justin
de50f2c803
Extends the #215 abstraction: - OpenAICompatibleLLMProvider / OpenAICompatibleEmbeddingProvider — one impl (via the official openai SDK) covers OpenAI, xAI (api.x.ai/v1), Ollama (…:11434/v1), OpenRouter, etc.; they differ only by base_url, key, and model. - Registry factory: build_llm_providers() / build_embedding_providers() return every provider whose credentials are configured, so you can run several concurrently. get_llm_provider(name)/get_embedding_provider(name) select by name, falling back to default_*_provider, then Null. - Per-provider env config (ANTHROPIC_*, OPENAI_*, XAI_*, OLLAMA_*) + DEFAULT_LLM_PROVIDER / DEFAULT_EMBEDDING_PROVIDER; documented in .env.example. Defaults keep AI off (empty registry). Embeddings now have real backends (OpenAI/Ollama), still separate from the LLM since Anthropic offers no embeddings endpoint. Tests cover multi-provider selection, default resolution, disabled-without-credentials, and null fail-loud. Full suite 87 passed. Relates to #215. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Signed-off-by: Justin Paul <justin@jpaul.me>
97 lines
3.7 KiB
Python
97 lines
3.7 KiB
Python
"""Application configuration.
|
|
|
|
Twelve-factor: everything is read from the environment. Defaults are
|
|
development-friendly; production supplies real values via the compose `.env`.
|
|
No secrets or endpoints are hard-coded.
|
|
"""
|
|
|
|
from functools import lru_cache
|
|
|
|
from pydantic import Field
|
|
from pydantic_settings import BaseSettings, SettingsConfigDict
|
|
|
|
|
|
class Settings(BaseSettings):
|
|
model_config = SettingsConfigDict(
|
|
env_file=".env",
|
|
env_file_encoding="utf-8",
|
|
extra="ignore",
|
|
)
|
|
|
|
app_name: str = "Provenance"
|
|
version: str = "0.0.0"
|
|
app_env: str = Field(default="development", description="development | production")
|
|
|
|
# SQLAlchemy async URL, e.g. postgresql+asyncpg://user:pass@host:5432/db
|
|
database_url: str = Field(
|
|
default="postgresql+asyncpg://provenance:provenance@localhost:5432/provenance",
|
|
)
|
|
|
|
# --- Auth / sessions ---
|
|
session_ttl_days: int = 30
|
|
token_ttl_hours: int = 24 # email-verify / password-reset token lifetime
|
|
cookie_name: str = "provenance_session"
|
|
cookie_secure: bool = True # set false for local http; true behind TLS
|
|
# Base URL used to build links in outbound email.
|
|
app_base_url: str = "http://localhost"
|
|
|
|
# --- Object storage (S3-compatible / MinIO) ---
|
|
s3_endpoint_url: str = "http://minio:9000"
|
|
s3_bucket: str = "provenance"
|
|
s3_access_key: str = "provenance"
|
|
s3_secret_key: str = "change-me-too"
|
|
s3_region: str = "us-east-1"
|
|
s3_presign_ttl: int = 3600 # seconds
|
|
|
|
# --- Worker ---
|
|
purge_interval_seconds: int = 3600 # how often to run the soft-delete purge
|
|
purge_after_days: int = 30 # soft-deleted rows older than this are purged
|
|
|
|
# --- Email (SMTP) ---
|
|
# When true, a user with no verified email gets no active session (login is
|
|
# refused and existing sessions stop resolving). Default false so self-hosts
|
|
# without SMTP — and accounts created before this gate existed — aren't
|
|
# locked out; operators turn it on once mail works and accounts are verified.
|
|
require_email_verification: bool = False
|
|
mailer: str = Field(default="console", description="console | smtp")
|
|
smtp_host: str | None = None
|
|
smtp_port: int = 587
|
|
smtp_username: str | None = None
|
|
smtp_password: str | None = None
|
|
smtp_from: str = "Provenance <no-reply@provenance.local>"
|
|
|
|
# --- Model providers (AI assistant + match-ranking embeddings) ---
|
|
# Configure as many as you like; each is enabled when its credentials are
|
|
# present. `default_*_provider` picks which one is used by default. LLM and
|
|
# embeddings are independent (Anthropic has no embeddings endpoint).
|
|
default_llm_provider: str = "null" # null | anthropic | openai | xai | ollama
|
|
default_embedding_provider: str = "null" # null | openai | ollama
|
|
llm_max_tokens: int = 4096
|
|
embedding_dimensions: int = 1536 # must match the embedding model + pgvector column
|
|
|
|
# Anthropic (LLM only)
|
|
anthropic_api_key: str | None = None
|
|
anthropic_model: str = "claude-opus-4-8"
|
|
|
|
# OpenAI (LLM + embeddings)
|
|
openai_api_key: str | None = None
|
|
openai_base_url: str = "https://api.openai.com/v1"
|
|
openai_model: str = "gpt-4o"
|
|
openai_embedding_model: str = "text-embedding-3-small"
|
|
|
|
# xAI / Grok — OpenAI-compatible (LLM)
|
|
xai_api_key: str | None = None
|
|
xai_base_url: str = "https://api.x.ai/v1"
|
|
xai_model: str = "grok-2-latest" # set to your account's current Grok model
|
|
|
|
# Ollama — local, OpenAI-compatible, no key (LLM + embeddings)
|
|
ollama_enabled: bool = False
|
|
ollama_base_url: str = "http://localhost:11434/v1"
|
|
ollama_model: str = "llama3.1"
|
|
ollama_embedding_model: str = "nomic-embed-text"
|
|
|
|
|
|
@lru_cache
|
|
def get_settings() -> Settings:
|
|
return Settings()
|