Adapter de benchmark isole (hors runtime Lea) ciblant un serveur /v1/chat/completions a support vision (vLLM/SGLang/TGI), pour comparer plus tard a Ollama via LeaBench. Ne controle jamais le desktop. - core/evaluation/openai_compat_lea_bench_adapter.py : payload data-URL image_url, parsing choices[0].message.content. Reutilise par import la logique prompt/parse/normalisation de ollama_lea_bench_adapter (zero refactor). - tools/lea_bench_openai_compat.py : wrapper CLI (--base-url defaut :8001). - tests/unit/test_openai_compat_lea_bench_adapter.py : 6 tests mockes HTTP (data URL, pas de fuite expectation/click_region, prediction valide, abstain safe sur HTTP!=200 et reponse malformee, JSONL rechargeable). Aucun runtime Lea modifie. Aucun service lance. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
16 lines
371 B
Python
16 lines
371 B
Python
#!/usr/bin/env python3
|
|
"""CLI wrapper for the OpenAI-compatible LeaBench adapter (benchmark only)."""
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
if str(ROOT) not in sys.path:
|
|
sys.path.insert(0, str(ROOT))
|
|
|
|
from core.evaluation.openai_compat_lea_bench_adapter import main
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|