wiki_crawler/backend/schemas/schemas.py

from pydantic import BaseModel
from typing import Optional, List, Any


class RegisterRequest(BaseModel):
    url: str

class PendingRequest(BaseModel):
    task_id: int
    limit: Optional[int] = 10

class AddUrlsRequest(BaseModel):
    task_id: int
    urls_obj: dict

# schemas.py
class CrawlResult(BaseModel):
    source_url: str
    chunk_index: int  # 新增字段
    title: Optional[str] = None
    content: Optional[str] = None
    embedding: Optional[List[float]] = None

class SaveResultsRequest(BaseModel):
    task_id: int
    results: List[CrawlResult]

class SearchRequest(BaseModel):
    # 如果不传 task_id，则进行全库搜索
    task_id: Optional[int] = None
    query_embedding: dict
    limit: Optional[int] = 5




# ... (保留原有的 Schema: RegisterRequest, AddUrlsRequest 等) ...

# === V2 New Schemas ===
class AutoMapRequest(BaseModel):
    url: str

class AutoProcessRequest(BaseModel):
    task_id: int
    batch_size: Optional[int] = 5

class TextSearchRequest(BaseModel):
    query: str  # 用户直接传文字，不需要传向量了
    task_id: Optional[int] = None
    limit: Optional[int] = 5