feat(data-process): 接入三种文档切分引擎

backend/app/schemas/data_process.py

@@ -13,23 +13,26 @@ def _config_value(config: dict[str, Any], snake_name: str, camel_name: str, defa
 
 
 def _validate_process_config(config: dict[str, Any]) -> None:
-    chunk_method = _config_value(config, "chunk_method", "chunkMethod", "structure")
+    chunk_method = _config_value(config, "chunk_method", "chunkMethod", "layout_hybrid")
     if not isinstance(chunk_method, str) or chunk_method not in {
-        "structure",
+        "layout_hybrid",
+        "semantic",
         "fixed",
-        "custom",
     }:
-        raise ValueError("chunk_method must be one of: structure, fixed, custom")
-    custom_delimiter = _config_value(
+        raise ValueError("chunk_method must be one of: layout_hybrid, semantic, fixed")
+
+    semantic_percentile = _config_value(
         config,
-        "custom_delimiter",
-        "customDelimiter",
-        "",
+        "semantic_breakpoint_percentile",
+        "semanticBreakpointPercentile",
+        95,
     )
-    if chunk_method == "custom" and (
-        not isinstance(custom_delimiter, str) or not custom_delimiter
+    if (
+        isinstance(semantic_percentile, bool)
+        or not isinstance(semantic_percentile, int)
+        or not 1 <= semantic_percentile <= 99
     ):
-        raise ValueError("custom_delimiter is required for custom chunking")
+        raise ValueError("semantic_breakpoint_percentile must be an integer in [1, 99]")
 
     split = _config_value(config, "dataset_split", "datasetSplit", None)
     if split is not None: