162 lines
6.4 KiB
Python
162 lines
6.4 KiB
Python
"""Centralized configuration via Pydantic Settings.
|
|
|
|
All env vars are loaded from .env once at import time and validated.
|
|
Import the singleton `settings` everywhere — never read os.environ directly.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from enum import Enum
|
|
from functools import lru_cache
|
|
from pathlib import Path
|
|
|
|
from pydantic import Field, HttpUrl, field_validator
|
|
from pydantic_settings import BaseSettings, SettingsConfigDict
|
|
|
|
|
|
class LlmRole(str, Enum):
|
|
"""Logical role a caller asks for. Routing decides which model serves it."""
|
|
|
|
REASONING = "reasoning" # critical: extraction, NLI, verdict, wiki
|
|
FAST = "fast" # mass processing (currently disabled)
|
|
VISION = "vision" # multimodal (currently disabled)
|
|
|
|
|
|
class Settings(BaseSettings):
|
|
"""Top-level config. Validated at startup, immutable thereafter."""
|
|
|
|
model_config = SettingsConfigDict(
|
|
env_file=Path(__file__).parent.parent / ".env",
|
|
env_file_encoding="utf-8",
|
|
extra="ignore",
|
|
)
|
|
|
|
# ---- LLM router ---------------------------------------------------------
|
|
llm_router_url: str = Field(default="http://localhost:14011")
|
|
llm_router_api_key: str = Field(default="")
|
|
llm_vllm_url: str = Field(default="http://localhost:14001")
|
|
llm_llamacpp_urls: str = Field(default="") # comma-separated
|
|
|
|
# ---- Models -------------------------------------------------------------
|
|
model_reasoning: str = Field(default="Qwen3.5-397B-A17B")
|
|
model_reasoning_backend: str = Field(default="llamacpp")
|
|
|
|
model_fast: str = Field(default="qwen3.5")
|
|
model_fast_backend: str = Field(default="vllm")
|
|
model_fast_enabled: bool = Field(default=False)
|
|
|
|
model_vision: str = Field(default="gemma-3-27b-it")
|
|
model_vision_url: str = Field(default="")
|
|
model_vision_enabled: bool = Field(default=False)
|
|
|
|
# ---- Embeddings ---------------------------------------------------------
|
|
embedding_url: str = Field(default="http://10.11.10.15:8200")
|
|
embedding_api_key: str = Field(default="")
|
|
embedding_model: str = Field(default="BAAI/bge-m3")
|
|
embedding_dim: int = Field(default=1024)
|
|
embedding_max_tokens: int = Field(default=8192)
|
|
|
|
# ---- Reranker -----------------------------------------------------------
|
|
reranker_url: str = Field(default="http://10.11.10.15:8100")
|
|
reranker_api_key: str = Field(default="")
|
|
reranker_model: str = Field(default="BAAI/bge-reranker-v2-m3")
|
|
|
|
# ---- Atomic -------------------------------------------------------------
|
|
atomic_url: str = Field(default="http://localhost:8080")
|
|
atomic_token: str = Field(default="")
|
|
|
|
# ---- Postgres -----------------------------------------------------------
|
|
postgres_user: str = Field(default="atomic")
|
|
postgres_password: str = Field(default="atomic_dev_changeme")
|
|
postgres_db: str = Field(default="atomic")
|
|
postgres_port: int = Field(default=5434)
|
|
postgres_host: str = Field(
|
|
default="postgres",
|
|
description="Hostname for direct PG connection (Docker: 'postgres', host: 'localhost')",
|
|
)
|
|
postgres_internal_port: int = Field(
|
|
default=5432,
|
|
description="Port inside the Docker network (external is postgres_port)",
|
|
)
|
|
|
|
# ---- Verification cache --------------------------------------------------
|
|
verification_cache_ttl_days: int = Field(
|
|
default=30,
|
|
description="How long cached verification entries live before auto-expiry",
|
|
)
|
|
verification_cache_max_payload_kb: int = Field(
|
|
default=64,
|
|
description="Reject POST /v1/verification_cache with payloads above this cap",
|
|
)
|
|
|
|
# ---- Analysis atom tier policy ------------------------------------------
|
|
# These are read live from the AI platform dashboard via RuntimeConfigClient
|
|
# (keys: brain.atom.silver_ttl_days, brain.atom.bronze_ttl_days,
|
|
# brain.atom.confidence_silver_threshold). The values below are fallbacks
|
|
# used at startup until the first dashboard poll completes (~30s).
|
|
atom_silver_ttl_days: int = Field(
|
|
default=90,
|
|
description="TTL for LLM-cached analysis atoms (silver tier)",
|
|
)
|
|
atom_bronze_ttl_days: int = Field(
|
|
default=30,
|
|
description="TTL for low-confidence atoms (never served, kept for audit)",
|
|
)
|
|
atom_confidence_silver_threshold: float = Field(
|
|
default=60.0,
|
|
description="LLM confidence ≥ this stores atom as silver, else bronze",
|
|
)
|
|
|
|
# ---- Logging ------------------------------------------------------------
|
|
log_level: str = Field(default="INFO")
|
|
|
|
# ---- Runtime config (live polling from AI platform dashboard) -----------
|
|
dashboard_url: str | None = Field(
|
|
default=None,
|
|
description=(
|
|
"Optional dashboard base URL (e.g. http://didiAI-dashboard:51300). "
|
|
"When set, RuntimeConfigClient polls /api/config every 30s for live "
|
|
"overrides on atom_* and log_level."
|
|
),
|
|
)
|
|
|
|
# ---- Computed -----------------------------------------------------------
|
|
@property
|
|
def postgres_dsn(self) -> str:
|
|
"""Async-compatible DSN for direct asyncpg connections."""
|
|
return (
|
|
f"postgresql://{self.postgres_user}:{self.postgres_password}"
|
|
f"@{self.postgres_host}:{self.postgres_internal_port}/{self.postgres_db}"
|
|
)
|
|
|
|
@property
|
|
def llamacpp_urls_list(self) -> list[str]:
|
|
return [u.strip() for u in self.llm_llamacpp_urls.split(",") if u.strip()]
|
|
|
|
def model_for(self, role: LlmRole) -> tuple[str, str] | None:
|
|
"""Return (model_id, backend_hint) for a logical role, or None if disabled."""
|
|
if role == LlmRole.REASONING:
|
|
return (self.model_reasoning, self.model_reasoning_backend)
|
|
if role == LlmRole.FAST and self.model_fast_enabled:
|
|
return (self.model_fast, self.model_fast_backend)
|
|
if role == LlmRole.VISION and self.model_vision_enabled:
|
|
return (self.model_vision, "external")
|
|
return None
|
|
|
|
@field_validator("log_level")
|
|
@classmethod
|
|
def _validate_log_level(cls, v: str) -> str:
|
|
v = v.upper()
|
|
if v not in {"DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"}:
|
|
raise ValueError(f"invalid log_level: {v}")
|
|
return v
|
|
|
|
|
|
@lru_cache(maxsize=1)
|
|
def get_settings() -> Settings:
|
|
"""Singleton accessor. Cached so .env is parsed only once per process."""
|
|
return Settings()
|
|
|
|
|
|
# Convenience: most code can `from shared.config import settings`
|
|
settings = get_settings()
|