checkpoint-postgres: allow passing pool (#1452)

* checkpoint-postgres: allow passing pool

* make psycopg_pool a non-dev dependency

* code review

* lockfile

* move methods

* relax requirements, remove binary

* add binary to dev dependencies

* update readme
This commit is contained in:
Vadym Barda
2024-08-27 15:30:13 +00:00
committed by GitHub
parent 9ff54e029e
commit d12f5c6d8b
11 changed files with 981 additions and 261 deletions
@@ -1,12 +1,13 @@
import threading
from contextlib import contextmanager
from typing import Any, Iterator, List, Optional
from typing import Any, Iterator, List, Optional, Union
from langchain_core.runnables import RunnableConfig
from psycopg import Connection, Cursor, Pipeline
from psycopg.errors import UndefinedTable
from psycopg.rows import dict_row
from psycopg.types.json import Jsonb
from psycopg_pool import ConnectionPool
from langgraph.checkpoint.base import (
ChannelVersions,
@@ -21,16 +22,32 @@ from langgraph.checkpoint.postgres.base import (
from langgraph.checkpoint.serde.base import SerializerProtocol
@contextmanager
def _get_connection(conn: Union[Connection, ConnectionPool]) -> Iterator[Connection]:
if isinstance(conn, Connection):
yield conn
elif isinstance(conn, ConnectionPool):
with conn.connection() as conn:
yield conn
else:
raise TypeError(f"Invalid connection type: {type(conn)}")
class PostgresSaver(BasePostgresSaver):
lock: threading.Lock
def __init__(
self,
conn: Connection,
conn: Union[Connection, ConnectionPool],
pipe: Optional[Pipeline] = None,
serde: Optional[SerializerProtocol] = None,
) -> None:
super().__init__(serde=serde)
if isinstance(conn, ConnectionPool) and pipe is not None:
raise ValueError(
"Pipeline should be used only with a single Connection, not ConnectionPool."
)
self.conn = conn
self.pipe = pipe
self.lock = threading.Lock()
@@ -65,22 +82,21 @@ class PostgresSaver(BasePostgresSaver):
already exist and runs database migrations. It MUST be called directly by the user
the first time checkpointer is used.
"""
with self.lock:
with self.conn.cursor(binary=True, row_factory=dict_row) as cur:
try:
version = cur.execute(
"SELECT v FROM checkpoint_migrations ORDER BY v DESC LIMIT 1"
).fetchone()["v"]
except UndefinedTable:
version = -1
for v, migration in zip(
range(version + 1, len(self.MIGRATIONS)),
self.MIGRATIONS[version + 1 :],
):
cur.execute(migration)
cur.execute(f"INSERT INTO checkpoint_migrations (v) VALUES ({v})")
if self.pipe:
self.pipe.sync()
with self._cursor() as cur:
try:
version = cur.execute(
"SELECT v FROM checkpoint_migrations ORDER BY v DESC LIMIT 1"
).fetchone()["v"]
except UndefinedTable:
version = -1
for v, migration in zip(
range(version + 1, len(self.MIGRATIONS)),
self.MIGRATIONS[version + 1 :],
):
cur.execute(migration)
cur.execute(f"INSERT INTO checkpoint_migrations (v) VALUES ({v})")
if self.pipe:
self.pipe.sync()
def list(
self,
@@ -333,23 +349,24 @@ class PostgresSaver(BasePostgresSaver):
@contextmanager
def _cursor(self, *, pipeline: bool = False) -> Iterator[Cursor]:
if self.pipe:
# a connection in pipeline mode can be used concurrently
# in multiple threads/coroutines, but only one cursor can be
# used at a time
try:
with self.conn.cursor(binary=True, row_factory=dict_row) as cur:
with _get_connection(self.conn) as conn:
if self.pipe:
# a connection in pipeline mode can be used concurrently
# in multiple threads/coroutines, but only one cursor can be
# used at a time
try:
with conn.cursor(binary=True, row_factory=dict_row) as cur:
yield cur
finally:
if pipeline:
self.pipe.sync()
elif pipeline:
# a connection not in pipeline mode can only be used by one
# thread/coroutine at a time, so we acquire a lock
with self.lock, conn.pipeline(), conn.cursor(
binary=True, row_factory=dict_row
) as cur:
yield cur
else:
with self.lock, conn.cursor(binary=True, row_factory=dict_row) as cur:
yield cur
finally:
if pipeline:
self.pipe.sync()
elif pipeline:
# a connection not in pipeline mode can only be used by one
# thread/coroutine at a time, so we acquire a lock
with self.lock, self.conn.pipeline(), self.conn.cursor(
binary=True, row_factory=dict_row
) as cur:
yield cur
else:
with self.lock, self.conn.cursor(binary=True, row_factory=dict_row) as cur:
yield cur
@@ -1,12 +1,13 @@
import asyncio
from contextlib import asynccontextmanager
from typing import Any, AsyncIterator, Optional
from typing import Any, AsyncIterator, Optional, Union
from langchain_core.runnables import RunnableConfig
from psycopg import AsyncConnection, AsyncCursor, AsyncPipeline
from psycopg.errors import UndefinedTable
from psycopg.rows import dict_row
from psycopg.types.json import Jsonb
from psycopg_pool import AsyncConnectionPool
from langgraph.checkpoint.base import (
ChannelVersions,
@@ -19,16 +20,34 @@ from langgraph.checkpoint.postgres.base import BasePostgresSaver
from langgraph.checkpoint.serde.base import SerializerProtocol
@asynccontextmanager
async def _get_connection(
conn: Union[AsyncConnection, AsyncConnectionPool],
) -> AsyncIterator[AsyncConnection]:
if isinstance(conn, AsyncConnection):
yield conn
elif isinstance(conn, AsyncConnectionPool):
async with conn.connection() as conn:
yield conn
else:
raise TypeError(f"Invalid connection type: {type(conn)}")
class AsyncPostgresSaver(BasePostgresSaver):
lock: asyncio.Lock
def __init__(
self,
conn: AsyncConnection,
conn: Union[AsyncConnection, AsyncConnectionPool],
pipe: Optional[AsyncPipeline] = None,
serde: Optional[SerializerProtocol] = None,
) -> None:
super().__init__(serde=serde)
if isinstance(conn, AsyncConnectionPool) and pipe is not None:
raise ValueError(
"Pipeline should be used only with a single AsyncConnection, not AsyncConnectionPool."
)
self.conn = conn
self.pipe = pipe
self.lock = asyncio.Lock()
@@ -63,25 +82,22 @@ class AsyncPostgresSaver(BasePostgresSaver):
already exist and runs database migrations. It MUST be called directly by the user
the first time checkpointer is used.
"""
async with self.lock:
async with self.conn.cursor(binary=True, row_factory=dict_row) as cur:
try:
results = await cur.execute(
"SELECT v FROM checkpoint_migrations ORDER BY v DESC LIMIT 1"
)
version = (await results.fetchone())["v"]
except UndefinedTable:
version = -1
for v, migration in zip(
range(version + 1, len(self.MIGRATIONS)),
self.MIGRATIONS[version + 1 :],
):
await cur.execute(migration)
await cur.execute(
f"INSERT INTO checkpoint_migrations (v) VALUES ({v})"
)
if self.pipe:
await self.pipe.sync()
async with self._cursor() as cur:
try:
results = await cur.execute(
"SELECT v FROM checkpoint_migrations ORDER BY v DESC LIMIT 1"
)
version = (await results.fetchone())["v"]
except UndefinedTable:
version = -1
for v, migration in zip(
range(version + 1, len(self.MIGRATIONS)),
self.MIGRATIONS[version + 1 :],
):
await cur.execute(migration)
await cur.execute(f"INSERT INTO checkpoint_migrations (v) VALUES ({v})")
if self.pipe:
await self.pipe.sync()
async def alist(
self,
@@ -290,25 +306,26 @@ class AsyncPostgresSaver(BasePostgresSaver):
@asynccontextmanager
async def _cursor(self, *, pipeline: bool = False) -> AsyncIterator[AsyncCursor]:
if self.pipe:
# a connection in pipeline mode can be used concurrently
# in multiple threads/coroutines, but only one cursor can be
# used at a time
try:
async with self.conn.cursor(binary=True, row_factory=dict_row) as cur:
async with _get_connection(self.conn) as conn:
if self.pipe:
# a connection in pipeline mode can be used concurrently
# in multiple threads/coroutines, but only one cursor can be
# used at a time
try:
async with conn.cursor(binary=True, row_factory=dict_row) as cur:
yield cur
finally:
if pipeline:
await self.pipe.sync()
elif pipeline:
# a connection not in pipeline mode can only be used by one
# thread/coroutine at a time, so we acquire a lock
async with self.lock, conn.pipeline(), conn.cursor(
binary=True, row_factory=dict_row
) as cur:
yield cur
else:
async with self.lock, conn.cursor(
binary=True, row_factory=dict_row
) as cur:
yield cur
finally:
if pipeline:
await self.pipe.sync()
elif pipeline:
# a connection not in pipeline mode can only be used by one
# thread/coroutine at a time, so we acquire a lock
async with self.lock, self.conn.pipeline(), self.conn.cursor(
binary=True, row_factory=dict_row
) as cur:
yield cur
else:
async with self.lock, self.conn.cursor(
binary=True, row_factory=dict_row
) as cur:
yield cur