtual Hosted Style`,
         'The default VLM for each newly created knowledge base. It describes a picture or video. If you cannot find a model from the dropdown, check https://ragflow.io/docs/dev/supported_models to see if your model provider supports this model.',
       sequence2txtModel: 'ASR',
       sequence2txtModelTip:
-        'The default ASR model for each newly created knowledgebase. Use this model to translate voices to corresponding text.',
+        'The default ASR model for each newly created dataset. Use this model to translate voices to corresponding text.',
       rerankModel: 'Rerank',
       rerankModelTip: `The default rerank model for reranking chunks. If you cannot find a model from the dropdown, check https://ragflow.io/docs/dev/supported_models to see if your model provider supports this model.`,
       ttsModel: 'TTS',