5cc306eb0a
后端: - 抽取 fetch_eval_result_content 复用函数，model_eval_detail 直接应用评测任务结果 - health 接口移除数据库依赖，返回静态指标 - 数据集: count_dataset_records JSON 感知计数; 文件统计改为从 dataset_files 聚合重算; 在线编辑记录 size/record_count/version_no; 上传同步批处理 - 算力节点: 调度支持 requested GPU 子集校验与容量计算; 新增 delete_compute_node(含活动任务保护)及 DELETE 接口; 连接池 connect_timeout - 评测任务落库 basic_metrics/score/completed_time, failed/stopped 记录 error 评测引擎: - _load_dataset 支持 JSON/JSONL 文件 - 新增 exact match 与文本相似度指标, 余弦相似度去掉 2 样本限制 前端: - 算力节点列表「维护」改为「删除」(带确认弹窗), compute.ts 新增 deleteComputeNode - 数据集上传超时调整为 120s; FineTuneTask 增加 compute_node_id; GpuInfo 状态增加 reserved
219 lines
9.3 KiB
Python
219 lines
9.3 KiB
Python
from __future__ import annotations
|
|
|
|
import time
|
|
from typing import Any
|
|
from urllib.parse import urljoin
|
|
|
|
import httpx
|
|
|
|
from app.core.config import get_settings
|
|
|
|
|
|
def _join_url(base_url: str, path: str) -> str:
|
|
return urljoin(base_url.rstrip("/") + "/", path.lstrip("/"))
|
|
|
|
|
|
def _unwrap_items(payload: Any) -> list[dict[str, Any]]:
|
|
if isinstance(payload, list):
|
|
return [item for item in payload if isinstance(item, dict)]
|
|
if isinstance(payload, dict):
|
|
data = payload.get("data")
|
|
if isinstance(data, dict) and isinstance(data.get("items"), list):
|
|
return [item for item in data["items"] if isinstance(item, dict)]
|
|
if isinstance(payload.get("items"), list):
|
|
return [item for item in payload["items"] if isinstance(item, dict)]
|
|
if isinstance(data, list):
|
|
return [item for item in data if isinstance(item, dict)]
|
|
return []
|
|
|
|
|
|
def _unwrap_dict(payload: Any) -> dict[str, Any]:
|
|
if isinstance(payload, dict) and isinstance(payload.get("data"), dict):
|
|
return payload["data"]
|
|
return payload if isinstance(payload, dict) else {}
|
|
|
|
|
|
class ComputeNodeClient:
|
|
"""Application-side client for one compute node.
|
|
|
|
The client accepts both current YG Compute API responses and common
|
|
wrapper shapes such as `{code,message,data}` to make future engine/node
|
|
adapters less brittle.
|
|
"""
|
|
|
|
def __init__(self, api_base_url: str, token: str | None = None, timeout: float | None = None) -> None:
|
|
settings = get_settings()
|
|
self.api_base_url = api_base_url.rstrip("/")
|
|
self.token = token or settings.compute_service_token
|
|
self.timeout = timeout or settings.compute_request_timeout_seconds
|
|
self.route_prefix = settings.route_prefix.rstrip("/") or "/modelTF"
|
|
|
|
def headers(self) -> dict[str, str]:
|
|
if not self.token:
|
|
return {}
|
|
return {"X-Compute-Token": self.token}
|
|
|
|
async def test_connection(self) -> dict[str, Any]:
|
|
started = time.perf_counter()
|
|
health = await self.health()
|
|
gpus = await self.gpus()
|
|
return {
|
|
"success": True,
|
|
"latency_ms": int((time.perf_counter() - started) * 1000),
|
|
"health": health,
|
|
"gpus": gpus,
|
|
}
|
|
|
|
async def health(self) -> dict[str, Any]:
|
|
paths = [f"{self.route_prefix}/v1/compute/health", f"{self.route_prefix}/health", "/health"]
|
|
last_error = ""
|
|
async with httpx.AsyncClient(timeout=self.timeout, headers=self.headers()) as client:
|
|
for path in paths:
|
|
try:
|
|
response = await client.get(_join_url(self.api_base_url, path))
|
|
response.raise_for_status()
|
|
return _unwrap_dict(response.json())
|
|
except Exception as exc: # noqa: BLE001 - keep endpoint compatibility fallback broad
|
|
last_error = str(exc)
|
|
raise RuntimeError(last_error or "compute health check failed")
|
|
|
|
async def gpus(self) -> list[dict[str, Any]]:
|
|
paths = [
|
|
f"{self.route_prefix}/compute/resources/gpus",
|
|
f"{self.route_prefix}/v1/compute/resources/gpus",
|
|
"/compute/resources/gpus",
|
|
]
|
|
last_error = ""
|
|
async with httpx.AsyncClient(timeout=self.timeout, headers=self.headers()) as client:
|
|
for path in paths:
|
|
try:
|
|
response = await client.get(_join_url(self.api_base_url, path))
|
|
response.raise_for_status()
|
|
return _unwrap_items(response.json())
|
|
except Exception as exc: # noqa: BLE001
|
|
last_error = str(exc)
|
|
raise RuntimeError(last_error or "compute gpu discovery failed")
|
|
|
|
async def create_job(self, payload: dict[str, Any]) -> dict[str, Any]:
|
|
async with httpx.AsyncClient(timeout=self.timeout, headers=self.headers()) as client:
|
|
response = await client.post(_join_url(self.api_base_url, f"{self.route_prefix}/compute/jobs"), json=payload)
|
|
response.raise_for_status()
|
|
return _unwrap_dict(response.json())
|
|
|
|
async def preview_job(self, payload: dict[str, Any]) -> dict[str, Any]:
|
|
async with httpx.AsyncClient(timeout=self.timeout, headers=self.headers()) as client:
|
|
response = await client.post(
|
|
_join_url(self.api_base_url, f"{self.route_prefix}/compute/jobs/preview"),
|
|
json=payload,
|
|
)
|
|
response.raise_for_status()
|
|
return _unwrap_dict(response.json())
|
|
|
|
async def validate_job(self, payload: dict[str, Any]) -> dict[str, Any]:
|
|
async with httpx.AsyncClient(timeout=self.timeout, headers=self.headers()) as client:
|
|
response = await client.post(
|
|
_join_url(self.api_base_url, f"{self.route_prefix}/compute/jobs/validate"),
|
|
json=payload,
|
|
)
|
|
response.raise_for_status()
|
|
return _unwrap_dict(response.json())
|
|
|
|
async def check_paths(self, paths: list[dict[str, Any]]) -> dict[str, Any]:
|
|
async with httpx.AsyncClient(timeout=self.timeout, headers=self.headers()) as client:
|
|
response = await client.post(
|
|
_join_url(self.api_base_url, f"{self.route_prefix}/compute/files/check-paths"),
|
|
json={"paths": paths},
|
|
)
|
|
response.raise_for_status()
|
|
return _unwrap_dict(response.json())
|
|
|
|
async def list_files(
|
|
self,
|
|
root: str = "data",
|
|
relative_path: str = "",
|
|
directories_only: bool = False,
|
|
) -> dict[str, Any]:
|
|
async with httpx.AsyncClient(timeout=self.timeout, headers=self.headers()) as client:
|
|
response = await client.get(
|
|
_join_url(self.api_base_url, f"{self.route_prefix}/compute/files/list"),
|
|
params={"root": root, "relative_path": relative_path, "directories_only": directories_only},
|
|
)
|
|
response.raise_for_status()
|
|
return _unwrap_dict(response.json())
|
|
|
|
async def get_job(self, job_id: str) -> dict[str, Any]:
|
|
async with httpx.AsyncClient(timeout=self.timeout, headers=self.headers()) as client:
|
|
response = await client.get(_join_url(self.api_base_url, f"{self.route_prefix}/compute/jobs/{job_id}"))
|
|
response.raise_for_status()
|
|
return _unwrap_dict(response.json())
|
|
|
|
async def stop_job(self, job_id: str) -> dict[str, Any]:
|
|
async with httpx.AsyncClient(timeout=self.timeout, headers=self.headers()) as client:
|
|
response = await client.post(_join_url(self.api_base_url, f"{self.route_prefix}/compute/jobs/{job_id}/stop"))
|
|
response.raise_for_status()
|
|
return _unwrap_dict(response.json())
|
|
|
|
async def job_logs(
|
|
self,
|
|
job_id: str,
|
|
tail_lines: int | None = None,
|
|
offset: int | None = None,
|
|
limit: int | None = None,
|
|
) -> dict[str, Any]:
|
|
params = {
|
|
key: value
|
|
for key, value in {"tail_lines": tail_lines, "offset": offset, "limit": limit}.items()
|
|
if value is not None
|
|
}
|
|
async with httpx.AsyncClient(timeout=self.timeout, headers=self.headers()) as client:
|
|
response = await client.get(
|
|
_join_url(self.api_base_url, f"{self.route_prefix}/compute/jobs/{job_id}/logs"),
|
|
params=params,
|
|
)
|
|
response.raise_for_status()
|
|
return _unwrap_dict(response.json())
|
|
|
|
async def import_local_file(self, payload: dict[str, Any]) -> dict[str, Any]:
|
|
async with httpx.AsyncClient(timeout=self.timeout, headers=self.headers()) as client:
|
|
response = await client.post(
|
|
_join_url(self.api_base_url, f"{self.route_prefix}/compute/files/import-local"),
|
|
json=payload,
|
|
)
|
|
response.raise_for_status()
|
|
return _unwrap_dict(response.json())
|
|
|
|
async def _request(self, method: str, path: str, json_data: dict[str, Any] | None = None) -> dict[str, Any]:
|
|
"""Generic request method for compute API endpoints."""
|
|
url = _join_url(self.api_base_url, f"{self.route_prefix}{path}")
|
|
async with httpx.AsyncClient(timeout=300, headers=self.headers()) as client:
|
|
if method.upper() == "GET":
|
|
response = await client.get(url)
|
|
else:
|
|
response = await client.post(url, json=json_data)
|
|
response.raise_for_status()
|
|
return _unwrap_dict(response.json())
|
|
|
|
async def upload_file(
|
|
self,
|
|
filename: str,
|
|
content: bytes,
|
|
target_relative_path: str,
|
|
resource_type: str | None = None,
|
|
resource_id: str | None = None,
|
|
) -> dict[str, Any]:
|
|
data = {
|
|
"target_relative_path": target_relative_path,
|
|
"resource_type": resource_type or "",
|
|
"resource_id": resource_id or "",
|
|
}
|
|
files = {"file": (filename, content)}
|
|
timeout = httpx.Timeout(max(self.timeout, 60), connect=self.timeout)
|
|
async with httpx.AsyncClient(timeout=timeout, headers=self.headers()) as client:
|
|
response = await client.post(
|
|
_join_url(self.api_base_url, f"{self.route_prefix}/compute/files/upload"),
|
|
data=data,
|
|
files=files,
|
|
)
|
|
response.raise_for_status()
|
|
return _unwrap_dict(response.json())
|