Spaces:
Running
Running
File size: 3,807 Bytes
069f0a0 9e9bc6b 069f0a0 20c7bad 069f0a0 9e9bc6b 3aa91e9 7cc8b69 9e9bc6b 7cc8b69 3aa91e9 069f0a0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 |
"""Application configuration using Pydantic Settings."""
import logging
from typing import Literal
import structlog
from pydantic import Field
from pydantic_settings import BaseSettings, SettingsConfigDict
from src.utils.exceptions import ConfigurationError
class Settings(BaseSettings):
"""Strongly-typed application settings."""
model_config = SettingsConfigDict(
env_file=".env",
env_file_encoding="utf-8",
case_sensitive=False,
extra="ignore",
)
# LLM Configuration
openai_api_key: str | None = Field(default=None, description="OpenAI API key")
anthropic_api_key: str | None = Field(default=None, description="Anthropic API key")
llm_provider: Literal["openai", "anthropic"] = Field(
default="openai", description="Which LLM provider to use"
)
openai_model: str = Field(default="gpt-5.1", description="OpenAI model name")
anthropic_model: str = Field(
default="claude-sonnet-4-5-20250929", description="Anthropic model"
)
# Embedding Configuration
# Note: OpenAI embeddings require OPENAI_API_KEY (Anthropic has no embeddings API)
openai_embedding_model: str = Field(
default="text-embedding-3-small",
description="OpenAI embedding model (used by LlamaIndex RAG)",
)
local_embedding_model: str = Field(
default="all-MiniLM-L6-v2",
description="Local sentence-transformers model (used by EmbeddingService)",
)
# PubMed Configuration
ncbi_api_key: str | None = Field(
default=None, description="NCBI API key for higher rate limits"
)
# Agent Configuration
max_iterations: int = Field(default=10, ge=1, le=50)
search_timeout: int = Field(default=30, description="Seconds to wait for search")
# Logging
log_level: Literal["DEBUG", "INFO", "WARNING", "ERROR"] = "INFO"
# External Services
modal_token_id: str | None = Field(default=None, description="Modal token ID")
modal_token_secret: str | None = Field(default=None, description="Modal token secret")
chroma_db_path: str = Field(default="./chroma_db", description="ChromaDB storage path")
@property
def modal_available(self) -> bool:
"""Check if Modal credentials are configured."""
return bool(self.modal_token_id and self.modal_token_secret)
def get_api_key(self) -> str:
"""Get the API key for the configured provider."""
if self.llm_provider == "openai":
if not self.openai_api_key:
raise ConfigurationError("OPENAI_API_KEY not set")
return self.openai_api_key
if self.llm_provider == "anthropic":
if not self.anthropic_api_key:
raise ConfigurationError("ANTHROPIC_API_KEY not set")
return self.anthropic_api_key
raise ConfigurationError(f"Unknown LLM provider: {self.llm_provider}")
def get_settings() -> Settings:
"""Factory function to get settings (allows mocking in tests)."""
return Settings()
def configure_logging(settings: Settings) -> None:
"""Configure structured logging with the configured log level."""
# Set stdlib logging level from settings
logging.basicConfig(
level=getattr(logging, settings.log_level),
format="%(message)s",
)
structlog.configure(
processors=[
structlog.stdlib.filter_by_level,
structlog.stdlib.add_logger_name,
structlog.stdlib.add_log_level,
structlog.processors.TimeStamper(fmt="iso"),
structlog.processors.JSONRenderer(),
],
wrapper_class=structlog.stdlib.BoundLogger,
context_class=dict,
logger_factory=structlog.stdlib.LoggerFactory(),
)
# Singleton for easy import
settings = get_settings()
|