feat(data-process): 支持单项生成五十条数据

backend/app/modules/data_process/algorithms.py

@@ -34,6 +34,8 @@ from openpyxl.utils.cell import range_boundaries
 from pptx import Presentation
 from pypdf import PdfReader
 
+from app.modules.data_process.constants import MAX_QA_PAIRS_PER_ITEM
+
 TextFormat = Literal[
     "json",
     "jsonl",
@@ -2659,8 +2661,10 @@ def generate_standard_records(
     LLM 响应解析后的统一落库步骤。
     """
 
-    if not 1 <= qa_pairs_per_item <= 5:
-        raise ValueError("qa_pairs_per_item must be in [1, 5]")
+    if not 1 <= qa_pairs_per_item <= MAX_QA_PAIRS_PER_ITEM:
+        raise ValueError(
+            f"qa_pairs_per_item must be in [1, {MAX_QA_PAIRS_PER_ITEM}]"
+        )
     prefixes = (
         "请结合实际情况说明：",
         "请用通俗易懂的方式说明：",
@@ -2677,7 +2681,13 @@ def generate_standard_records(
             variant_instruction = instruction
             if variant_index:
                 if semantic_enrichment:
-                    variant_instruction = f"{prefixes[variant_index]}{instruction}"
+                    prefix = prefixes[variant_index % len(prefixes)]
+                    if variant_index >= len(prefixes):
+                        prefix = (
+                            f"{prefix.removesuffix('：')}"
+                            f"（问法 {variant_index + 1}）："
+                        )
+                    variant_instruction = f"{prefix}{instruction}"
                 else:
                     variant_instruction = f"{instruction}(问法 {variant_index + 1})"
             raw_id = f"{preview_id}:{variant_index + 1}"