feat(dataset): 添加PDF文本提取功能支持

- 新增dataset模块路由配置
- 添加PdfTextExtractRequest和PdfTextExtractResponse数据传输对象
- 实现PDF文本提取接口，支持从PDF文件中提取文本内容
- 集成数据库会话管理和异步处理能力

runtime/datamate-python/app/module/__init__.py

@@ -6,6 +6,7 @@ from .ratio.interface import router as ratio_router
 from .generation.interface import router as generation_router
 from .evaluation.interface import router as evaluation_router
 from .collection.interface import router as collection_route
+from .dataset.interface import router as dataset_router
 
 router = APIRouter(
     prefix="/api"
@@ -17,5 +18,6 @@ router.include_router(ratio_router)
 router.include_router(generation_router)
 router.include_router(evaluation_router)
 router.include_router(collection_route)
+router.include_router(dataset_router)
 
 __all__ = ["router"]

runtime/datamate-python/app/module/dataset/interface/pdf_extract.py

@@ -0,0 +1,22 @@
+from fastapi import APIRouter, Depends
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.db.session import get_db
+from app.module.dataset.schema.pdf_extract import PdfTextExtractRequest, PdfTextExtractResponse
+from app.module.dataset.service.pdf_extract import PdfTextExtractService
+from app.module.shared.schema.common import StandardResponse
+
+router = APIRouter(
+    prefix="",
+    tags=["dataset"],
+)
+
+
+@router.post("/pdf-text-extract", response_model=StandardResponse[PdfTextExtractResponse])
+async def extract_pdf_text(
+    request: PdfTextExtractRequest,
+    db: AsyncSession = Depends(get_db),
+):
+    service = PdfTextExtractService(db)
+    result = await service.extract_pdf_to_text(request.dataset_id, request.file_id)
+    return StandardResponse(code=200, message="Success", data=result)