Spaces:
Sleeping
Sleeping
File size: 4,211 Bytes
31db1d3 5f3209c 31db1d3 0af3440 5f3209c 0af3440 6e356be 31db1d3 0af3440 31db1d3 8dc65ba d102640 31db1d3 8dc65ba 31db1d3 8dc65ba 31db1d3 8dc65ba 31db1d3 8dc65ba 31db1d3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | from flask import Flask, request, Response, jsonify
import requests
import threading
import time
import random
import logging
from typing import Optional
app = Flask(__name__)
# =========================
# CONFIG
# =========================
Server = [
"https://Techbitforge-hello_server.hf.space"
]
HF_SERVERS = [
"https://techbitforge-ollamaserver.hf.space/"
]
PING_INTERVAL = 7200
REQUEST_TIMEOUT = 300
# =========================
# LOGGING
# =========================
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s — %(levelname)s — %(message)s"
)
logger = logging.getLogger("proxy")
def pick_server() -> str:
return random.choice(HF_SERVERS)
def error_response(message: str, code: int = 500):
logger.error(message)
return jsonify({
"error": {
"message": message,
"type": "proxy_error"
}
}), code
# =========================
# CHAT COMPLETIONS PROXY
# =========================
@app.route("/v1/chat/completions", methods=["POST"])
def chat_completions():
try:
payload = request.get_json(force=True)
except Exception:
return error_response("Invalid JSON payload", 400)
headers = dict(request.headers)
headers.pop("Host", None)
target = pick_server() + "/v1/chat/completions"
stream = payload.get("stream", False)
logger.info(f"Forwarding request to {target} | Stream={stream}")
try:
if stream:
def generate():
with requests.post(
target,
json=payload,
headers=headers,
stream=True,
timeout=REQUEST_TIMEOUT
) as res:
res.raise_for_status()
for line in res.iter_lines():
if line:
yield line + b"\n\n"
return Response(
generate(),
mimetype="text/event-stream",
headers={"Cache-Control": "no-cache", "X-Accel-Buffering": "no"}
)
res = requests.post(
target,
json=payload,
headers=headers,
timeout=REQUEST_TIMEOUT
)
res.raise_for_status()
return jsonify(res.json())
except requests.exceptions.Timeout:
return error_response("Upstream server timeout", 504)
except requests.exceptions.ConnectionError:
return error_response("Failed to connect to upstream server", 502)
except Exception as e:
return error_response(str(e), 500)
# =========================
# MODELS ROUTE
# =========================
@app.route("/models", methods=["GET"])
def models():
url = pick_server()
target = f"{url}/models"
logger.info(f"Fetching models from {target}")
try:
res = requests.get(target, timeout=20)
res.raise_for_status()
return jsonify(res.json())
except Exception as e:
return error_response(f"Failed to fetch models: {e}", 500)
# =========================
# HEALTH CHECK
# =========================
@app.route("/", methods=["GET"])
def home():
return jsonify({"status": "running", "service": "HF Proxy"})
import requests
import threading
import time
PING_INTERVAL = 3600 # 24 hours
def keep_alive_worker():
url = "https://techbitforge-server.hf.space/"
while True:
try:
response = requests.get(url, timeout=120)
if response.status_code == 200:
print("Success: server is alive")
else:
print(f"Server returned status code: {response.status_code}")
except requests.RequestException as e:
print(f"Ping failed: {e}")
# Wait 24 hours before the next ping
time.sleep(PING_INTERVAL)
def start_background_thread():
thread = threading.Thread(
target=keep_alive_worker,
daemon=True
)
thread.start()
# =========================
# MAIN
# =========================
if __name__ == "__main__":
start_background_thread()
app.run(
host="0.0.0.0",
port=7860,
threaded=True,
debug=False
)
|