feat: Sync collection (#3368)

* feat: sync collection

* feat: sync collection

* perf: website selector

* update doc

packages/web/i18n/en/dataset.json

@@ -3,6 +3,8 @@
   "add_file": "Import",
   "api_file": "API Dataset",
   "api_url": "API Url",
+  "chunk_max_tokens": "max_tokens",
+  "close_auto_sync": "Are you sure you want to turn off automatic sync?",
   "collection.Create update time": "Creation/Update Time",
   "collection.Training type": "Training",
   "collection_not_support_retraining": "This collection type does not support retuning parameters",
@@ -12,6 +14,7 @@
   "collection_tags": "Collection Tags",
   "common_dataset": "General Dataset",
   "common_dataset_desc": "Build a Dataset by importing files, web links, or manual input.",
+  "config_sync_schedule": "Configure scheduled synchronization",
   "confirm_to_rebuild_embedding_tip": "Are you sure you want to switch the index for the Dataset?\nSwitching the index is a significant operation that requires re-indexing all data in your Dataset, which may take a long time. Please ensure your account has sufficient remaining points.\n\nAdditionally, you need to update the applications that use this Dataset to avoid conflicts with other indexed model Datasets.",
   "core.dataset.import.Adjust parameters": "Adjust parameters",
   "custom_data_process_params": "Custom",
@@ -36,7 +39,9 @@
   "ideal_chunk_length_tips": "Segment according to the end symbol and combine multiple segments into one block. This value determines the estimated size of the block, if there is any fluctuation.",
   "import.Auto mode Estimated Price Tips": "The text understanding model needs to be called, which requires more points: {{price}} points/1K tokens",
   "import.Embedding Estimated Price Tips": "Only use the index model and consume a small amount of AI points: {{price}} points/1K tokens",
+  "is_open_schedule": "Enable scheduled synchronization",
   "move.hint": "After moving, the selected knowledge base/folder will inherit the permission settings of the new folder, and the original permission settings will become invalid.",
+  "open_auto_sync": "After scheduled synchronization is turned on, the system will try to synchronize the collection from time to time every day. During the collection synchronization period, the collection data will not be searched.",
   "permission.des.manage": "Can manage the entire knowledge base data and information",
   "permission.des.read": "View knowledge base content",
   "permission.des.write": "Ability to add and change knowledge base content",
@@ -47,6 +52,9 @@
   "retrain_task_submitted": "The retraining task has been submitted",
   "same_api_collection": "The same API set exists",
   "start_sync_website_tip": "Confirm to start synchronizing data? \nThe old data will be deleted and retrieved again, please confirm!",
+  "sync_collection_failed": "Synchronization collection error, please check whether the source file can be accessed normally",
+  "sync_schedule": "Timing synchronization",
+  "sync_schedule_tip": "Only existing collections will be synchronized. \nIncludes linked collections and all collections in the API knowledge base. \nThe system will poll for updates every day, and the specific update time cannot be determined.",
   "tag.Add New": "Add New",
   "tag.Add_new_tag": "Add New Tag",
   "tag.Edit_tag": "Edit Tag",
@@ -59,6 +67,7 @@
   "tag.total_tags": "Total {{total}} tags",
   "the_knowledge_base_has_indexes_that_are_being_trained_or_being_rebuilt": "The Dataset has indexes that are being trained or rebuilt",
   "training_mode": "Chunk mode",
+  "vector_model_max_tokens_tip": "Each chunk of data has a maximum length of 3000 tokens",
   "website_dataset": "Website Sync",
   "website_dataset_desc": "Website sync allows you to build a Dataset directly using a web link."
 }