Folzo
2a9f721c4e
Architecture (voir docs/ARCHITECTURE-LITELLM.md):
open-webui -> LiteLLM:4000
|- qwen3.6-27b -> jean-proxy:3012 -> Jean (.11:8080)
|- llama3.1-8b -> wol-proxy:3011 -> Ollama (.11:11434)
Nouveaux fichiers:
- wol-proxy/ (versionne l'app.py de prod deja en place)
- jean-proxy/ (clone du wol-proxy avec HEALTH_PATH=/health + retry post-WoL
pour services qui mettent du temps a demarrer apres WoL, ex: Jean qui
charge 14 Go en VRAM)
- litellm/config.yaml (routing par nom de modele, drop_params=true)
- docker-compose.litellm.yml (override ADDITIF: ajoute uniquement jean-proxy
et litellm, ne redemarre PAS open-webui/wol-proxy/hermes)
Teste en prod sur .27: Jean + Ollama repondent via LiteLLM:4000 avec
path-through de chat_template_kwargs.enable_thinking (raisonnement Qwen3.6
desactivable par requete). Zero impact hermes-webui/wol-proxy.
Basculer open-webui reste une etape manuelle (step 3 de la doc).
99 lines
3.3 KiB
Python
99 lines
3.3 KiB
Python
import os
|
|
import time
|
|
import socket
|
|
import logging
|
|
from urllib.parse import urljoin
|
|
|
|
import requests
|
|
from flask import Flask, request, Response
|
|
|
|
TARGET_HOST = os.getenv("TARGET_HOST", "192.168.1.10")
|
|
TARGET_PORT = int(os.getenv("TARGET_PORT", "11434"))
|
|
TARGET_MAC = os.getenv("TARGET_MAC", "02:76:C6:01:48:C8")
|
|
LISTEN_PORT = int(os.getenv("LISTEN_PORT", "3010"))
|
|
WAKE_TIMEOUT = int(os.getenv("WAKE_TIMEOUT", "60"))
|
|
CHECK_INTERVAL = int(os.getenv("CHECK_INTERVAL", "5"))
|
|
BROADCAST_IP = os.getenv("BROADCAST_IP", "192.168.1.255") # ← broadcast dirigé
|
|
|
|
logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s")
|
|
log = logging.getLogger(__name__)
|
|
|
|
app = Flask(__name__)
|
|
|
|
def send_wol(mac_address: str):
|
|
mac = mac_address.replace(":", "").replace("-", "")
|
|
if len(mac) != 12:
|
|
raise ValueError("MAC invalide: %s" % mac_address)
|
|
data = bytes.fromhex("FF" * 6 + mac * 16)
|
|
# Envoyer 3 paquets pour fiabilité
|
|
with socket.socket(socket.AF_INET, socket.SOCK_DGRAM) as s:
|
|
s.setsockopt(socket.SOL_SOCKET, socket.SO_BROADCAST, 1)
|
|
for i in range(3):
|
|
s.sendto(data, (BROADCAST_IP, 9))
|
|
log.info(f"[WoL] Paquet magic #{i+1} envoyé → MAC={mac_address} via {BROADCAST_IP}:9")
|
|
|
|
def ollama_alive() -> bool:
|
|
try:
|
|
url = f"http://{TARGET_HOST}:{TARGET_PORT}/api/version"
|
|
r = requests.get(url, timeout=2)
|
|
return r.ok
|
|
except Exception:
|
|
return False
|
|
|
|
def wait_for_ollama():
|
|
if ollama_alive():
|
|
log.info("[WoL] Ollama déjà UP, skip WoL")
|
|
return
|
|
log.info(f"[WoL] Ollama DOWN → envoi WoL vers {TARGET_MAC}")
|
|
send_wol(TARGET_MAC)
|
|
deadline = time.time() + WAKE_TIMEOUT
|
|
while time.time() < deadline:
|
|
remaining = int(deadline - time.time())
|
|
if ollama_alive():
|
|
log.info(f"[WoL] Ollama UP après réveil (reste {remaining}s)")
|
|
return
|
|
log.info(f"[WoL] En attente d'Ollama... ({remaining}s restantes)")
|
|
time.sleep(CHECK_INTERVAL)
|
|
raise RuntimeError("Ollama ne répond pas après WoL")
|
|
|
|
def proxy_request(path: str):
|
|
wait_for_ollama()
|
|
base = f"http://{TARGET_HOST}:{TARGET_PORT}"
|
|
upstream_url = urljoin(base + "/", path)
|
|
headers = dict(request.headers)
|
|
headers.pop("Host", None)
|
|
try:
|
|
resp = requests.request(
|
|
method=request.method,
|
|
url=upstream_url,
|
|
headers=headers,
|
|
data=request.get_data(),
|
|
cookies=request.cookies,
|
|
allow_redirects=False,
|
|
stream=True,
|
|
timeout=60,
|
|
)
|
|
except Exception as e:
|
|
return Response(str(e), status=502)
|
|
|
|
excluded = {"content-encoding", "content-length", "transfer-encoding", "connection"}
|
|
response_headers = [
|
|
(name, value)
|
|
for name, value in resp.headers.items()
|
|
if name.lower() not in excluded
|
|
]
|
|
return Response(
|
|
resp.raw,
|
|
status=resp.status_code,
|
|
headers=response_headers,
|
|
direct_passthrough=True,
|
|
)
|
|
|
|
@app.route("/", defaults={"path": ""}, methods=["GET", "POST", "PUT", "DELETE", "PATCH", "OPTIONS"])
|
|
@app.route("/<path:path>", methods=["GET", "POST", "PUT", "DELETE", "PATCH", "OPTIONS"])
|
|
def handle(path):
|
|
return proxy_request(path)
|
|
|
|
if __name__ == "__main__":
|
|
app.run(host="0.0.0.0", port=LISTEN_PORT)
|