feat: improve assistant knowledge import and database compatibility

This commit is contained in:
吉鑫升 committed 2026-09-02 17:55:17 +08:00
1 parent fbd8dec48f
commit 6b724bd00d
51 files changed
+4393 -1021

No files matched your search

@@ -11,10 +11,15 @@ blocking, making a unified file safe for both workloads. Writers
that contend for the lock wait via the default 5-second sqlite3
busy timeout rather than failing immediately.
Postgres mode: both use the same database URL but maintain independent
connection pools with different lifecycles.
MySQL mode: application ORM data uses MySQL. LangGraph's checkpointer does
Postgres mode: both use the same database URL but maintain independent
connection pools with different lifecycles.
Gauss mode: application ORM data uses the official openGauss SQLAlchemy
dialect over asyncpg. LangGraph's PostgreSQL checkpointer is intentionally not
reused for GaussDB; configure the legacy ``checkpointer:`` section separately
(normally sqlite).
MySQL mode: application ORM data uses MySQL. LangGraph's checkpointer does
not have a built-in MySQL backend in this project, so deployments that choose
MySQL for business tables should configure the legacy ``checkpointer:``
section separately (usually sqlite) to preserve conversation checkpoints.
@@ -42,24 +47,40 @@ from typing import Literal
from pydantic import BaseModel, Field
class DatabaseConfig(BaseModel):
backend: Literal["memory", "sqlite", "postgres", "mysql"] = Field(
default="memory",
description=("Storage backend for application data. 'memory' for development (no persistence across restarts), 'sqlite' for single-node deployment, 'postgres' for production multi-node deployment, 'mysql' for MySQL-backed business tables."),
class DatabaseConfig(BaseModel):
backend: Literal["memory", "sqlite", "postgres", "gauss", "mysql"] = Field(
default="memory",
description=(
"Storage backend for application data. 'memory' for development "
"(no persistence across restarts), 'sqlite' for single-node "
"deployment, 'postgres' for production multi-node deployment, "
"'gauss' for openGauss/GaussDB business tables, and 'mysql' for "
"MySQL-backed business tables."
),
)
sqlite_dir: str = Field(
default=".deer-flow/data",
description=("Directory for the SQLite database file. Both checkpointer and application data share {sqlite_dir}/deerflow.db."),
)
postgres_url: str = Field(
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)."
),
)
),
)
gauss_url: str = Field(
default="",
description=(
"openGauss/GaussDB connection URL for the application ORM. "
"Use $GAUSS_DATABASE_URL in config.yaml to reference .env. "
"Example: opengauss+asyncpg://user:pass@host:26000/deerflow. "
"Plain opengauss:// or PostgreSQL-style URLs are normalized to the "
"official asynchronous openGauss SQLAlchemy dialect."
),
)
mysql_url: str = Field(
default="",
description=(
@@ -75,26 +96,26 @@ class DatabaseConfig(BaseModel):
)
pool_size: int = Field(
default=5,
description="Connection pool size for the app ORM engine (postgres/mysql only).",
description="Connection pool size for the app ORM engine (postgres/gauss/mysql only).",
)
max_overflow: int = Field(
default=10,
description=(
"Extra connections allowed beyond pool_size under load (postgres/mysql only). "
"Extra connections allowed beyond pool_size under load (postgres/gauss/mysql only). "
"The real connection ceiling is pool_size + max_overflow. SQLAlchemy default is 10."
),
)
pool_timeout: int = Field(
default=30,
description=(
"Seconds a caller waits for a free pooled connection before erroring (postgres/mysql only). "
"Seconds a caller waits for a free pooled connection before erroring (postgres/gauss/mysql only). "
"SQLAlchemy default is 30."
),
)
pool_recycle: int = Field(
default=1800,
description=(
"Recycle pooled connections after this many seconds (postgres/mysql only). "
"Recycle pooled connections after this many seconds (postgres/gauss/mysql only). "
"Prevents stale-connection errors when a firewall, pgbouncer, or MySQL "
"wait_timeout silently drops idle connections. pool_pre_ping catches most "
"cases, but pool_recycle is the belt-and-suspenders safety net. "
@@ -133,12 +154,38 @@ class DatabaseConfig(BaseModel):
"""SQLAlchemy async URL for the application ORM engine."""
if self.backend == "sqlite":
return f"sqlite+aiosqlite:///{self.sqlite_path}"
if self.backend == "postgres":
url = self.postgres_url
if url.startswith("postgresql://"):
url = url.replace("postgresql://", "postgresql+asyncpg://", 1)
return url
if self.backend == "mysql":
if self.backend == "postgres":
url = self.postgres_url
if url.startswith("postgresql://"):
url = url.replace("postgresql://", "postgresql+asyncpg://", 1)
return url
if self.backend == "gauss":
url = self.gauss_url.strip()
if not url:
raise ValueError("database.gauss_url is required for backend='gauss'")
# GaussDB speaks the PostgreSQL wire protocol, but its server
# version string and DDL capabilities are not identical to
# PostgreSQL. Always select the official openGauss dialect instead
# of silently sending the URL through SQLAlchemy's generic PG
# dialect (the latter commonly connects and then fails while
# SQLAlchemy initializes/creates the schema).
for prefix in (
"opengauss://",
"gaussdb://",
"postgres://",
"postgresql://",
"postgresql+asyncpg://",
):
if url.startswith(prefix):
return "opengauss+asyncpg://" + url[len(prefix) :]
if url.startswith("opengauss+asyncpg://"):
return url
raise ValueError(
"database.gauss_url must use opengauss://, "
"opengauss+asyncpg://, or a PostgreSQL-style URL"
)
if self.backend == "mysql":
url = self.mysql_url
if not url:
raise ValueError("database.mysql_url is required for backend='mysql'")