kplam
51dc8dc4f6
- FastAPI + Qdrant + Redis + Ollama 技术栈 - L1→L2→L3→chunk 四层分层检索（dense + sparse RRF 融合） - 文档三级总结与 2.5 级回退 - query 解析路由与分类 - /admin 管理页面
61 lines
2.1 KiB
Python
61 lines
2.1 KiB
Python
from pydantic_settings import BaseSettings
|
||
|
||
|
||
class Settings(BaseSettings):
|
||
"""应用配置，通过环境变量注入"""
|
||
|
||
# 应用
|
||
app_name: str = "QMDSearch"
|
||
log_level: str = "info"
|
||
|
||
# 嵌入模型
|
||
embedding_provider: str = "openai" # openai | local
|
||
openai_api_key: str = ""
|
||
openai_base_url: str = "https://api.openai.com/v1"
|
||
embedding_model: str = "text-embedding-3-small"
|
||
embedding_dimension: int = 1536
|
||
|
||
# Ollama 本地模型（用于文档三级总结）
|
||
ollama_base_url: str = "http://localhost:11434"
|
||
ollama_model: str = "qwen2.5:1.5b" # 备选: qwen2.5:3b
|
||
ollama_embedding_model: str = "bge-m3" # embedding_provider=local 时使用的嵌入模型
|
||
|
||
# Qdrant
|
||
qdrant_host: str = "localhost"
|
||
qdrant_port: int = 6333
|
||
|
||
# Redis
|
||
redis_url: str = "redis://localhost:6379/0"
|
||
|
||
# 检索参数
|
||
retrieval_top_k: int = 20 # L2 语义检索召回数
|
||
retrieval_final_k: int = 5 # L3 重排后返回数
|
||
|
||
# 文档入库参数
|
||
summary_min_text_length: int = 500 # 低于此字符数触发 2.5 级回退
|
||
|
||
# 入库异步任务
|
||
ingest_max_concurrency: int = 2 # 入库后台任务并发上限
|
||
ingest_task_ttl_done: int = 86400 # 任务状态 Redis 保留秒数（进行中与已完成，24h）
|
||
ingest_task_ttl_failed: int = 604800 # 失败任务状态 Redis 保留秒数（7 天）
|
||
|
||
# 知识分类（taxonomy）
|
||
taxonomy_path: str = "" # taxonomy JSON 文件路径，为空用内置默认
|
||
classify_confidence_threshold: float = 0.6 # 低于此值归 uncategorized
|
||
classify_max_categories: int = 3 # query 路由命中类目数上限，超过走全库兜底
|
||
|
||
# 分层检索参数
|
||
l1_doc_top_n: int = 10 # L1 层候选文档数
|
||
l2_section_top_n: int = 5 # L2 层候选 section 数
|
||
l3_top_n: int = 10 # L3 层定位数
|
||
sparse_enabled: bool = True # 是否启用稀疏检索
|
||
cache_ttl: int = 300 # Redis 缓存秒数
|
||
|
||
# 分块参数
|
||
chunk_max_chars: int = 800 # chunk 超长二次切分阈值
|
||
|
||
model_config = {"env_prefix": "", "case_sensitive": False}
|
||
|
||
|
||
settings = Settings()
|