0ce879aa44
- Implemented HTML pages for datasets, models, training, testing, and results. - Created API endpoints for managing repositories, results, tests, and training sessions. - Added functionality for streaming training progress via Server-Sent Events (SSE). - Introduced a Dockerfile for the ML runner with necessary dependencies. - Developed an SDK for user code execution within the runner container. - Enhanced CSS styles for improved UI layout and navigation. - Established a layout template for consistent HTML structure across pages. - Added JavaScript for dynamic interactions on the models page. - Implemented WebSocket handling for real-time communication with kiosk devices and controllers. - Implemented model registration and management API at /api/models - Added Gitea proxy API for repository interactions at /api/repos - Created results API for listing and comparing training results at /api/results - Developed training management API for enqueueing and retrieving training jobs at /api/trainings - Introduced SSE endpoint for live training progress updates - Added HTML pages for models, datasets, and training management - Created a Dockerfile for the ML runner with necessary dependencies - Developed SDK for user code execution within the runner container - Enhanced CSS styles for improved UI/UX - Implemented WebSocket communication for real-time device and controller interactions in the kiosk system
76 lines
2.3 KiB
Python
76 lines
2.3 KiB
Python
"""Client InfluxDB (influxdb-client sync wrapper in thread-pool per async).
|
|
|
|
Le scritture usano il batching async dell'SDK invece di SYNCHRONOUS.
|
|
Le metriche di training arrivano in burst (logs container, stats loop ogni 5s):
|
|
con SYNCHRONOUS ogni write era una HTTP request bloccante. Con WriteOptions
|
|
batched, l'SDK accumula i Point e fa flush periodico in background, senza
|
|
perdere durabilità (flush forzato a fine training).
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
from typing import Iterable, Optional
|
|
|
|
from influxdb_client import InfluxDBClient, Point, WriteOptions
|
|
|
|
from core.config import settings
|
|
|
|
_client: Optional[InfluxDBClient] = None
|
|
_write_api = None
|
|
|
|
|
|
def client() -> InfluxDBClient:
|
|
global _client, _write_api
|
|
if _client is None:
|
|
_client = InfluxDBClient(
|
|
url=settings.influx_url, token=settings.influx_token, org=settings.influx_org
|
|
)
|
|
_write_api = _client.write_api(write_options=WriteOptions(
|
|
batch_size=200,
|
|
flush_interval=2_000,
|
|
jitter_interval=200,
|
|
retry_interval=2_000,
|
|
max_retries=3,
|
|
))
|
|
return _client
|
|
|
|
|
|
def _wa():
|
|
client()
|
|
return _write_api
|
|
|
|
|
|
async def write_points(points: Iterable[Point]) -> None:
|
|
wa = _wa()
|
|
pts = list(points)
|
|
await asyncio.to_thread(wa.write, settings.influx_bucket, settings.influx_org, pts)
|
|
|
|
|
|
async def flush() -> None:
|
|
"""Forza il flush del buffer batched. Da chiamare a fine training per
|
|
garantire che tutte le metriche raccolte siano persistite."""
|
|
if _write_api is None:
|
|
return
|
|
try:
|
|
await asyncio.to_thread(_write_api.flush)
|
|
except Exception:
|
|
pass
|
|
|
|
|
|
async def query_flux(flux: str) -> list[dict]:
|
|
c = client()
|
|
def _q():
|
|
tables = c.query_api().query(flux, org=settings.influx_org)
|
|
out = []
|
|
for table in tables:
|
|
for r in table.records:
|
|
out.append({
|
|
"time": r.get_time().isoformat() if r.get_time() else None,
|
|
"measurement": r.get_measurement(),
|
|
"field": r.get_field(),
|
|
"value": r.get_value(),
|
|
"tags": {k: v for k, v in r.values.items() if k.startswith("_") is False and k not in ("result", "table")},
|
|
})
|
|
return out
|
|
return await asyncio.to_thread(_q)
|