chore: save local changes

backend/app/models/schemas.py

@@ -1,7 +1,10 @@
 from pydantic import BaseModel
-from typing import Optional, List, Dict
+from typing import Optional, List, Dict, Literal
 from enum import Enum
 
+# Language type for prompts
+LanguageType = Literal["zh", "en"]
+
 
 class AttributeNode(BaseModel):
     name: str
@@ -47,16 +50,19 @@ class CausalChain(BaseModel):
 
 
 class StreamAnalyzeRequest(BaseModel):
-    """多步驟分析請求（更新為支持動態類別）"""
+    """Multi-step analysis request (updated to support dynamic categories)"""
     query: str
     model: Optional[str] = None
     temperature: Optional[float] = 0.7
-    chain_count: int = 5  # 用戶可設定要生成多少條因果鏈
+    chain_count: int = 5  # User can set how many causal chains to generate
 
-    # 新增：動態類別支持
-    category_mode: Optional[str] = "dynamic_auto"  # CategoryMode enum 值
+    # Dynamic category support
+    category_mode: Optional[str] = "dynamic_auto"  # CategoryMode enum value
     custom_categories: Optional[List[str]] = None
-    suggested_category_count: int = 3  # 建議 LLM 生成的類別數量
+    suggested_category_count: int = 3  # Suggest LLM to generate this many categories
+
+    # Language setting
+    lang: LanguageType = "zh"
 
 
 class StreamAnalyzeResponse(BaseModel):
@@ -136,13 +142,14 @@ class DAGRelationship(BaseModel):
 # ===== Transformation Agent schemas =====
 
 class TransformationRequest(BaseModel):
-    """Transformation Agent 請求"""
-    query: str                        # 原始查詢 (e.g., "腳踏車")
-    category: str                     # 類別名稱 (e.g., "功能")
-    attributes: List[str]             # 該類別的屬性列表
+    """Transformation Agent request"""
+    query: str                        # Original query (e.g., "bicycle")
+    category: str                     # Category name (e.g., "Functions")
+    attributes: List[str]             # Attribute list for this category
     model: Optional[str] = None
     temperature: Optional[float] = 0.7
-    keyword_count: int = 3            # 要生成的新關鍵字數量
+    keyword_count: int = 3            # Number of new keywords to generate
+    lang: LanguageType = "zh"         # Language for prompts
 
 
 class TransformationDescription(BaseModel):
@@ -215,24 +222,27 @@ class ExpertSource(str, Enum):
 
 
 class ExpertTransformationRequest(BaseModel):
-    """Expert Transformation Agent 請求"""
+    """Expert Transformation Agent request"""
     query: str
     category: str
     attributes: List[str]
 
     # Expert parameters
-    expert_count: int = 3                        # 專家數量 (2-8)
-    keywords_per_expert: int = 1                 # 每個專家為每個屬性生成幾個關鍵字 (1-3)
-    custom_experts: Optional[List[str]] = None   # 用戶指定專家 ["藥師", "工程師"]
+    expert_count: int = 3                        # Number of experts (2-8)
+    keywords_per_expert: int = 1                 # Keywords per expert per attribute (1-3)
+    custom_experts: Optional[List[str]] = None   # User-specified experts
 
     # Expert source parameters
-    expert_source: ExpertSource = ExpertSource.LLM  # 專家來源
-    expert_language: str = "en"                     # 外部來源的語言 (目前只有英文資料)
+    expert_source: ExpertSource = ExpertSource.LLM  # Expert source
+    expert_language: str = "en"                     # Language for external sources
 
     # LLM parameters
     model: Optional[str] = None
     temperature: Optional[float] = 0.7
 
+    # Prompt language
+    lang: LanguageType = "zh"
+
 
 # ===== Deduplication Agent schemas =====
 
@@ -243,11 +253,12 @@ class DeduplicationMethod(str, Enum):
 
 
 class DeduplicationRequest(BaseModel):
-    """去重請求"""
+    """Deduplication request"""
     descriptions: List[ExpertTransformationDescription]
-    method: DeduplicationMethod = DeduplicationMethod.EMBEDDING  # 去重方法
-    similarity_threshold: float = 0.85  # 餘弦相似度閾值 (0.0-1.0)，僅 Embedding 使用
-    model: Optional[str] = None  # Embedding/LLM 模型
+    method: DeduplicationMethod = DeduplicationMethod.EMBEDDING  # Deduplication method
+    similarity_threshold: float = 0.85  # Cosine similarity threshold (0.0-1.0), only for Embedding
+    model: Optional[str] = None  # Embedding/LLM model
+    lang: LanguageType = "zh"  # Prompt language (for LLM method)
 
 
 class DescriptionGroup(BaseModel):