KucLab commited on
Commit
701ff74
·
verified ·
1 Parent(s): fcfd26c

Add serve.py

Browse files
Files changed (1) hide show
  1. serve.py +115 -0
serve.py ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """Batch classification API for the Barist.1 Hub bundle (stdlib only, no FastAPI).
2
+
3
+ python serve.py --port 8000 # serves the local HF bundle dir (run from the bundle root)
4
+ CENSER_DIR=/path/to/bundle python scripts/serve.py
5
+
6
+ Endpoints:
7
+ GET /health -> {"status": "ok", "model": ...}
8
+ POST /classify -> {"texts": [...]} => {"results": [{label, unsafe, score, categories, chunks}]}
9
+ POST /classify-one -> {"text": "..."} => single result
10
+
11
+ Features: batching, long-input chunking (chunk_tokens/stride), token-bucket
12
+ rate limit (env RATE_LIMIT_PER_MIN, default 600), max body size guard.
13
+
14
+ python serve.py --dir bundle --port 8000
15
+ """
16
+
17
+ from __future__ import annotations
18
+
19
+ import argparse
20
+ import json
21
+ import os
22
+ import time
23
+ from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
24
+ from pathlib import Path
25
+
26
+ MAX_BODY = 2 * 1024 * 1024 # 2 MB
27
+
28
+
29
+ class RateLimiter:
30
+ def __init__(self, per_min: float) -> None:
31
+ self.per_min = per_min
32
+ self.tokens = per_min
33
+ self.updated = time.monotonic()
34
+ self.last_deny = 0.0
35
+
36
+ def allow(self, cost: float = 1.0) -> bool:
37
+ now = time.monotonic()
38
+ self.tokens = min(self.per_min, self.tokens + (now - self.updated) * self.per_min / 60.0)
39
+ self.updated = now
40
+ if self.tokens >= cost:
41
+ self.tokens -= cost
42
+ return True
43
+ return False
44
+
45
+
46
+ def make_handler(pipe, limiter: RateLimiter, model_name: str):
47
+ class Handler(BaseHTTPRequestHandler):
48
+ def _json(self, code: int, payload: dict) -> None:
49
+ body = json.dumps(payload, ensure_ascii=False).encode("utf-8")
50
+ self.send_response(code)
51
+ self.send_header("Content-Type", "application/json; charset=utf-8")
52
+ self.send_header("Content-Length", str(len(body)))
53
+ self.end_headers()
54
+ self.wfile.write(body)
55
+
56
+ def log_message(self, fmt, *args): # quiet
57
+ pass
58
+
59
+ def do_GET(self):
60
+ if self.path == "/health":
61
+ self._json(200, {"status": "ok", "model": model_name, "device": str(pipe.device)})
62
+ else:
63
+ self._json(404, {"error": "not found"})
64
+
65
+ def do_POST(self):
66
+ if not limiter.allow():
67
+ self._json(429, {"error": "rate limit exceeded"})
68
+ return
69
+ length = int(self.headers.get("Content-Length") or 0)
70
+ if length > MAX_BODY:
71
+ self._json(413, {"error": "body too large"})
72
+ return
73
+ try:
74
+ payload = json.loads(self.rfile.read(length) or b"{}")
75
+ except Exception:
76
+ self._json(400, {"error": "invalid json"})
77
+ return
78
+ if self.path == "/classify-one":
79
+ text = str(payload.get("text", ""))
80
+ self._json(200, pipe.predict(text))
81
+ elif self.path == "/classify":
82
+ texts = payload.get("texts")
83
+ if not isinstance(texts, list) or not texts or len(texts) > 256:
84
+ self._json(400, {"error": "texts must be a list of 1..256 strings"})
85
+ return
86
+ self._json(200, {"results": pipe.predict_batch([str(t) for t in texts])})
87
+ else:
88
+ self._json(404, {"error": "not found"})
89
+
90
+ return Handler
91
+
92
+
93
+ def main() -> None:
94
+ parser = argparse.ArgumentParser()
95
+ parser.add_argument("--dir", default=os.environ.get("CENSER_DIR", "bundle"))
96
+ parser.add_argument("--port", type=int, default=8000)
97
+ parser.add_argument("--host", default="0.0.0.0")
98
+ parser.add_argument("--device", default=None)
99
+ args = parser.parse_args()
100
+
101
+ import sys
102
+
103
+ sys.path.insert(0, str(Path(__file__).resolve().parent))
104
+ from censer import CenserPipeline
105
+
106
+ pipe = CenserPipeline(args.dir, device=args.device)
107
+ limiter = RateLimiter(float(os.environ.get("RATE_LIMIT_PER_MIN", "600")))
108
+ server = ThreadingHTTPServer((args.host, args.port), make_handler(pipe, limiter, args.dir))
109
+ print(f"censer serve: model={args.dir} device={pipe.device} on http://{args.host}:{args.port}")
110
+ print(" POST /classify {\"texts\": [...]} POST /classify-one {\"text\": ...} GET /health")
111
+ server.serve_forever()
112
+
113
+
114
+ if __name__ == "__main__":
115
+ main()