50 lines
1.6 KiB
YAML
50 lines
1.6 KiB
YAML
# ============================================================
|
||
# 多专业小模型 + 路由模型系统 — 配置
|
||
# 默认全 mock 模式（零依赖、离线可跑）。要接入真实模型，把对应
|
||
# 后端 type 改为 hf / api 即可（见 README）。
|
||
# ============================================================
|
||
|
||
system:
|
||
name: multi-expert-router
|
||
version: 0.1.0
|
||
|
||
router:
|
||
low_confidence_threshold: 0.60 # 分类置信度低于此值 -> 直接走大模型
|
||
judge_fallback_threshold: 0.70 # Judge 质量分低于此值 -> 升级大模型
|
||
default_temperature: 0.2
|
||
|
||
classifier:
|
||
type: rule # rule（零依赖）| hf（transformers）
|
||
model: Qwen/Qwen3-0.6B
|
||
confidence_floor: 0.55
|
||
|
||
domains:
|
||
- code
|
||
- math
|
||
- legal
|
||
- medical
|
||
- general
|
||
|
||
experts:
|
||
code: { type: mock, model: Qwen/Qwen2.5-Coder-7B-Instruct }
|
||
math: { type: mock, model: Qwen/Qwen3-4B-Instruct }
|
||
legal: { type: mock, model: Qwen/Qwen3-4B-Instruct }
|
||
medical: { type: mock, model: Qwen/Qwen3-4B-Instruct }
|
||
general: { type: mock, model: Qwen/Qwen3-1.7B-Instruct }
|
||
|
||
fallback:
|
||
type: mock # mock | api（OpenAI 兼容，如 DeepSeek）
|
||
model: deepseek-chat
|
||
base_url: https://api.deepseek.com/v1
|
||
api_key_env: DEEPSEEK_API_KEY
|
||
|
||
judge:
|
||
type: rule # rule（零依赖）| llm
|
||
model: Qwen/Qwen3-1.7B-Instruct
|
||
|
||
cache:
|
||
enabled: true
|
||
semantic_enabled: true # 语义缓存（字符 n-gram 相似度，零依赖）
|
||
similarity_threshold: 0.88
|
||
promote_frequency: 5 # 命中 N 次后提升为精确缓存
|
||
|