fix(data-process): 发布精确三路数据切分

This commit is contained in:
caoxiaozhu
2026-07-24 20:43:47 +08:00
parent e6a5a36bc0
commit 9cb77c251a
8 changed files with 405 additions and 181 deletions

View File

@@ -534,6 +534,12 @@ async def _sync_training_dataset_to_compute_node(
files = store.training_dataset_files(dataset_id)
if not files:
raise RuntimeError(f"dataset has no uploaded file: {dataset_id}")
split_aware = any(item.get("split") for item in files)
files = [
item
for item in files
if not split_aware or item.get("split") in {"train", "validation"}
]
client = ComputeNodeClient(node["api_base_url"])
results: list[dict[str, Any]] = []
for item in files:
@@ -1533,4 +1539,3 @@ async def log_content(file: str = Query(...)) -> dict[str, Any]:
@router.post("/web-log")
async def web_log(payload: dict[str, Any] = Body(...)) -> dict[str, Any]:
return ok({"received": True, **payload})