feat(ai): add PixelRAG VLM generate preflight

This commit is contained in:
ogt
2026-07-10 00:17:02 +08:00
parent d1ca067054
commit bed3a8a8ee
11 changed files with 384 additions and 14 deletions

View File

@@ -34,12 +34,25 @@ def main() -> int:
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

View File

@@ -87,6 +87,17 @@ def main() -> int:
default=3,
help="auto-select model 的 /api/tags readiness timeout 秒數。",
)
parser.add_argument(
"--no-probe-generate-before-execute",
action="store_true",
help="停用 execute 前的極小 /api/generate preflight。",
)
parser.add_argument(
"--route-generate-probe-timeout",
type=int,
default=8,
help="execute 前 /api/generate preflight timeout 秒數。",
)
args = parser.parse_args()
payload = run_pixelrag_ollama_vlm_replay_worker(
@@ -102,6 +113,8 @@ def main() -> int:
write_receipt=bool(args.write_receipt and args.execute),
auto_select_model=not args.no_auto_select_model,
route_readiness_timeout=args.route_readiness_timeout,
probe_generate_before_execute=not args.no_probe_generate_before_execute,
route_generate_probe_timeout=args.route_generate_probe_timeout,
)
print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True))
return 0 if payload.get("success") else 1