63 lines
1.7 KiB
Python
63 lines
1.7 KiB
Python
#!/usr/bin/env python3
|
||
"""Report PixelRAG VLM route/model readiness."""
|
||
|
||
from __future__ import annotations
|
||
|
||
import argparse
|
||
import json
|
||
import sys
|
||
from pathlib import Path
|
||
|
||
|
||
ROOT = Path(__file__).resolve().parents[2]
|
||
if str(ROOT) not in sys.path:
|
||
sys.path.insert(0, str(ROOT))
|
||
|
||
from services.pixelrag_vlm_route_readiness_service import ( # noqa: E402
|
||
build_pixelrag_vlm_route_readiness,
|
||
)
|
||
|
||
|
||
def main() -> int:
|
||
parser = argparse.ArgumentParser(
|
||
description="讀回 PixelRAG VLM approved Ollama route / model readiness。"
|
||
)
|
||
parser.add_argument("--model", help="要檢查的 configured VLM model。")
|
||
parser.add_argument(
|
||
"--timeout",
|
||
type=int,
|
||
default=3,
|
||
help="/api/tags probe timeout 秒數。",
|
||
)
|
||
parser.add_argument(
|
||
"--include-models",
|
||
action="store_true",
|
||
help="輸出每個 host 的 model list。",
|
||
)
|
||
parser.add_argument(
|
||
"--probe-generate",
|
||
action="store_true",
|
||
help="執行極小 /api/generate preflight；預設不呼叫模型。",
|
||
)
|
||
parser.add_argument(
|
||
"--probe-timeout",
|
||
type=int,
|
||
default=8,
|
||
help="/api/generate preflight timeout 秒數。",
|
||
)
|
||
args = parser.parse_args()
|
||
|
||
payload = build_pixelrag_vlm_route_readiness(
|
||
model=args.model,
|
||
timeout_seconds=args.timeout,
|
||
include_models=args.include_models,
|
||
probe_generate=args.probe_generate,
|
||
probe_timeout_seconds=args.probe_timeout,
|
||
)
|
||
print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
|
||
return 0 if payload.get("success") else 1
|
||
|
||
|
||
if __name__ == "__main__":
|
||
raise SystemExit(main())
|