Files
langgraph/libs/checkpoint-postgres/langgraph/checkpoint/postgres/aio.py
T

536 lines
21 KiB
Python

import asyncio
from collections.abc import AsyncIterator, Iterator, Sequence
from contextlib import asynccontextmanager
from typing import Any, Optional
from langchain_core.runnables import RunnableConfig
from psycopg import AsyncConnection, AsyncCursor, AsyncPipeline, Capabilities
from psycopg.rows import DictRow, dict_row
from psycopg.types.json import Jsonb
from psycopg_pool import AsyncConnectionPool
from langgraph.checkpoint.base import (
WRITES_IDX_MAP,
ChannelVersions,
Checkpoint,
CheckpointMetadata,
CheckpointTuple,
get_checkpoint_id,
get_checkpoint_metadata,
)
from langgraph.checkpoint.postgres import _ainternal
from langgraph.checkpoint.postgres.base import BasePostgresSaver
from langgraph.checkpoint.postgres.shallow import AsyncShallowPostgresSaver
from langgraph.checkpoint.serde.base import SerializerProtocol
Conn = _ainternal.Conn # For backward compatibility
class AsyncPostgresSaver(BasePostgresSaver):
"""Asynchronous checkpointer that stores checkpoints in a Postgres database."""
lock: asyncio.Lock
def __init__(
self,
conn: _ainternal.Conn,
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()
self.loop = asyncio.get_running_loop()
self.supports_pipeline = Capabilities().has_pipeline()
@classmethod
@asynccontextmanager
async def from_conn_string(
cls,
conn_string: str,
*,
pipeline: bool = False,
serde: Optional[SerializerProtocol] = None,
) -> AsyncIterator["AsyncPostgresSaver"]:
"""Create a new AsyncPostgresSaver instance from a connection string.
Args:
conn_string: The Postgres connection info string.
pipeline: whether to use AsyncPipeline
Returns:
AsyncPostgresSaver: A new AsyncPostgresSaver instance.
"""
async with await AsyncConnection.connect(
conn_string, autocommit=True, prepare_threshold=0, row_factory=dict_row
) as conn:
if pipeline:
async with conn.pipeline() as pipe:
yield cls(conn=conn, pipe=pipe, serde=serde)
else:
yield cls(conn=conn, serde=serde)
async def setup(self) -> None:
"""Set up the checkpoint database asynchronously.
This method creates the necessary tables in the Postgres database if they don't
already exist and runs database migrations. It MUST be called directly by the user
the first time checkpointer is used.
"""
async with self._cursor() as cur:
await cur.execute(self.MIGRATIONS[0])
results = await cur.execute(
"SELECT v FROM checkpoint_migrations ORDER BY v DESC LIMIT 1"
)
row = await results.fetchone()
if row is None:
version = -1
else:
version = row["v"]
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,
config: Optional[RunnableConfig],
*,
filter: Optional[dict[str, Any]] = None,
before: Optional[RunnableConfig] = None,
limit: Optional[int] = None,
) -> AsyncIterator[CheckpointTuple]:
"""List checkpoints from the database asynchronously.
This method retrieves a list of checkpoint tuples from the Postgres database based
on the provided config. The checkpoints are ordered by checkpoint ID in descending order (newest first).
Args:
config: Base configuration for filtering checkpoints.
filter: Additional filtering criteria for metadata.
before: If provided, only checkpoints before the specified checkpoint ID are returned. Defaults to None.
limit: Maximum number of checkpoints to return.
Yields:
AsyncIterator[CheckpointTuple]: An asynchronous iterator of matching checkpoint tuples.
"""
where, args = self._search_where(config, filter, before)
query = self.SELECT_SQL + where + " ORDER BY checkpoint_id DESC"
if limit:
query += f" LIMIT {limit}"
# if we change this to use .stream() we need to make sure to close the cursor
async with self._cursor() as cur:
await cur.execute(query, args, binary=True)
async for value in cur:
yield CheckpointTuple(
{
"configurable": {
"thread_id": value["thread_id"],
"checkpoint_ns": value["checkpoint_ns"],
"checkpoint_id": value["checkpoint_id"],
}
},
await asyncio.to_thread(
self._load_checkpoint,
value["checkpoint"],
value["channel_values"],
value["pending_sends"],
),
self._load_metadata(value["metadata"]),
(
{
"configurable": {
"thread_id": value["thread_id"],
"checkpoint_ns": value["checkpoint_ns"],
"checkpoint_id": value["parent_checkpoint_id"],
}
}
if value["parent_checkpoint_id"]
else None
),
await asyncio.to_thread(self._load_writes, value["pending_writes"]),
)
async def aget_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
"""Get a checkpoint tuple from the database asynchronously.
This method retrieves a checkpoint tuple from the Postgres database based on the
provided config. If the config contains a "checkpoint_id" key, the checkpoint with
the matching thread ID and "checkpoint_id" is retrieved. Otherwise, the latest checkpoint
for the given thread ID is retrieved.
Args:
config: The config to use for retrieving the checkpoint.
Returns:
Optional[CheckpointTuple]: The retrieved checkpoint tuple, or None if no matching checkpoint was found.
"""
thread_id = config["configurable"]["thread_id"]
checkpoint_id = get_checkpoint_id(config)
checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
if checkpoint_id:
args: tuple[Any, ...] = (thread_id, checkpoint_ns, checkpoint_id)
where = "WHERE thread_id = %s AND checkpoint_ns = %s AND checkpoint_id = %s"
else:
args = (thread_id, checkpoint_ns)
where = "WHERE thread_id = %s AND checkpoint_ns = %s ORDER BY checkpoint_id DESC LIMIT 1"
async with self._cursor() as cur:
await cur.execute(
self.SELECT_SQL + where,
args,
binary=True,
)
async for value in cur:
return CheckpointTuple(
{
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": value["checkpoint_id"],
}
},
await asyncio.to_thread(
self._load_checkpoint,
value["checkpoint"],
value["channel_values"],
value["pending_sends"],
),
self._load_metadata(value["metadata"]),
(
{
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": value["parent_checkpoint_id"],
}
}
if value["parent_checkpoint_id"]
else None
),
await asyncio.to_thread(self._load_writes, value["pending_writes"]),
)
async def aput(
self,
config: RunnableConfig,
checkpoint: Checkpoint,
metadata: CheckpointMetadata,
new_versions: ChannelVersions,
) -> RunnableConfig:
"""Save a checkpoint to the database asynchronously.
This method saves a checkpoint to the Postgres database. The checkpoint is associated
with the provided config and its parent config (if any).
Args:
config: The config to associate with the checkpoint.
checkpoint: The checkpoint to save.
metadata: Additional metadata to save with the checkpoint.
new_versions: New channel versions as of this write.
Returns:
RunnableConfig: Updated configuration after storing the checkpoint.
"""
configurable = config["configurable"].copy()
thread_id = configurable.pop("thread_id")
checkpoint_ns = configurable.pop("checkpoint_ns")
checkpoint_id = configurable.pop(
"checkpoint_id", configurable.pop("thread_ts", None)
)
copy = checkpoint.copy()
next_config = {
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": checkpoint["id"],
}
}
async with self._cursor(pipeline=True) as cur:
await cur.executemany(
self.UPSERT_CHECKPOINT_BLOBS_SQL,
await asyncio.to_thread(
self._dump_blobs,
thread_id,
checkpoint_ns,
copy.pop("channel_values"), # type: ignore[misc]
new_versions,
),
)
await cur.execute(
self.UPSERT_CHECKPOINTS_SQL,
(
thread_id,
checkpoint_ns,
checkpoint["id"],
checkpoint_id,
Jsonb(self._dump_checkpoint(copy)),
self._dump_metadata(get_checkpoint_metadata(config, metadata)),
),
)
return next_config
async def aput_writes(
self,
config: RunnableConfig,
writes: Sequence[tuple[str, Any]],
task_id: str,
task_path: str = "",
) -> None:
"""Store intermediate writes linked to a checkpoint asynchronously.
This method saves intermediate writes associated with a checkpoint to the database.
Args:
config: Configuration of the related checkpoint.
writes: List of writes to store, each as (channel, value) pair.
task_id: Identifier for the task creating the writes.
"""
query = (
self.UPSERT_CHECKPOINT_WRITES_SQL
if all(w[0] in WRITES_IDX_MAP for w in writes)
else self.INSERT_CHECKPOINT_WRITES_SQL
)
params = await asyncio.to_thread(
self._dump_writes,
config["configurable"]["thread_id"],
config["configurable"]["checkpoint_ns"],
config["configurable"]["checkpoint_id"],
task_id,
task_path,
writes,
)
async with self._cursor(pipeline=True) as cur:
await cur.executemany(query, params)
async def adelete_thread(self, thread_id: str) -> None:
"""Delete all checkpoints and writes associated with a thread ID.
Args:
thread_id: The thread ID to delete.
Returns:
None
"""
async with self._cursor(pipeline=True) as cur:
await cur.execute(
"DELETE FROM checkpoints WHERE thread_id = %s",
(str(thread_id),),
)
await cur.execute(
"DELETE FROM checkpoint_blobs WHERE thread_id = %s",
(str(thread_id),),
)
await cur.execute(
"DELETE FROM checkpoint_writes WHERE thread_id = %s",
(str(thread_id),),
)
@asynccontextmanager
async def _cursor(
self, *, pipeline: bool = False
) -> AsyncIterator[AsyncCursor[DictRow]]:
"""Create a database cursor as a context manager.
Args:
pipeline: whether to use pipeline for the DB operations inside the context manager.
Will be applied regardless of whether the AsyncPostgresSaver instance was initialized with a pipeline.
If pipeline mode is not supported, will fall back to using transaction context manager.
"""
async with _ainternal.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
if self.supports_pipeline:
async with (
self.lock,
conn.pipeline(),
conn.cursor(binary=True, row_factory=dict_row) as cur,
):
yield cur
else:
# Use connection's transaction context manager when pipeline mode not supported
async with (
self.lock,
conn.transaction(),
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
def list(
self,
config: Optional[RunnableConfig],
*,
filter: Optional[dict[str, Any]] = None,
before: Optional[RunnableConfig] = None,
limit: Optional[int] = None,
) -> Iterator[CheckpointTuple]:
"""List checkpoints from the database.
This method retrieves a list of checkpoint tuples from the Postgres database based
on the provided config. The checkpoints are ordered by checkpoint ID in descending order (newest first).
Args:
config: Base configuration for filtering checkpoints.
filter: Additional filtering criteria for metadata.
before: If provided, only checkpoints before the specified checkpoint ID are returned. Defaults to None.
limit: Maximum number of checkpoints to return.
Yields:
Iterator[CheckpointTuple]: An iterator of matching checkpoint tuples.
"""
try:
# check if we are in the main thread, only bg threads can block
# we don't check in other methods to avoid the overhead
if asyncio.get_running_loop() is self.loop:
raise asyncio.InvalidStateError(
"Synchronous calls to AsyncPostgresSaver are only allowed from a "
"different thread. From the main thread, use the async interface. "
"For example, use `checkpointer.alist(...)` or `await "
"graph.ainvoke(...)`."
)
except RuntimeError:
pass
aiter_ = self.alist(config, filter=filter, before=before, limit=limit)
while True:
try:
yield asyncio.run_coroutine_threadsafe(
anext(aiter_), # noqa: F821
self.loop,
).result()
except StopAsyncIteration:
break
def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
"""Get a checkpoint tuple from the database.
This method retrieves a checkpoint tuple from the Postgres database based on the
provided config. If the config contains a "checkpoint_id" key, the checkpoint with
the matching thread ID and "checkpoint_id" is retrieved. Otherwise, the latest checkpoint
for the given thread ID is retrieved.
Args:
config: The config to use for retrieving the checkpoint.
Returns:
Optional[CheckpointTuple]: The retrieved checkpoint tuple, or None if no matching checkpoint was found.
"""
try:
# check if we are in the main thread, only bg threads can block
# we don't check in other methods to avoid the overhead
if asyncio.get_running_loop() is self.loop:
raise asyncio.InvalidStateError(
"Synchronous calls to AsyncPostgresSaver are only allowed from a "
"different thread. From the main thread, use the async interface. "
"For example, use `await checkpointer.aget_tuple(...)` or `await "
"graph.ainvoke(...)`."
)
except RuntimeError:
pass
return asyncio.run_coroutine_threadsafe(
self.aget_tuple(config), self.loop
).result()
def put(
self,
config: RunnableConfig,
checkpoint: Checkpoint,
metadata: CheckpointMetadata,
new_versions: ChannelVersions,
) -> RunnableConfig:
"""Save a checkpoint to the database.
This method saves a checkpoint to the Postgres database. The checkpoint is associated
with the provided config and its parent config (if any).
Args:
config: The config to associate with the checkpoint.
checkpoint: The checkpoint to save.
metadata: Additional metadata to save with the checkpoint.
new_versions: New channel versions as of this write.
Returns:
RunnableConfig: Updated configuration after storing the checkpoint.
"""
return asyncio.run_coroutine_threadsafe(
self.aput(config, checkpoint, metadata, new_versions), self.loop
).result()
def put_writes(
self,
config: RunnableConfig,
writes: Sequence[tuple[str, Any]],
task_id: str,
task_path: str = "",
) -> None:
"""Store intermediate writes linked to a checkpoint.
This method saves intermediate writes associated with a checkpoint to the database.
Args:
config: Configuration of the related checkpoint.
writes: List of writes to store, each as (channel, value) pair.
task_id: Identifier for the task creating the writes.
task_path: Path of the task creating the writes.
"""
return asyncio.run_coroutine_threadsafe(
self.aput_writes(config, writes, task_id, task_path), self.loop
).result()
def delete_thread(self, thread_id: str) -> None:
"""Delete all checkpoints and writes associated with a thread ID.
Args:
thread_id: The thread ID to delete.
Returns:
None
"""
try:
# check if we are in the main thread, only bg threads can block
# we don't check in other methods to avoid the overhead
if asyncio.get_running_loop() is self.loop:
raise asyncio.InvalidStateError(
"Synchronous calls to AsyncPostgresSaver are only allowed from a "
"different thread. From the main thread, use the async interface. "
"For example, use `await checkpointer.aget_tuple(...)` or `await "
"graph.ainvoke(...)`."
)
except RuntimeError:
pass
return asyncio.run_coroutine_threadsafe(
self.adelete_thread(thread_id), self.loop
).result()
__all__ = ["AsyncPostgresSaver", "AsyncShallowPostgresSaver", "Conn"]