langgraph-checkpoint-postgres 2.0.7__tar.gz → 2.0.9__tar.gz

{langgraph_checkpoint_postgres-2.0.7 → langgraph_checkpoint_postgres-2.0.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langgraph-checkpoint-postgres
-Version: 2.0.7
+Version: 2.0.9
 Summary: Library with a Postgres implementation of LangGraph checkpoint saver.
 Home-page: https://www.github.com/langchain-ai/langgraph
 License: MIT

{langgraph_checkpoint_postgres-2.0.7 → langgraph_checkpoint_postgres-2.0.9}/langgraph/checkpoint/postgres/__init__.py

@@ -19,6 +19,7 @@ from langgraph.checkpoint.base import (
 )
 from langgraph.checkpoint.postgres import _internal
 from langgraph.checkpoint.postgres.base import BasePostgresSaver
+from langgraph.checkpoint.postgres.shallow import ShallowPostgresSaver
 from langgraph.checkpoint.serde.base import SerializerProtocol
 
 Conn = _internal.Conn  # For backward compatibility
@@ -396,4 +397,4 @@ class PostgresSaver(BasePostgresSaver):
                     yield cur
 
 
-__all__ = ["PostgresSaver", "BasePostgresSaver", "Conn"]
+__all__ = ["PostgresSaver", "BasePostgresSaver", "ShallowPostgresSaver", "Conn"]

{langgraph_checkpoint_postgres-2.0.7 → langgraph_checkpoint_postgres-2.0.9}/langgraph/checkpoint/postgres/aio.py

@@ -19,6 +19,7 @@ from langgraph.checkpoint.base import (
 )
 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
@@ -54,7 +55,7 @@ class AsyncPostgresSaver(BasePostgresSaver):
         pipeline: bool = False,
         serde: Optional[SerializerProtocol] = None,
     ) -> AsyncIterator["AsyncPostgresSaver"]:
-        """Create a new PostgresSaver instance from a connection string.
+        """Create a new AsyncPostgresSaver instance from a connection string.
 
         Args:
             conn_string (str): The Postgres connection info string.
@@ -464,4 +465,4 @@ class AsyncPostgresSaver(BasePostgresSaver):
         ).result()
 
 
-__all__ = ["AsyncPostgresSaver", "Conn"]
+__all__ = ["AsyncPostgresSaver", "AsyncShallowPostgresSaver", "Conn"]

{langgraph_checkpoint_postgres-2.0.7 → langgraph_checkpoint_postgres-2.0.9}/langgraph/checkpoint/postgres/base.py

@@ -57,6 +57,17 @@ MIGRATIONS = [
     PRIMARY KEY (thread_id, checkpoint_ns, checkpoint_id, task_id, idx)
 );""",
     "ALTER TABLE checkpoint_blobs ALTER COLUMN blob DROP not null;",
+    """
+    """,
+    """
+    CREATE INDEX CONCURRENTLY IF NOT EXISTS checkpoints_thread_id_idx ON checkpoints(thread_id);
+    """,
+    """
+    CREATE INDEX CONCURRENTLY IF NOT EXISTS checkpoint_blobs_thread_id_idx ON checkpoint_blobs(thread_id);
+    """,
+    """
+    CREATE INDEX CONCURRENTLY IF NOT EXISTS checkpoint_writes_thread_id_idx ON checkpoint_writes(thread_id);
+    """,
 ]
 
 SELECT_SQL = f"""

langgraph_checkpoint_postgres-2.0.9/langgraph/checkpoint/postgres/shallow.py

@@ -0,0 +1,918 @@
+import asyncio
+import threading
+from collections.abc import AsyncIterator, Iterator, Sequence
+from contextlib import asynccontextmanager, contextmanager
+from typing import Any, Optional
+
+from langchain_core.runnables import RunnableConfig
+from psycopg import (
+    AsyncConnection,
+    AsyncCursor,
+    AsyncPipeline,
+    Capabilities,
+    Connection,
+    Cursor,
+    Pipeline,
+)
+from psycopg.rows import DictRow, dict_row
+from psycopg.types.json import Jsonb
+from psycopg_pool import AsyncConnectionPool, ConnectionPool
+
+from langgraph.checkpoint.base import (
+    WRITES_IDX_MAP,
+    ChannelVersions,
+    Checkpoint,
+    CheckpointMetadata,
+    CheckpointTuple,
+)
+from langgraph.checkpoint.postgres import _ainternal, _internal
+from langgraph.checkpoint.postgres.base import BasePostgresSaver
+from langgraph.checkpoint.serde.base import SerializerProtocol
+from langgraph.checkpoint.serde.types import TASKS
+
+"""
+To add a new migration, add a new string to the MIGRATIONS list.
+The position of the migration in the list is the version number.
+"""
+MIGRATIONS = [
+    """CREATE TABLE IF NOT EXISTS checkpoint_migrations (
+    v INTEGER PRIMARY KEY
+);""",
+    """CREATE TABLE IF NOT EXISTS checkpoints (
+    thread_id TEXT NOT NULL,
+    checkpoint_ns TEXT NOT NULL DEFAULT '',
+    type TEXT,
+    checkpoint JSONB NOT NULL,
+    metadata JSONB NOT NULL DEFAULT '{}',
+    PRIMARY KEY (thread_id, checkpoint_ns)
+);""",
+    """CREATE TABLE IF NOT EXISTS checkpoint_blobs (
+    thread_id TEXT NOT NULL,
+    checkpoint_ns TEXT NOT NULL DEFAULT '',
+    channel TEXT NOT NULL,
+    type TEXT NOT NULL,
+    blob BYTEA,
+    PRIMARY KEY (thread_id, checkpoint_ns, channel)
+);""",
+    """CREATE TABLE IF NOT EXISTS checkpoint_writes (
+    thread_id TEXT NOT NULL,
+    checkpoint_ns TEXT NOT NULL DEFAULT '',
+    checkpoint_id TEXT NOT NULL,
+    task_id TEXT NOT NULL,
+    idx INTEGER NOT NULL,
+    channel TEXT NOT NULL,
+    type TEXT,
+    blob BYTEA NOT NULL,
+    PRIMARY KEY (thread_id, checkpoint_ns, checkpoint_id, task_id, idx)
+);""",
+    """
+    CREATE INDEX CONCURRENTLY IF NOT EXISTS checkpoints_thread_id_idx ON checkpoints(thread_id);
+    """,
+    """
+    CREATE INDEX CONCURRENTLY IF NOT EXISTS checkpoint_blobs_thread_id_idx ON checkpoint_blobs(thread_id);
+    """,
+    """
+    CREATE INDEX CONCURRENTLY IF NOT EXISTS checkpoint_writes_thread_id_idx ON checkpoint_writes(thread_id);
+    """,
+]
+
+SELECT_SQL = f"""
+select
+    thread_id,
+    checkpoint,
+    checkpoint_ns,
+    metadata,
+    (
+        select array_agg(array[bl.channel::bytea, bl.type::bytea, bl.blob])
+        from jsonb_each_text(checkpoint -> 'channel_versions')
+        inner join checkpoint_blobs bl
+            on bl.thread_id = checkpoints.thread_id
+            and bl.checkpoint_ns = checkpoints.checkpoint_ns
+            and bl.channel = jsonb_each_text.key
+    ) as channel_values,
+    (
+        select
+        array_agg(array[cw.task_id::text::bytea, cw.channel::bytea, cw.type::bytea, cw.blob] order by cw.task_id, cw.idx)
+        from checkpoint_writes cw
+        where cw.thread_id = checkpoints.thread_id
+            and cw.checkpoint_ns = checkpoints.checkpoint_ns
+            and cw.checkpoint_id = (checkpoint->>'id')
+    ) as pending_writes,
+    (
+        select array_agg(array[cw.type::bytea, cw.blob] order by cw.task_id, cw.idx)
+        from checkpoint_writes cw
+        where cw.thread_id = checkpoints.thread_id
+            and cw.checkpoint_ns = checkpoints.checkpoint_ns
+            and cw.channel = '{TASKS}'
+    ) as pending_sends
+from checkpoints """
+
+UPSERT_CHECKPOINT_BLOBS_SQL = """
+    INSERT INTO checkpoint_blobs (thread_id, checkpoint_ns, channel, type, blob)
+    VALUES (%s, %s, %s, %s, %s)
+    ON CONFLICT (thread_id, checkpoint_ns, channel) DO UPDATE SET
+        type = EXCLUDED.type,
+        blob = EXCLUDED.blob;
+"""
+
+UPSERT_CHECKPOINTS_SQL = """
+    INSERT INTO checkpoints (thread_id, checkpoint_ns, checkpoint, metadata)
+    VALUES (%s, %s, %s, %s)
+    ON CONFLICT (thread_id, checkpoint_ns)
+    DO UPDATE SET
+        checkpoint = EXCLUDED.checkpoint,
+        metadata = EXCLUDED.metadata;
+"""
+
+UPSERT_CHECKPOINT_WRITES_SQL = """
+    INSERT INTO checkpoint_writes (thread_id, checkpoint_ns, checkpoint_id, task_id, idx, channel, type, blob)
+    VALUES (%s, %s, %s, %s, %s, %s, %s, %s)
+    ON CONFLICT (thread_id, checkpoint_ns, checkpoint_id, task_id, idx) DO UPDATE SET
+        channel = EXCLUDED.channel,
+        type = EXCLUDED.type,
+        blob = EXCLUDED.blob;
+"""
+
+INSERT_CHECKPOINT_WRITES_SQL = """
+    INSERT INTO checkpoint_writes (thread_id, checkpoint_ns, checkpoint_id, task_id, idx, channel, type, blob)
+    VALUES (%s, %s, %s, %s, %s, %s, %s, %s)
+    ON CONFLICT (thread_id, checkpoint_ns, checkpoint_id, task_id, idx) DO NOTHING
+"""
+
+
+def _dump_blobs(
+    serde: SerializerProtocol,
+    thread_id: str,
+    checkpoint_ns: str,
+    values: dict[str, Any],
+    versions: ChannelVersions,
+) -> list[tuple[str, str, str, str, str, Optional[bytes]]]:
+    if not versions:
+        return []
+
+    return [
+        (
+            thread_id,
+            checkpoint_ns,
+            k,
+            *(serde.dumps_typed(values[k]) if k in values else ("empty", None)),
+        )
+        for k in versions
+    ]
+
+
+class ShallowPostgresSaver(BasePostgresSaver):
+    """A checkpoint saver that uses Postgres to store checkpoints.
+
+    This checkpointer ONLY stores the most recent checkpoint and does NOT retain any history.
+    It is meant to be a light-weight drop-in replacement for the PostgresSaver that
+    supports most of the LangGraph persistence functionality with the exception of time travel.
+    """
+
+    SELECT_SQL = SELECT_SQL
+    MIGRATIONS = MIGRATIONS
+    UPSERT_CHECKPOINT_BLOBS_SQL = UPSERT_CHECKPOINT_BLOBS_SQL
+    UPSERT_CHECKPOINTS_SQL = UPSERT_CHECKPOINTS_SQL
+    UPSERT_CHECKPOINT_WRITES_SQL = UPSERT_CHECKPOINT_WRITES_SQL
+    INSERT_CHECKPOINT_WRITES_SQL = INSERT_CHECKPOINT_WRITES_SQL
+
+    lock: threading.Lock
+
+    def __init__(
+        self,
+        conn: _internal.Conn,
+        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()
+        self.supports_pipeline = Capabilities().has_pipeline()
+
+    @classmethod
+    @contextmanager
+    def from_conn_string(
+        cls, conn_string: str, *, pipeline: bool = False
+    ) -> Iterator["ShallowPostgresSaver"]:
+        """Create a new ShallowPostgresSaver instance from a connection string.
+
+        Args:
+            conn_string (str): The Postgres connection info string.
+            pipeline (bool): whether to use Pipeline
+
+        Returns:
+            ShallowPostgresSaver: A new ShallowPostgresSaver instance.
+        """
+        with Connection.connect(
+            conn_string, autocommit=True, prepare_threshold=0, row_factory=dict_row
+        ) as conn:
+            if pipeline:
+                with conn.pipeline() as pipe:
+                    yield cls(conn, pipe)
+            else:
+                yield cls(conn)
+
+    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.
+        """
+        with self._cursor() as cur:
+            cur.execute(self.MIGRATIONS[0])
+            results = cur.execute(
+                "SELECT v FROM checkpoint_migrations ORDER BY v DESC LIMIT 1"
+            )
+            row = 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 :],
+            ):
+                cur.execute(migration)
+                cur.execute(f"INSERT INTO checkpoint_migrations (v) VALUES ({v})")
+        if self.pipe:
+            self.pipe.sync()
+
+    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. For ShallowPostgresSaver, this method returns a list with
+        ONLY the most recent checkpoint.
+        """
+        where, args = self._search_where(config, filter, before)
+        query = self.SELECT_SQL + where
+        if limit:
+            query += f" LIMIT {limit}"
+        with self._cursor() as cur:
+            cur.execute(self.SELECT_SQL + where, args, binary=True)
+            for value in cur:
+                checkpoint = self._load_checkpoint(
+                    value["checkpoint"],
+                    value["channel_values"],
+                    value["pending_sends"],
+                )
+                yield CheckpointTuple(
+                    config={
+                        "configurable": {
+                            "thread_id": value["thread_id"],
+                            "checkpoint_ns": value["checkpoint_ns"],
+                            "checkpoint_id": checkpoint["id"],
+                        }
+                    },
+                    checkpoint=checkpoint,
+                    metadata=self._load_metadata(value["metadata"]),
+                    pending_writes=self._load_writes(value["pending_writes"]),
+                )
+
+    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 (matching the thread ID in the config).
+
+        Args:
+            config (RunnableConfig): The config to use for retrieving the checkpoint.
+
+        Returns:
+            Optional[CheckpointTuple]: The retrieved checkpoint tuple, or None if no matching checkpoint was found.
+
+        Examples:
+
+            Basic:
+            >>> config = {"configurable": {"thread_id": "1"}}
+            >>> checkpoint_tuple = memory.get_tuple(config)
+            >>> print(checkpoint_tuple)
+            CheckpointTuple(...)
+
+            With timestamp:
+
+            >>> config = {
+            ...    "configurable": {
+            ...        "thread_id": "1",
+            ...        "checkpoint_ns": "",
+            ...        "checkpoint_id": "1ef4f797-8335-6428-8001-8a1503f9b875",
+            ...    }
+            ... }
+            >>> checkpoint_tuple = memory.get_tuple(config)
+            >>> print(checkpoint_tuple)
+            CheckpointTuple(...)
+        """  # noqa
+        thread_id = config["configurable"]["thread_id"]
+        checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
+        args = (thread_id, checkpoint_ns)
+        where = "WHERE thread_id = %s AND checkpoint_ns = %s"
+
+        with self._cursor() as cur:
+            cur.execute(
+                self.SELECT_SQL + where,
+                args,
+                binary=True,
+            )
+
+            for value in cur:
+                checkpoint = self._load_checkpoint(
+                    value["checkpoint"],
+                    value["channel_values"],
+                    value["pending_sends"],
+                )
+                return CheckpointTuple(
+                    config={
+                        "configurable": {
+                            "thread_id": thread_id,
+                            "checkpoint_ns": checkpoint_ns,
+                            "checkpoint_id": checkpoint["id"],
+                        }
+                    },
+                    checkpoint=checkpoint,
+                    metadata=self._load_metadata(value["metadata"]),
+                    pending_writes=self._load_writes(value["pending_writes"]),
+                )
+
+    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. For ShallowPostgresSaver, this method saves ONLY the most recent
+        checkpoint and overwrites a previous checkpoint, if it exists.
+
+        Args:
+            config (RunnableConfig): The config to associate with the checkpoint.
+            checkpoint (Checkpoint): The checkpoint to save.
+            metadata (CheckpointMetadata): Additional metadata to save with the checkpoint.
+            new_versions (ChannelVersions): New channel versions as of this write.
+
+        Returns:
+            RunnableConfig: Updated configuration after storing the checkpoint.
+
+        Examples:
+
+            >>> from langgraph.checkpoint.postgres import ShallowPostgresSaver
+            >>> DB_URI = "postgres://postgres:postgres@localhost:5432/postgres?sslmode=disable"
+            >>> with ShallowPostgresSaver.from_conn_string(DB_URI) as memory:
+            >>>     config = {"configurable": {"thread_id": "1", "checkpoint_ns": ""}}
+            >>>     checkpoint = {"ts": "2024-05-04T06:32:42.235444+00:00", "id": "1ef4f797-8335-6428-8001-8a1503f9b875", "channel_values": {"key": "value"}}
+            >>>     saved_config = memory.put(config, checkpoint, {"source": "input", "step": 1, "writes": {"key": "value"}}, {})
+            >>> print(saved_config)
+            {'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '1ef4f797-8335-6428-8001-8a1503f9b875'}}
+        """
+        configurable = config["configurable"].copy()
+        thread_id = configurable.pop("thread_id")
+        checkpoint_ns = configurable.pop("checkpoint_ns")
+
+        copy = checkpoint.copy()
+        next_config = {
+            "configurable": {
+                "thread_id": thread_id,
+                "checkpoint_ns": checkpoint_ns,
+                "checkpoint_id": checkpoint["id"],
+            }
+        }
+
+        with self._cursor(pipeline=True) as cur:
+            cur.execute(
+                """DELETE FROM checkpoint_writes
+                WHERE thread_id = %s AND checkpoint_ns = %s AND checkpoint_id NOT IN (%s, %s)""",
+                (
+                    thread_id,
+                    checkpoint_ns,
+                    checkpoint["id"],
+                    configurable.get("checkpoint_id", ""),
+                ),
+            )
+            cur.executemany(
+                self.UPSERT_CHECKPOINT_BLOBS_SQL,
+                _dump_blobs(
+                    self.serde,
+                    thread_id,
+                    checkpoint_ns,
+                    copy.pop("channel_values"),  # type: ignore[misc]
+                    new_versions,
+                ),
+            )
+            cur.execute(
+                self.UPSERT_CHECKPOINTS_SQL,
+                (
+                    thread_id,
+                    checkpoint_ns,
+                    Jsonb(self._dump_checkpoint(copy)),
+                    self._dump_metadata(metadata),
+                ),
+            )
+        return next_config
+
+    def put_writes(
+        self,
+        config: RunnableConfig,
+        writes: Sequence[tuple[str, Any]],
+        task_id: str,
+    ) -> None:
+        """Store intermediate writes linked to a checkpoint.
+
+        This method saves intermediate writes associated with a checkpoint to the Postgres database.
+
+        Args:
+            config (RunnableConfig): Configuration of the related checkpoint.
+            writes (List[Tuple[str, Any]]): List of writes to store.
+            task_id (str): 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
+        )
+        with self._cursor(pipeline=True) as cur:
+            cur.executemany(
+                query,
+                self._dump_writes(
+                    config["configurable"]["thread_id"],
+                    config["configurable"]["checkpoint_ns"],
+                    config["configurable"]["checkpoint_id"],
+                    task_id,
+                    writes,
+                ),
+            )
+
+    @contextmanager
+    def _cursor(self, *, pipeline: bool = False) -> Iterator[Cursor[DictRow]]:
+        """Create a database cursor as a context manager.
+
+        Args:
+            pipeline (bool): whether to use pipeline for the DB operations inside the context manager.
+                Will be applied regardless of whether the ShallowPostgresSaver instance was initialized with a pipeline.
+                If pipeline mode is not supported, will fall back to using transaction context manager.
+        """
+        with _internal.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
+                if self.supports_pipeline:
+                    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
+                    with (
+                        self.lock,
+                        conn.transaction(),
+                        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
+
+
+class AsyncShallowPostgresSaver(BasePostgresSaver):
+    """A checkpoint saver that uses Postgres to store checkpoints asynchronously.
+
+    This checkpointer ONLY stores the most recent checkpoint and does NOT retain any history.
+    It is meant to be a light-weight drop-in replacement for the AsyncPostgresSaver that
+    supports most of the LangGraph persistence functionality with the exception of time travel.
+    """
+
+    SELECT_SQL = SELECT_SQL
+    MIGRATIONS = MIGRATIONS
+    UPSERT_CHECKPOINT_BLOBS_SQL = UPSERT_CHECKPOINT_BLOBS_SQL
+    UPSERT_CHECKPOINTS_SQL = UPSERT_CHECKPOINTS_SQL
+    UPSERT_CHECKPOINT_WRITES_SQL = UPSERT_CHECKPOINT_WRITES_SQL
+    INSERT_CHECKPOINT_WRITES_SQL = INSERT_CHECKPOINT_WRITES_SQL
+    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["AsyncShallowPostgresSaver"]:
+        """Create a new AsyncShallowPostgresSaver instance from a connection string.
+
+        Args:
+            conn_string (str): The Postgres connection info string.
+            pipeline (bool): whether to use AsyncPipeline
+
+        Returns:
+            AsyncShallowPostgresSaver: A new AsyncShallowPostgresSaver 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. For ShallowPostgresSaver, this method returns a list with
+        ONLY the most recent checkpoint.
+        """
+        where, args = self._search_where(config, filter, before)
+        query = self.SELECT_SQL + where
+        if limit:
+            query += f" LIMIT {limit}"
+        async with self._cursor() as cur:
+            await cur.execute(self.SELECT_SQL + where, args, binary=True)
+            async for value in cur:
+                checkpoint = await asyncio.to_thread(
+                    self._load_checkpoint,
+                    value["checkpoint"],
+                    value["channel_values"],
+                    value["pending_sends"],
+                )
+                yield CheckpointTuple(
+                    config={
+                        "configurable": {
+                            "thread_id": value["thread_id"],
+                            "checkpoint_ns": value["checkpoint_ns"],
+                            "checkpoint_id": checkpoint["id"],
+                        }
+                    },
+                    checkpoint=checkpoint,
+                    metadata=self._load_metadata(value["metadata"]),
+                    pending_writes=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 (matching the thread ID in the config).
+
+        Args:
+            config (RunnableConfig): 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_ns = config["configurable"].get("checkpoint_ns", "")
+        args = (thread_id, checkpoint_ns)
+        where = "WHERE thread_id = %s AND checkpoint_ns = %s"
+
+        async with self._cursor() as cur:
+            await cur.execute(
+                self.SELECT_SQL + where,
+                args,
+                binary=True,
+            )
+
+            async for value in cur:
+                checkpoint = await asyncio.to_thread(
+                    self._load_checkpoint,
+                    value["checkpoint"],
+                    value["channel_values"],
+                    value["pending_sends"],
+                )
+                return CheckpointTuple(
+                    config={
+                        "configurable": {
+                            "thread_id": thread_id,
+                            "checkpoint_ns": checkpoint_ns,
+                            "checkpoint_id": checkpoint["id"],
+                        }
+                    },
+                    checkpoint=checkpoint,
+                    metadata=self._load_metadata(value["metadata"]),
+                    pending_writes=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. For AsyncShallowPostgresSaver, this method saves ONLY the most recent
+        checkpoint and overwrites a previous checkpoint, if it exists.
+
+        Args:
+            config (RunnableConfig): The config to associate with the checkpoint.
+            checkpoint (Checkpoint): The checkpoint to save.
+            metadata (CheckpointMetadata): Additional metadata to save with the checkpoint.
+            new_versions (ChannelVersions): 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")
+
+        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.execute(
+                """DELETE FROM checkpoint_writes
+                WHERE thread_id = %s AND checkpoint_ns = %s AND checkpoint_id NOT IN (%s, %s)""",
+                (
+                    thread_id,
+                    checkpoint_ns,
+                    checkpoint["id"],
+                    configurable.get("checkpoint_id", ""),
+                ),
+            )
+            await cur.executemany(
+                self.UPSERT_CHECKPOINT_BLOBS_SQL,
+                _dump_blobs(
+                    self.serde,
+                    thread_id,
+                    checkpoint_ns,
+                    copy.pop("channel_values"),  # type: ignore[misc]
+                    new_versions,
+                ),
+            )
+            await cur.execute(
+                self.UPSERT_CHECKPOINTS_SQL,
+                (
+                    thread_id,
+                    checkpoint_ns,
+                    Jsonb(self._dump_checkpoint(copy)),
+                    self._dump_metadata(metadata),
+                ),
+            )
+        return next_config
+
+    async def aput_writes(
+        self,
+        config: RunnableConfig,
+        writes: Sequence[tuple[str, Any]],
+        task_id: str,
+    ) -> None:
+        """Store intermediate writes linked to a checkpoint asynchronously.
+
+        This method saves intermediate writes associated with a checkpoint to the database.
+
+        Args:
+            config (RunnableConfig): Configuration of the related checkpoint.
+            writes (Sequence[Tuple[str, Any]]): List of writes to store, each as (channel, value) pair.
+            task_id (str): 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,
+            writes,
+        )
+        async with self._cursor(pipeline=True) as cur:
+            await cur.executemany(query, params)
+
+    @asynccontextmanager
+    async def _cursor(
+        self, *, pipeline: bool = False
+    ) -> AsyncIterator[AsyncCursor[DictRow]]:
+        """Create a database cursor as a context manager.
+
+        Args:
+            pipeline (bool): whether to use pipeline for the DB operations inside the context manager.
+                Will be applied regardless of whether the AsyncShallowPostgresSaver 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. For ShallowPostgresSaver, this method returns a list with
+        ONLY the most recent checkpoint.
+        """
+        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 (matching the thread ID in the config).
+
+        Args:
+            config (RunnableConfig): 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 AsyncShallowPostgresSaver 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. For AsyncShallowPostgresSaver, this method saves ONLY the most recent
+        checkpoint and overwrites a previous checkpoint, if it exists.
+
+        Args:
+            config (RunnableConfig): The config to associate with the checkpoint.
+            checkpoint (Checkpoint): The checkpoint to save.
+            metadata (CheckpointMetadata): Additional metadata to save with the checkpoint.
+            new_versions (ChannelVersions): 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,
+    ) -> None:
+        """Store intermediate writes linked to a checkpoint.
+
+        This method saves intermediate writes associated with a checkpoint to the database.
+
+        Args:
+            config (RunnableConfig): Configuration of the related checkpoint.
+            writes (Sequence[Tuple[str, Any]]): List of writes to store, each as (channel, value) pair.
+            task_id (str): Identifier for the task creating the writes.
+        """
+        return asyncio.run_coroutine_threadsafe(
+            self.aput_writes(config, writes, task_id), self.loop
+        ).result()

{langgraph_checkpoint_postgres-2.0.7 → langgraph_checkpoint_postgres-2.0.9}/langgraph/store/postgres/aio.py

@@ -6,7 +6,6 @@ from typing import Any, Callable, Optional, Union, cast
 
 import orjson
 from psycopg import AsyncConnection, AsyncCursor, AsyncPipeline, Capabilities
-from psycopg.errors import UndefinedTable
 from psycopg.rows import DictRow, dict_row
 from psycopg_pool import AsyncConnectionPool
 
@@ -37,6 +36,75 @@ logger = logging.getLogger(__name__)
 
 
 class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Conn]):
+    """Asynchronous Postgres-backed store with optional vector search using pgvector.
+
+    !!! example "Examples"
+        Basic setup and key-value storage:
+        ```python
+        from langgraph.store.postgres import AsyncPostgresStore
+
+        async with AsyncPostgresStore.from_conn_string(
+            "postgresql://user:pass@localhost:5432/dbname"
+        ) as store:
+            await store.setup()
+
+            # Store and retrieve data
+            await store.aput(("users", "123"), "prefs", {"theme": "dark"})
+            item = await store.aget(("users", "123"), "prefs")
+        ```
+
+        Vector search using LangChain embeddings:
+        ```python
+        from langchain.embeddings import init_embeddings
+        from langgraph.store.postgres import AsyncPostgresStore
+
+        async with AsyncPostgresStore.from_conn_string(
+            "postgresql://user:pass@localhost:5432/dbname",
+            index={
+                "dims": 1536,
+                "embed": init_embeddings("openai:text-embedding-3-small"),
+                "fields": ["text"]  # specify which fields to embed. Default is the whole serialized value
+            }
+        ) as store:
+            await store.setup()  # Do this once to run migrations
+
+            # Store documents
+            await store.aput(("docs",), "doc1", {"text": "Python tutorial"})
+            await store.aput(("docs",), "doc2", {"text": "TypeScript guide"})
+            # Don't index the following
+            await store.aput(("docs",), "doc3", {"text": "Other guide"}, index=False)
+
+            # Search by similarity
+            results = await store.asearch(("docs",), query="python programming")
+        ```
+
+        Using connection pooling for better performance:
+        ```python
+        from langgraph.store.postgres import AsyncPostgresStore, PoolConfig
+
+        async with AsyncPostgresStore.from_conn_string(
+            "postgresql://user:pass@localhost:5432/dbname",
+            pool_config=PoolConfig(
+                min_size=5,
+                max_size=20
+            )
+        ) as store:
+            await store.setup()
+            # Use store with connection pooling...
+        ```
+
+    Warning:
+        Make sure to:
+        1. Call `setup()` before first use to create necessary tables and indexes
+        2. Have the pgvector extension available to use vector search
+        3. Use Python 3.10+ for async functionality
+
+    Note:
+        Semantic search is disabled by default. You can enable it by providing an `index` configuration
+        when creating the store. Without this configuration, all `index` arguments passed to
+        `put` or `aput`will have no effect.
+    """
+
     __slots__ = (
         "_deserializer",
         "pipe",
@@ -87,9 +155,6 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
 
         return results
 
-    def batch(self, ops: Iterable[Op]) -> list[Result]:
-        return asyncio.run_coroutine_threadsafe(self.abatch(ops), self.loop).result()
-
     @classmethod
     @asynccontextmanager
     async def from_conn_string(
@@ -150,22 +215,19 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
         """
 
         async def _get_version(cur: AsyncCursor[DictRow], table: str) -> int:
-            try:
-                await cur.execute(f"SELECT v FROM {table} ORDER BY v DESC LIMIT 1")
-                row = await cur.fetchone()
-                if row is None:
-                    version = -1
-                else:
-                    version = row["v"]
-            except UndefinedTable:
-                version = -1
-                await cur.execute(
-                    f"""
-                    CREATE TABLE IF NOT EXISTS {table} (
-                        v INTEGER PRIMARY KEY
-                    )
-                """
+            await cur.execute(
+                f"""
+                CREATE TABLE IF NOT EXISTS {table} (
+                    v INTEGER PRIMARY KEY
                 )
+            """
+            )
+            await cur.execute(f"SELECT v FROM {table} ORDER BY v DESC LIMIT 1")
+            row = cast(dict, await cur.fetchone())
+            if row is None:
+                version = -1
+            else:
+                version = row["v"]
             return version
 
         async with self._cursor() as cur:

{langgraph_checkpoint_postgres-2.0.7 → langgraph_checkpoint_postgres-2.0.9}/langgraph/store/postgres/base.py

@@ -21,7 +21,6 @@ from typing import (
 
 import orjson
 from psycopg import Capabilities, Connection, Cursor, Pipeline
-from psycopg.errors import UndefinedTable
 from psycopg.rows import DictRow, dict_row
 from psycopg.types.json import Jsonb
 from psycopg_pool import ConnectionPool
@@ -73,7 +72,7 @@ CREATE TABLE IF NOT EXISTS store (
 """,
     """
 -- For faster lookups by prefix
-CREATE INDEX IF NOT EXISTS store_prefix_idx ON store USING btree (prefix text_pattern_ops);
+CREATE INDEX CONCURRENTLY IF NOT EXISTS store_prefix_idx ON store USING btree (prefix text_pattern_ops);
 """,
 ]
 
@@ -107,7 +106,7 @@ CREATE TABLE IF NOT EXISTS store_vectors (
     ),
     Migration(
         """
-CREATE INDEX IF NOT EXISTS store_vectors_embedding_idx ON store_vectors 
+CREATE INDEX CONCURRENTLY IF NOT EXISTS store_vectors_embedding_idx ON store_vectors 
     USING %(index_type)s (embedding %(ops)s)%(index_params)s;
 """,
         condition=lambda store: bool(
@@ -534,6 +533,58 @@ class BasePostgresStore(Generic[C]):
 
 
 class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
+    """Postgres-backed store with optional vector search using pgvector.
+
+    !!! example "Examples"
+        Basic setup and key-value storage:
+        ```python
+        from langgraph.store.postgres import PostgresStore
+
+        store = PostgresStore(
+            connection_string="postgresql://user:pass@localhost:5432/dbname"
+        )
+        store.setup()
+
+        # Store and retrieve data
+        store.put(("users", "123"), "prefs", {"theme": "dark"})
+        item = store.get(("users", "123"), "prefs")
+        ```
+
+        Vector search using LangChain embeddings:
+        ```python
+        from langchain.embeddings import init_embeddings
+        from langgraph.store.postgres import PostgresStore
+
+        store = PostgresStore(
+            connection_string="postgresql://user:pass@localhost:5432/dbname",
+            index={
+                "dims": 1536,
+                "embed": init_embeddings("openai:text-embedding-3-small"),
+                "fields": ["text"]  # specify which fields to embed. Default is the whole serialized value
+            }
+        )
+        store.setup() # Do this once to run migrations
+
+        # Store documents
+        store.put(("docs",), "doc1", {"text": "Python tutorial"})
+        store.put(("docs",), "doc2", {"text": "TypeScript guide"})
+        store.put(("docs",), "doc2", {"text": "Other guide"}, index=False) # don't index
+
+        # Search by similarity
+        results = store.search(("docs",), query="python programming")
+        ```
+
+    Note:
+        Semantic search is disabled by default. You can enable it by providing an `index` configuration
+        when creating the store. Without this configuration, all `index` arguments passed to
+        `put` or `aput`will have no effect.
+
+    Warning:
+        Make sure to call `setup()` before first use to create necessary tables and indexes.
+        The pgvector extension must be available to use vector search.
+
+    """
+
     __slots__ = (
         "_deserializer",
         "pipe",
@@ -795,22 +846,19 @@ class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
         """
 
         def _get_version(cur: Cursor[dict[str, Any]], table: str) -> int:
-            try:
-                cur.execute(f"SELECT v FROM {table} ORDER BY v DESC LIMIT 1")
-                row = cast(dict, cur.fetchone())
-                if row is None:
-                    version = -1
-                else:
-                    version = row["v"]
-            except UndefinedTable:
-                version = -1
-                cur.execute(
-                    f"""
-                    CREATE TABLE IF NOT EXISTS {table} (
-                        v INTEGER PRIMARY KEY
-                    )
-                """
+            cur.execute(
+                f"""
+                CREATE TABLE IF NOT EXISTS {table} (
+                    v INTEGER PRIMARY KEY
                 )
+            """
+            )
+            cur.execute(f"SELECT v FROM {table} ORDER BY v DESC LIMIT 1")
+            row = cast(dict, cur.fetchone())
+            if row is None:
+                version = -1
+            else:
+                version = row["v"]
             return version
 
         with self._cursor() as cur:

{langgraph_checkpoint_postgres-2.0.7 → langgraph_checkpoint_postgres-2.0.9}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langgraph-checkpoint-postgres"
-version = "2.0.7"
+version = "2.0.9"
 description = "Library with a Postgres implementation of LangGraph checkpoint saver."
 authors = []
 license = "MIT"