mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-06 08:48:24 +00:00
14c5f4b798
Keep SQLite databases alongside other DeerFlow-managed data (threads, memory) under the .deer-flow/ directory instead of a top-level ./data folder. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
86 lines
3.2 KiB
Python
86 lines
3.2 KiB
Python
"""Unified database backend configuration.
|
|
|
|
Controls BOTH the LangGraph checkpointer and the DeerFlow application
|
|
persistence layer (runs, threads metadata, users, etc.). The user
|
|
configures one backend; the system handles physical separation details.
|
|
|
|
SQLite mode: checkpointer and app use different .db files in the same
|
|
directory to avoid write-lock contention. This is automatic.
|
|
|
|
Postgres mode: both use the same database URL but maintain independent
|
|
connection pools with different lifecycles.
|
|
|
|
Memory mode: checkpointer uses MemorySaver, app uses in-memory stores.
|
|
No database is initialized.
|
|
|
|
Sensitive values (postgres_url) should use $VAR syntax in config.yaml
|
|
to reference environment variables from .env:
|
|
|
|
database:
|
|
backend: postgres
|
|
postgres_url: $DATABASE_URL
|
|
|
|
The $VAR resolution is handled by AppConfig.resolve_env_variables()
|
|
before this config is instantiated -- DatabaseConfig itself does not
|
|
need to do any environment variable processing.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
from typing import Literal
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
|
|
class DatabaseConfig(BaseModel):
|
|
backend: Literal["memory", "sqlite", "postgres"] = Field(
|
|
default="memory",
|
|
description=("Storage backend for both checkpointer and application data. 'memory' for development (no persistence across restarts), 'sqlite' for single-node deployment, 'postgres' for production multi-node deployment."),
|
|
)
|
|
sqlite_dir: str = Field(
|
|
default=".deer-flow/data",
|
|
description=("Directory for SQLite database files. Checkpointer uses {sqlite_dir}/checkpoints.db, application data uses {sqlite_dir}/app.db."),
|
|
)
|
|
postgres_url: str = Field(
|
|
default="",
|
|
description=(
|
|
"PostgreSQL connection URL, shared by checkpointer and app. "
|
|
"Use $DATABASE_URL in config.yaml to reference .env. "
|
|
"Example: postgresql://user:pass@host:5432/deerflow "
|
|
"(the +asyncpg driver suffix is added automatically where needed)."
|
|
),
|
|
)
|
|
echo_sql: bool = Field(
|
|
default=False,
|
|
description="Echo all SQL statements to log (debug only).",
|
|
)
|
|
pool_size: int = Field(
|
|
default=5,
|
|
description="Connection pool size for the app ORM engine (postgres only).",
|
|
)
|
|
|
|
# -- Derived helpers (not user-configured) --
|
|
|
|
@property
|
|
def checkpointer_sqlite_path(self) -> str:
|
|
"""SQLite file path for the LangGraph checkpointer."""
|
|
return os.path.join(self.sqlite_dir, "checkpoints.db")
|
|
|
|
@property
|
|
def app_sqlite_path(self) -> str:
|
|
"""SQLite file path for application ORM data."""
|
|
return os.path.join(self.sqlite_dir, "app.db")
|
|
|
|
@property
|
|
def app_sqlalchemy_url(self) -> str:
|
|
"""SQLAlchemy async URL for the application ORM engine."""
|
|
if self.backend == "sqlite":
|
|
return f"sqlite+aiosqlite:///{self.app_sqlite_path}"
|
|
if self.backend == "postgres":
|
|
url = self.postgres_url
|
|
if url.startswith("postgresql://"):
|
|
url = url.replace("postgresql://", "postgresql+asyncpg://", 1)
|
|
return url
|
|
raise ValueError(f"No SQLAlchemy URL for backend={self.backend!r}")
|