mirror of
https://github.com/microsoft/SkillOpt.git
synced 2026-07-04 06:29:56 +08:00
244e346b83
- Skill optimization framework with training loop analogy - 11 benchmarks, 4 model backends (Azure OpenAI, Claude, Codex, Qwen) - WebUI for browser-based training control - Pluggable architecture for extending benchmarks and backends
5 lines
224 B
Python
5 lines
224 B
Python
"""ReflACT utilities — JSON extraction, scoring, hashing."""
|
|
|
|
from skillopt.utils.json_utils import extract_json, extract_json_array # noqa: F401
|
|
from skillopt.utils.scoring import compute_score, skill_hash # noqa: F401
|