Remove sqlite

This commit is contained in:
Nuno Campos
2025-03-01 10:14:10 -08:00
parent b9fe53777f
commit 25fea591b5
11 changed files with 0 additions and 2715 deletions
-35
View File
@@ -1,35 +0,0 @@
.PHONY: test test_watch lint format
######################
# TESTING AND COVERAGE
######################
test:
poetry run pytest tests
test_watch:
poetry run ptw .
######################
# LINTING AND FORMATTING
######################
# Define a variable for Python and notebook files.
PYTHON_FILES=.
MYPY_CACHE=.mypy_cache
lint format: PYTHON_FILES=.
lint_diff format_diff: PYTHON_FILES=$(shell git diff --name-only --relative --diff-filter=d main . | grep -E '\.py$$|\.ipynb$$')
lint_package: PYTHON_FILES=langgraph
lint_tests: PYTHON_FILES=tests
lint_tests: MYPY_CACHE=.mypy_cache_test
lint lint_diff lint_package lint_tests:
poetry run ruff check .
[ "$(PYTHON_FILES)" = "" ] || poetry run ruff format $(PYTHON_FILES) --diff
[ "$(PYTHON_FILES)" = "" ] || poetry run ruff check --select I $(PYTHON_FILES)
[ "$(PYTHON_FILES)" = "" ] || mkdir -p $(MYPY_CACHE)
[ "$(PYTHON_FILES)" = "" ] || poetry run mypy $(PYTHON_FILES) --cache-dir $(MYPY_CACHE)
format format_diff:
poetry run ruff format $(PYTHON_FILES)
poetry run ruff check --select I --fix $(PYTHON_FILES)
-90
View File
@@ -1,90 +0,0 @@
# LangGraph SQLite Checkpoint
Implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via `aiosqlite`)
## Usage
```python
from langgraph.checkpoint.sqlite import SqliteSaver
write_config = {"configurable": {"thread_id": "1", "checkpoint_ns": ""}}
read_config = {"configurable": {"thread_id": "1"}}
with SqliteSaver.from_conn_string(":memory:") as checkpointer:
checkpoint = {
"v": 1,
"ts": "2024-07-31T20:14:19.804150+00:00",
"id": "1ef4f797-8335-6428-8001-8a1503f9b875",
"channel_values": {
"my_key": "meow",
"node": "node"
},
"channel_versions": {
"__start__": 2,
"my_key": 3,
"start:node": 3,
"node": 3
},
"versions_seen": {
"__input__": {},
"__start__": {
"__start__": 1
},
"node": {
"start:node": 2
}
},
"pending_sends": [],
}
# store checkpoint
checkpointer.put(write_config, checkpoint, {}, {})
# load checkpoint
checkpointer.get(read_config)
# list checkpoints
list(checkpointer.list(read_config))
```
### Async
```python
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
async with AsyncSqliteSaver.from_conn_string(":memory:") as checkpointer:
checkpoint = {
"v": 1,
"ts": "2024-07-31T20:14:19.804150+00:00",
"id": "1ef4f797-8335-6428-8001-8a1503f9b875",
"channel_values": {
"my_key": "meow",
"node": "node"
},
"channel_versions": {
"__start__": 2,
"my_key": 3,
"start:node": 3,
"node": 3
},
"versions_seen": {
"__input__": {},
"__start__": {
"__start__": 1
},
"node": {
"start:node": 2
}
},
"pending_sends": [],
}
# store checkpoint
await checkpointer.aput(write_config, checkpoint, {}, {})
# load checkpoint
await checkpointer.aget(read_config)
# list checkpoints
[c async for c in checkpointer.alist(read_config)]
```
@@ -1,525 +0,0 @@
import random
import sqlite3
import threading
from contextlib import closing, contextmanager
from typing import Any, AsyncIterator, Dict, Iterator, Optional, Sequence, Tuple
from langchain_core.runnables import RunnableConfig
from langgraph.checkpoint.base import (
WRITES_IDX_MAP,
BaseCheckpointSaver,
ChannelVersions,
Checkpoint,
CheckpointMetadata,
CheckpointTuple,
SerializerProtocol,
get_checkpoint_id,
get_checkpoint_metadata,
)
from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
from langgraph.checkpoint.serde.types import ChannelProtocol
from langgraph.checkpoint.sqlite.utils import search_where
_AIO_ERROR_MSG = (
"The SqliteSaver does not support async methods. "
"Consider using AsyncSqliteSaver instead.\n"
"from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver\n"
"Note: AsyncSqliteSaver requires the aiosqlite package to use.\n"
"Install with:\n`pip install aiosqlite`\n"
"See https://langchain-ai.github.io/langgraph/reference/checkpoints/asyncsqlitesaver"
"for more information."
)
class SqliteSaver(BaseCheckpointSaver[str]):
"""A checkpoint saver that stores checkpoints in a SQLite database.
Note:
This class is meant for lightweight, synchronous use cases
(demos and small projects) and does not
scale to multiple threads.
For a similar sqlite saver with `async` support,
consider using [AsyncSqliteSaver][langgraph.checkpoint.sqlite.aio.AsyncSqliteSaver].
Args:
conn (sqlite3.Connection): The SQLite database connection.
serde (Optional[SerializerProtocol]): The serializer to use for serializing and deserializing checkpoints. Defaults to JsonPlusSerializerCompat.
Examples:
>>> import sqlite3
>>> from langgraph.checkpoint.sqlite import SqliteSaver
>>> from langgraph.graph import StateGraph
>>>
>>> builder = StateGraph(int)
>>> builder.add_node("add_one", lambda x: x + 1)
>>> builder.set_entry_point("add_one")
>>> builder.set_finish_point("add_one")
>>> conn = sqlite3.connect("checkpoints.sqlite")
>>> memory = SqliteSaver(conn)
>>> graph = builder.compile(checkpointer=memory)
>>> config = {"configurable": {"thread_id": "1"}}
>>> graph.get_state(config)
>>> result = graph.invoke(3, config)
>>> graph.get_state(config)
StateSnapshot(values=4, next=(), config={'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '0c62ca34-ac19-445d-bbb0-5b4984975b2a'}}, parent_config=None)
""" # noqa
conn: sqlite3.Connection
is_setup: bool
def __init__(
self,
conn: sqlite3.Connection,
*,
serde: Optional[SerializerProtocol] = None,
) -> None:
super().__init__(serde=serde)
self.jsonplus_serde = JsonPlusSerializer()
self.conn = conn
self.is_setup = False
self.lock = threading.Lock()
@classmethod
@contextmanager
def from_conn_string(cls, conn_string: str) -> Iterator["SqliteSaver"]:
"""Create a new SqliteSaver instance from a connection string.
Args:
conn_string (str): The SQLite connection string.
Yields:
SqliteSaver: A new SqliteSaver instance.
Examples:
In memory:
with SqliteSaver.from_conn_string(":memory:") as memory:
...
To disk:
with SqliteSaver.from_conn_string("checkpoints.sqlite") as memory:
...
"""
with closing(
sqlite3.connect(
conn_string,
# https://ricardoanderegg.com/posts/python-sqlite-thread-safety/
check_same_thread=False,
)
) as conn:
yield cls(conn)
def setup(self) -> None:
"""Set up the checkpoint database.
This method creates the necessary tables in the SQLite database if they don't
already exist. It is called automatically when needed and should not be called
directly by the user.
"""
if self.is_setup:
return
self.conn.executescript(
"""
PRAGMA journal_mode=WAL;
CREATE TABLE IF NOT EXISTS checkpoints (
thread_id TEXT NOT NULL,
checkpoint_ns TEXT NOT NULL DEFAULT '',
checkpoint_id TEXT NOT NULL,
parent_checkpoint_id TEXT,
type TEXT,
checkpoint BLOB,
metadata BLOB,
PRIMARY KEY (thread_id, checkpoint_ns, checkpoint_id)
);
CREATE TABLE IF NOT EXISTS 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,
value BLOB,
PRIMARY KEY (thread_id, checkpoint_ns, checkpoint_id, task_id, idx)
);
"""
)
self.is_setup = True
@contextmanager
def cursor(self, transaction: bool = True) -> Iterator[sqlite3.Cursor]:
"""Get a cursor for the SQLite database.
This method returns a cursor for the SQLite database. It is used internally
by the SqliteSaver and should not be called directly by the user.
Args:
transaction (bool): Whether to commit the transaction when the cursor is closed. Defaults to True.
Yields:
sqlite3.Cursor: A cursor for the SQLite database.
"""
with self.lock:
self.setup()
cur = self.conn.cursor()
try:
yield cur
finally:
if transaction:
self.conn.commit()
cur.close()
def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
"""Get a checkpoint tuple from the database.
This method retrieves a checkpoint tuple from the SQLite 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 (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 checkpoint ID:
>>> 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
checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
with self.cursor(transaction=False) as cur:
# find the latest checkpoint for the thread_id
if checkpoint_id := get_checkpoint_id(config):
cur.execute(
"SELECT thread_id, checkpoint_id, parent_checkpoint_id, type, checkpoint, metadata FROM checkpoints WHERE thread_id = ? AND checkpoint_ns = ? AND checkpoint_id = ?",
(
str(config["configurable"]["thread_id"]),
checkpoint_ns,
checkpoint_id,
),
)
else:
cur.execute(
"SELECT thread_id, checkpoint_id, parent_checkpoint_id, type, checkpoint, metadata FROM checkpoints WHERE thread_id = ? AND checkpoint_ns = ? ORDER BY checkpoint_id DESC LIMIT 1",
(str(config["configurable"]["thread_id"]), checkpoint_ns),
)
# if a checkpoint is found, return it
if value := cur.fetchone():
(
thread_id,
checkpoint_id,
parent_checkpoint_id,
type,
checkpoint,
metadata,
) = value
if not get_checkpoint_id(config):
config = {
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": checkpoint_id,
}
}
# find any pending writes
cur.execute(
"SELECT task_id, channel, type, value FROM writes WHERE thread_id = ? AND checkpoint_ns = ? AND checkpoint_id = ? ORDER BY task_id, idx",
(
str(config["configurable"]["thread_id"]),
checkpoint_ns,
str(config["configurable"]["checkpoint_id"]),
),
)
# deserialize the checkpoint and metadata
return CheckpointTuple(
config,
self.serde.loads_typed((type, checkpoint)),
self.jsonplus_serde.loads(metadata) if metadata is not None else {},
(
{
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": parent_checkpoint_id,
}
}
if parent_checkpoint_id
else None
),
[
(task_id, channel, self.serde.loads_typed((type, value)))
for task_id, channel, type, value in 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 SQLite database based
on the provided config. The checkpoints are ordered by checkpoint ID in descending order (newest first).
Args:
config (RunnableConfig): The config to use for listing the checkpoints.
filter (Optional[Dict[str, Any]]): Additional filtering criteria for metadata. Defaults to None.
before (Optional[RunnableConfig]): If provided, only checkpoints before the specified checkpoint ID are returned. Defaults to None.
limit (Optional[int]): The maximum number of checkpoints to return. Defaults to None.
Yields:
Iterator[CheckpointTuple]: An iterator of checkpoint tuples.
Examples:
>>> from langgraph.checkpoint.sqlite import SqliteSaver
>>> with SqliteSaver.from_conn_string(":memory:") as memory:
... # Run a graph, then list the checkpoints
>>> config = {"configurable": {"thread_id": "1"}}
>>> checkpoints = list(memory.list(config, limit=2))
>>> print(checkpoints)
[CheckpointTuple(...), CheckpointTuple(...)]
>>> config = {"configurable": {"thread_id": "1"}}
>>> before = {"configurable": {"checkpoint_id": "1ef4f797-8335-6428-8001-8a1503f9b875"}}
>>> with SqliteSaver.from_conn_string(":memory:") as memory:
... # Run a graph, then list the checkpoints
>>> checkpoints = list(memory.list(config, before=before))
>>> print(checkpoints)
[CheckpointTuple(...), ...]
"""
where, param_values = search_where(config, filter, before)
query = f"""SELECT thread_id, checkpoint_ns, checkpoint_id, parent_checkpoint_id, type, checkpoint, metadata
FROM checkpoints
{where}
ORDER BY checkpoint_id DESC"""
if limit:
query += f" LIMIT {limit}"
with self.cursor(transaction=False) as cur, closing(self.conn.cursor()) as wcur:
cur.execute(query, param_values)
for (
thread_id,
checkpoint_ns,
checkpoint_id,
parent_checkpoint_id,
type,
checkpoint,
metadata,
) in cur:
wcur.execute(
"SELECT task_id, channel, type, value FROM writes WHERE thread_id = ? AND checkpoint_ns = ? AND checkpoint_id = ? ORDER BY task_id, idx",
(thread_id, checkpoint_ns, checkpoint_id),
)
yield CheckpointTuple(
{
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": checkpoint_id,
}
},
self.serde.loads_typed((type, checkpoint)),
self.jsonplus_serde.loads(metadata) if metadata is not None else {},
(
{
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": parent_checkpoint_id,
}
}
if parent_checkpoint_id
else None
),
[
(task_id, channel, self.serde.loads_typed((type, value)))
for task_id, channel, type, value in wcur
],
)
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 SQLite database. The checkpoint is associated
with the provided config and its parent config (if any).
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.sqlite import SqliteSaver
>>> with SqliteSaver.from_conn_string(":memory:") 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'}}
"""
thread_id = config["configurable"]["thread_id"]
checkpoint_ns = config["configurable"]["checkpoint_ns"]
type_, serialized_checkpoint = self.serde.dumps_typed(checkpoint)
serialized_metadata = self.jsonplus_serde.dumps(
get_checkpoint_metadata(config, metadata)
)
with self.cursor() as cur:
cur.execute(
"INSERT OR REPLACE INTO checkpoints (thread_id, checkpoint_ns, checkpoint_id, parent_checkpoint_id, type, checkpoint, metadata) VALUES (?, ?, ?, ?, ?, ?, ?)",
(
str(config["configurable"]["thread_id"]),
checkpoint_ns,
checkpoint["id"],
config["configurable"].get("checkpoint_id"),
type_,
serialized_checkpoint,
serialized_metadata,
),
)
return {
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": checkpoint["id"],
}
}
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 SQLite 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.
task_path (str): Path of the task creating the writes.
"""
query = (
"INSERT OR REPLACE INTO writes (thread_id, checkpoint_ns, checkpoint_id, task_id, idx, channel, type, value) VALUES (?, ?, ?, ?, ?, ?, ?, ?)"
if all(w[0] in WRITES_IDX_MAP for w in writes)
else "INSERT OR IGNORE INTO writes (thread_id, checkpoint_ns, checkpoint_id, task_id, idx, channel, type, value) VALUES (?, ?, ?, ?, ?, ?, ?, ?)"
)
with self.cursor() as cur:
cur.executemany(
query,
[
(
str(config["configurable"]["thread_id"]),
str(config["configurable"]["checkpoint_ns"]),
str(config["configurable"]["checkpoint_id"]),
task_id,
WRITES_IDX_MAP.get(channel, idx),
channel,
*self.serde.dumps_typed(value),
)
for idx, (channel, value) in enumerate(writes)
],
)
async def aget_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
"""Get a checkpoint tuple from the database asynchronously.
Note:
This async method is not supported by the SqliteSaver class.
Use get_tuple() instead, or consider using [AsyncSqliteSaver][langgraph.checkpoint.sqlite.aio.AsyncSqliteSaver].
"""
raise NotImplementedError(_AIO_ERROR_MSG)
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.
Note:
This async method is not supported by the SqliteSaver class.
Use list() instead, or consider using [AsyncSqliteSaver][langgraph.checkpoint.sqlite.aio.AsyncSqliteSaver].
"""
raise NotImplementedError(_AIO_ERROR_MSG)
yield
async def aput(
self,
config: RunnableConfig,
checkpoint: Checkpoint,
metadata: CheckpointMetadata,
new_versions: ChannelVersions,
) -> RunnableConfig:
"""Save a checkpoint to the database asynchronously.
Note:
This async method is not supported by the SqliteSaver class.
Use put() instead, or consider using [AsyncSqliteSaver][langgraph.checkpoint.sqlite.aio.AsyncSqliteSaver].
"""
raise NotImplementedError(_AIO_ERROR_MSG)
def get_next_version(self, current: Optional[str], channel: ChannelProtocol) -> str:
"""Generate the next version ID for a channel.
This method creates a new version identifier for a channel based on its current version.
Args:
current (Optional[str]): The current version identifier of the channel.
channel (BaseChannel): The channel being versioned.
Returns:
str: The next version identifier, which is guaranteed to be monotonically increasing.
"""
if current is None:
current_v = 0
elif isinstance(current, int):
current_v = current
else:
current_v = int(current.split(".")[0])
next_v = current_v + 1
next_h = random.random()
return f"{next_v:032}.{next_h:016}"
@@ -1,554 +0,0 @@
import asyncio
import random
from collections.abc import AsyncIterator, Iterator, Sequence
from contextlib import asynccontextmanager
from typing import Any, Callable, Optional, TypeVar
import aiosqlite
from langchain_core.runnables import RunnableConfig
from langgraph.checkpoint.base import (
WRITES_IDX_MAP,
BaseCheckpointSaver,
ChannelVersions,
Checkpoint,
CheckpointMetadata,
CheckpointTuple,
SerializerProtocol,
get_checkpoint_id,
get_checkpoint_metadata,
)
from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
from langgraph.checkpoint.serde.types import ChannelProtocol
from langgraph.checkpoint.sqlite.utils import search_where
T = TypeVar("T", bound=Callable)
class AsyncSqliteSaver(BaseCheckpointSaver[str]):
"""An asynchronous checkpoint saver that stores checkpoints in a SQLite database.
This class provides an asynchronous interface for saving and retrieving checkpoints
using a SQLite database. It's designed for use in asynchronous environments and
offers better performance for I/O-bound operations compared to synchronous alternatives.
Attributes:
conn (aiosqlite.Connection): The asynchronous SQLite database connection.
serde (SerializerProtocol): The serializer used for encoding/decoding checkpoints.
Tip:
Requires the [aiosqlite](https://pypi.org/project/aiosqlite/) package.
Install it with `pip install aiosqlite`.
Warning:
While this class supports asynchronous checkpointing, it is not recommended
for production workloads due to limitations in SQLite's write performance.
For production use, consider a more robust database like PostgreSQL.
Tip:
Remember to **close the database connection** after executing your code,
otherwise, you may see the graph "hang" after execution (since the program
will not exit until the connection is closed).
The easiest way is to use the `async with` statement as shown in the examples.
```python
async with AsyncSqliteSaver.from_conn_string("checkpoints.sqlite") as saver:
# Your code here
graph = builder.compile(checkpointer=saver)
config = {"configurable": {"thread_id": "thread-1"}}
async for event in graph.astream_events(..., config, version="v1"):
print(event)
```
Examples:
Usage within StateGraph:
```pycon
>>> import asyncio
>>>
>>> from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
>>> from langgraph.graph import StateGraph
>>>
>>> builder = StateGraph(int)
>>> builder.add_node("add_one", lambda x: x + 1)
>>> builder.set_entry_point("add_one")
>>> builder.set_finish_point("add_one")
>>> async with AsyncSqliteSaver.from_conn_string("checkpoints.db") as memory:
>>> graph = builder.compile(checkpointer=memory)
>>> coro = graph.ainvoke(1, {"configurable": {"thread_id": "thread-1"}})
>>> print(asyncio.run(coro))
Output: 2
```
Raw usage:
```pycon
>>> import asyncio
>>> import aiosqlite
>>> from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
>>>
>>> async def main():
>>> async with aiosqlite.connect("checkpoints.db") as conn:
... saver = AsyncSqliteSaver(conn)
... config = {"configurable": {"thread_id": "1"}}
... checkpoint = {"ts": "2023-05-03T10:00:00Z", "data": {"key": "value"}}
... saved_config = await saver.aput(config, checkpoint, {}, {})
... print(saved_config)
>>> asyncio.run(main())
{"configurable": {"thread_id": "1", "checkpoint_id": "0c62ca34-ac19-445d-bbb0-5b4984975b2a"}}
```
"""
lock: asyncio.Lock
is_setup: bool
def __init__(
self,
conn: aiosqlite.Connection,
*,
serde: Optional[SerializerProtocol] = None,
):
super().__init__(serde=serde)
self.jsonplus_serde = JsonPlusSerializer()
self.conn = conn
self.lock = asyncio.Lock()
self.loop = asyncio.get_running_loop()
self.is_setup = False
@classmethod
@asynccontextmanager
async def from_conn_string(
cls, conn_string: str
) -> AsyncIterator["AsyncSqliteSaver"]:
"""Create a new AsyncSqliteSaver instance from a connection string.
Args:
conn_string (str): The SQLite connection string.
Yields:
AsyncSqliteSaver: A new AsyncSqliteSaver instance.
"""
async with aiosqlite.connect(conn_string) as conn:
yield cls(conn)
def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
"""Get a checkpoint tuple from the database.
This method retrieves a checkpoint tuple from the SQLite 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 (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 AsyncSqliteSaver 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 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 asynchronously.
This method retrieves a list of checkpoint tuples from the SQLite database based
on the provided config. The checkpoints are ordered by checkpoint ID in descending order (newest first).
Args:
config (Optional[RunnableConfig]): Base configuration for filtering checkpoints.
filter (Optional[Dict[str, Any]]): Additional filtering criteria for metadata.
before (Optional[RunnableConfig]): If provided, only checkpoints before the specified checkpoint ID are returned. Defaults to None.
limit (Optional[int]): 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 AsyncSqliteSaver 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 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 SQLite database. The checkpoint is associated
with the provided config and its parent config (if any).
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,
task_path: str = "",
) -> None:
return asyncio.run_coroutine_threadsafe(
self.aput_writes(config, writes, task_id, task_path), self.loop
).result()
async def setup(self) -> None:
"""Set up the checkpoint database asynchronously.
This method creates the necessary tables in the SQLite database if they don't
already exist. It is called automatically when needed and should not be called
directly by the user.
"""
async with self.lock:
if self.is_setup:
return
if not self.conn.is_alive():
await self.conn
async with self.conn.executescript(
"""
PRAGMA journal_mode=WAL;
CREATE TABLE IF NOT EXISTS checkpoints (
thread_id TEXT NOT NULL,
checkpoint_ns TEXT NOT NULL DEFAULT '',
checkpoint_id TEXT NOT NULL,
parent_checkpoint_id TEXT,
type TEXT,
checkpoint BLOB,
metadata BLOB,
PRIMARY KEY (thread_id, checkpoint_ns, checkpoint_id)
);
CREATE TABLE IF NOT EXISTS 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,
value BLOB,
PRIMARY KEY (thread_id, checkpoint_ns, checkpoint_id, task_id, idx)
);
"""
):
await self.conn.commit()
self.is_setup = True
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 SQLite 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 (RunnableConfig): The config to use for retrieving the checkpoint.
Returns:
Optional[CheckpointTuple]: The retrieved checkpoint tuple, or None if no matching checkpoint was found.
"""
await self.setup()
checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
async with self.lock, self.conn.cursor() as cur:
# find the latest checkpoint for the thread_id
if checkpoint_id := get_checkpoint_id(config):
await cur.execute(
"SELECT thread_id, checkpoint_id, parent_checkpoint_id, type, checkpoint, metadata FROM checkpoints WHERE thread_id = ? AND checkpoint_ns = ? AND checkpoint_id = ?",
(
str(config["configurable"]["thread_id"]),
checkpoint_ns,
checkpoint_id,
),
)
else:
await cur.execute(
"SELECT thread_id, checkpoint_id, parent_checkpoint_id, type, checkpoint, metadata FROM checkpoints WHERE thread_id = ? AND checkpoint_ns = ? ORDER BY checkpoint_id DESC LIMIT 1",
(str(config["configurable"]["thread_id"]), checkpoint_ns),
)
# if a checkpoint is found, return it
if value := await cur.fetchone():
(
thread_id,
checkpoint_id,
parent_checkpoint_id,
type,
checkpoint,
metadata,
) = value
if not get_checkpoint_id(config):
config = {
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": checkpoint_id,
}
}
# find any pending writes
await cur.execute(
"SELECT task_id, channel, type, value FROM writes WHERE thread_id = ? AND checkpoint_ns = ? AND checkpoint_id = ? ORDER BY task_id, idx",
(
str(config["configurable"]["thread_id"]),
checkpoint_ns,
str(config["configurable"]["checkpoint_id"]),
),
)
# deserialize the checkpoint and metadata
return CheckpointTuple(
config,
self.serde.loads_typed((type, checkpoint)),
self.jsonplus_serde.loads(metadata) if metadata is not None else {},
(
{
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": parent_checkpoint_id,
}
}
if parent_checkpoint_id
else None
),
[
(task_id, channel, self.serde.loads_typed((type, value)))
async for task_id, channel, type, value in cur
],
)
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 SQLite database based
on the provided config. The checkpoints are ordered by checkpoint ID in descending order (newest first).
Args:
config (Optional[RunnableConfig]): Base configuration for filtering checkpoints.
filter (Optional[Dict[str, Any]]): Additional filtering criteria for metadata.
before (Optional[RunnableConfig]): If provided, only checkpoints before the specified checkpoint ID are returned. Defaults to None.
limit (Optional[int]): Maximum number of checkpoints to return.
Yields:
AsyncIterator[CheckpointTuple]: An asynchronous iterator of matching checkpoint tuples.
"""
await self.setup()
where, params = search_where(config, filter, before)
query = f"""SELECT thread_id, checkpoint_ns, checkpoint_id, parent_checkpoint_id, type, checkpoint, metadata
FROM checkpoints
{where}
ORDER BY checkpoint_id DESC"""
if limit:
query += f" LIMIT {limit}"
async with (
self.lock,
self.conn.execute(query, params) as cur,
self.conn.cursor() as wcur,
):
async for (
thread_id,
checkpoint_ns,
checkpoint_id,
parent_checkpoint_id,
type,
checkpoint,
metadata,
) in cur:
await wcur.execute(
"SELECT task_id, channel, type, value FROM writes WHERE thread_id = ? AND checkpoint_ns = ? AND checkpoint_id = ? ORDER BY task_id, idx",
(thread_id, checkpoint_ns, checkpoint_id),
)
yield CheckpointTuple(
{
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": checkpoint_id,
}
},
self.serde.loads_typed((type, checkpoint)),
self.jsonplus_serde.loads(metadata) if metadata is not None else {},
(
{
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": parent_checkpoint_id,
}
}
if parent_checkpoint_id
else None
),
[
(task_id, channel, self.serde.loads_typed((type, value)))
async for task_id, channel, type, value in wcur
],
)
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 SQLite database. The checkpoint is associated
with the provided config and its parent config (if any).
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.
"""
await self.setup()
thread_id = config["configurable"]["thread_id"]
checkpoint_ns = config["configurable"]["checkpoint_ns"]
type_, serialized_checkpoint = self.serde.dumps_typed(checkpoint)
serialized_metadata = self.jsonplus_serde.dumps(
get_checkpoint_metadata(config, metadata)
)
async with (
self.lock,
self.conn.execute(
"INSERT OR REPLACE INTO checkpoints (thread_id, checkpoint_ns, checkpoint_id, parent_checkpoint_id, type, checkpoint, metadata) VALUES (?, ?, ?, ?, ?, ?, ?)",
(
str(config["configurable"]["thread_id"]),
checkpoint_ns,
checkpoint["id"],
config["configurable"].get("checkpoint_id"),
type_,
serialized_checkpoint,
serialized_metadata,
),
),
):
await self.conn.commit()
return {
"configurable": {
"thread_id": thread_id,
"checkpoint_ns": checkpoint_ns,
"checkpoint_id": checkpoint["id"],
}
}
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 (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.
task_path (str): Path of the task creating the writes.
"""
query = (
"INSERT OR REPLACE INTO writes (thread_id, checkpoint_ns, checkpoint_id, task_id, idx, channel, type, value) VALUES (?, ?, ?, ?, ?, ?, ?, ?)"
if all(w[0] in WRITES_IDX_MAP for w in writes)
else "INSERT OR IGNORE INTO writes (thread_id, checkpoint_ns, checkpoint_id, task_id, idx, channel, type, value) VALUES (?, ?, ?, ?, ?, ?, ?, ?)"
)
await self.setup()
async with self.lock, self.conn.cursor() as cur:
await cur.executemany(
query,
[
(
str(config["configurable"]["thread_id"]),
str(config["configurable"]["checkpoint_ns"]),
str(config["configurable"]["checkpoint_id"]),
task_id,
WRITES_IDX_MAP.get(channel, idx),
channel,
*self.serde.dumps_typed(value),
)
for idx, (channel, value) in enumerate(writes)
],
)
def get_next_version(self, current: Optional[str], channel: ChannelProtocol) -> str:
"""Generate the next version ID for a channel.
This method creates a new version identifier for a channel based on its current version.
Args:
current (Optional[str]): The current version identifier of the channel.
channel (BaseChannel): The channel being versioned.
Returns:
str: The next version identifier, which is guaranteed to be monotonically increasing.
"""
if current is None:
current_v = 0
elif isinstance(current, int):
current_v = current
else:
current_v = int(current.split(".")[0])
next_v = current_v + 1
next_h = random.random()
return f"{next_v:032}.{next_h:016}"
@@ -1,93 +0,0 @@
import json
from typing import Any, Dict, Optional, Sequence, Tuple
from langchain_core.runnables import RunnableConfig
from langgraph.checkpoint.base import get_checkpoint_id
def _metadata_predicate(
metadata_filter: Dict[str, Any],
) -> Tuple[Sequence[str], Sequence[Any]]:
"""Return WHERE clause predicates for (a)search() given metadata filter.
This method returns a tuple of a string and a tuple of values. The string
is the parametered WHERE clause predicate (excluding the WHERE keyword):
"column1 = ? AND column2 IS ?". The tuple of values contains the values
for each of the corresponding parameters.
"""
def _where_value(query_value: Any) -> Tuple[str, Any]:
"""Return tuple of operator and value for WHERE clause predicate."""
if query_value is None:
return ("IS ?", None)
elif (
isinstance(query_value, str)
or isinstance(query_value, int)
or isinstance(query_value, float)
):
return ("= ?", query_value)
elif isinstance(query_value, bool):
return ("= ?", 1 if query_value else 0)
elif isinstance(query_value, dict) or isinstance(query_value, list):
# query value for JSON object cannot have trailing space after separators (, :)
# SQLite json_extract() returns JSON string without whitespace
return ("= ?", json.dumps(query_value, separators=(",", ":")))
else:
return ("= ?", str(query_value))
predicates = []
param_values = []
# process metadata query
for query_key, query_value in metadata_filter.items():
operator, param_value = _where_value(query_value)
predicates.append(
f"json_extract(CAST(metadata AS TEXT), '$.{query_key}') {operator}"
)
param_values.append(param_value)
return (predicates, param_values)
def search_where(
config: Optional[RunnableConfig],
filter: Optional[Dict[str, Any]],
before: Optional[RunnableConfig] = None,
) -> Tuple[str, Sequence[Any]]:
"""Return WHERE clause predicates for (a)search() given metadata filter
and `before` config.
This method returns a tuple of a string and a tuple of values. The string
is the parametered WHERE clause predicate (including the WHERE keyword):
"WHERE column1 = ? AND column2 IS ?". The tuple of values contains the
values for each of the corresponding parameters.
"""
wheres = []
param_values = []
# construct predicate for config filter
if config is not None:
wheres.append("thread_id = ?")
param_values.append(config["configurable"]["thread_id"])
checkpoint_ns = config["configurable"].get("checkpoint_ns")
if checkpoint_ns is not None:
wheres.append("checkpoint_ns = ?")
param_values.append(checkpoint_ns)
if checkpoint_id := get_checkpoint_id(config):
wheres.append("checkpoint_id = ?")
param_values.append(checkpoint_id)
# construct predicate for metadata filter
if filter:
metadata_predicates, metadata_values = _metadata_predicate(filter)
wheres.extend(metadata_predicates)
param_values.extend(metadata_values)
# construct predicate for `before`
if before is not None:
wheres.append("checkpoint_id < ?")
param_values.append(get_checkpoint_id(before))
return ("WHERE " + " AND ".join(wheres) if wheres else "", param_values)
-1046
View File
File diff suppressed because it is too large Load Diff
-65
View File
@@ -1,65 +0,0 @@
[tool.poetry]
name = "langgraph-checkpoint-sqlite"
version = "2.0.5"
description = "Library with a SQLite implementation of LangGraph checkpoint saver."
authors = []
license = "MIT"
readme = "README.md"
repository = "https://www.github.com/langchain-ai/langgraph"
packages = [{ include = "langgraph" }]
[tool.poetry.dependencies]
python = "^3.9.0"
langgraph-checkpoint = "^2.0.15"
aiosqlite = ">=0.20,<0.22"
[tool.poetry.group.dev.dependencies]
ruff = "^0.6.2"
codespell = "^2.2.0"
pytest = "^7.2.1"
pytest-asyncio = "^0.21.1"
pytest-mock = "^3.11.1"
pytest-watcher = "^0.4.1"
mypy = "^1.10.0"
langgraph-checkpoint = {path = "../checkpoint", develop = true}
[tool.pytest.ini_options]
# --strict-markers will raise errors on unknown marks.
# https://docs.pytest.org/en/7.1.x/how-to/mark.html#raising-errors-on-unknown-marks
#
# https://docs.pytest.org/en/7.1.x/reference/reference.html
# --strict-config any warnings encountered while parsing the `pytest`
# section of the configuration file raise errors.
addopts = "--strict-markers --strict-config --durations=5 -vv"
asyncio_mode = "auto"
[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"
[tool.ruff]
lint.select = [
"E", # pycodestyle
"F", # Pyflakes
"UP", # pyupgrade
"B", # flake8-bugbear
"I", # isort
]
lint.ignore = ["E501", "B008", "UP007", "UP006"]
[tool.pytest-watcher]
now = true
delay = 0.1
runner_args = ["--ff", "-v", "--tb", "short"]
patterns = ["*.py"]
[tool.mypy]
# https://mypy.readthedocs.io/en/stable/config_file.html
disallow_untyped_defs = "True"
explicit_package_bases = "True"
warn_no_return = "False"
warn_unused_ignores = "True"
warn_redundant_casts = "True"
allow_redefinition = "True"
disable_error_code = "typeddict-item, return-value"
@@ -1,125 +0,0 @@
from typing import Any
import pytest
from langchain_core.runnables import RunnableConfig
from langgraph.checkpoint.base import (
Checkpoint,
CheckpointMetadata,
create_checkpoint,
empty_checkpoint,
)
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
class TestAsyncSqliteSaver:
@pytest.fixture(autouse=True)
def setup(self) -> None:
# objects for test setup
self.config_1: RunnableConfig = {
"configurable": {
"thread_id": "thread-1",
# for backwards compatibility testing
"thread_ts": "1",
"checkpoint_ns": "",
}
}
self.config_2: RunnableConfig = {
"configurable": {
"thread_id": "thread-2",
"checkpoint_id": "2",
"checkpoint_ns": "",
}
}
self.config_3: RunnableConfig = {
"configurable": {
"thread_id": "thread-2",
"checkpoint_id": "2-inner",
"checkpoint_ns": "inner",
}
}
self.chkpnt_1: Checkpoint = empty_checkpoint()
self.chkpnt_2: Checkpoint = create_checkpoint(self.chkpnt_1, {}, 1)
self.chkpnt_3: Checkpoint = empty_checkpoint()
self.metadata_1: CheckpointMetadata = {
"source": "input",
"step": 2,
"writes": {},
"score": 1,
}
self.metadata_2: CheckpointMetadata = {
"source": "loop",
"step": 1,
"writes": {"foo": "bar"},
"score": None,
}
self.metadata_3: CheckpointMetadata = {}
async def test_combined_metadata(self) -> None:
async with AsyncSqliteSaver.from_conn_string(":memory:") as saver:
config = {
"configurable": {
"thread_id": "thread-2",
"checkpoint_ns": "",
"__super_private_key": "super_private_value",
},
"metadata": {"run_id": "my_run_id"},
}
await saver.aput(config, self.chkpnt_2, self.metadata_2, {})
checkpoint = await saver.aget_tuple(config)
assert checkpoint.metadata == {
**self.metadata_2,
"thread_id": "thread-2",
"run_id": "my_run_id",
}
async def test_asearch(self) -> None:
async with AsyncSqliteSaver.from_conn_string(":memory:") as saver:
await saver.aput(self.config_1, self.chkpnt_1, self.metadata_1, {})
await saver.aput(self.config_2, self.chkpnt_2, self.metadata_2, {})
await saver.aput(self.config_3, self.chkpnt_3, self.metadata_3, {})
# call method / assertions
query_1 = {"source": "input"} # search by 1 key
query_2 = {
"step": 1,
"writes": {"foo": "bar"},
} # search by multiple keys
query_3: dict[str, Any] = {} # search by no keys, return all checkpoints
query_4 = {"source": "update", "step": 1} # no match
search_results_1 = [c async for c in saver.alist(None, filter=query_1)]
assert len(search_results_1) == 1
assert search_results_1[0].metadata == {
"thread_id": "thread-1",
"thread_ts": "1",
**self.metadata_1,
}
search_results_2 = [c async for c in saver.alist(None, filter=query_2)]
assert len(search_results_2) == 1
assert search_results_2[0].metadata == {
"thread_id": "thread-2",
**self.metadata_2,
}
search_results_3 = [c async for c in saver.alist(None, filter=query_3)]
assert len(search_results_3) == 3
search_results_4 = [c async for c in saver.alist(None, filter=query_4)]
assert len(search_results_4) == 0
# search by config (defaults to checkpoints across all namespaces)
search_results_5 = [
c
async for c in saver.alist({"configurable": {"thread_id": "thread-2"}})
]
assert len(search_results_5) == 2
assert {
search_results_5[0].config["configurable"]["checkpoint_ns"],
search_results_5[1].config["configurable"]["checkpoint_ns"],
} == {"", "inner"}
# TODO: test before and limit params
-182
View File
@@ -1,182 +0,0 @@
from typing import Any, cast
import pytest
from langchain_core.runnables import RunnableConfig
from langgraph.checkpoint.base import (
Checkpoint,
CheckpointMetadata,
create_checkpoint,
empty_checkpoint,
)
from langgraph.checkpoint.sqlite import SqliteSaver
from langgraph.checkpoint.sqlite.utils import _metadata_predicate, search_where
class TestSqliteSaver:
@pytest.fixture(autouse=True)
def setup(self) -> None:
# objects for test setup
self.config_1: RunnableConfig = {
"configurable": {
"thread_id": "thread-1",
# for backwards compatibility testing
"thread_ts": "1",
"checkpoint_ns": "",
}
}
self.config_2: RunnableConfig = {
"configurable": {
"thread_id": "thread-2",
"checkpoint_id": "2",
"checkpoint_ns": "",
}
}
self.config_3: RunnableConfig = {
"configurable": {
"thread_id": "thread-2",
"checkpoint_id": "2-inner",
"checkpoint_ns": "inner",
}
}
self.chkpnt_1: Checkpoint = empty_checkpoint()
self.chkpnt_2: Checkpoint = create_checkpoint(self.chkpnt_1, {}, 1)
self.chkpnt_3: Checkpoint = empty_checkpoint()
self.metadata_1: CheckpointMetadata = {
"source": "input",
"step": 2,
"writes": {},
"score": 1,
}
self.metadata_2: CheckpointMetadata = {
"source": "loop",
"step": 1,
"writes": {"foo": "bar"},
"score": None,
}
self.metadata_3: CheckpointMetadata = {}
def test_combined_metadata(self) -> None:
with SqliteSaver.from_conn_string(":memory:") as saver:
config = {
"configurable": {
"thread_id": "thread-2",
"checkpoint_ns": "",
"__super_private_key": "super_private_value",
},
"metadata": {"run_id": "my_run_id"},
}
saver.put(config, self.chkpnt_2, self.metadata_2, {})
checkpoint = saver.get_tuple(config)
assert checkpoint.metadata == {
**self.metadata_2,
"thread_id": "thread-2",
"run_id": "my_run_id",
}
def test_search(self) -> None:
with SqliteSaver.from_conn_string(":memory:") as saver:
# set up test
# save checkpoints
saver.put(self.config_1, self.chkpnt_1, self.metadata_1, {})
saver.put(self.config_2, self.chkpnt_2, self.metadata_2, {})
saver.put(self.config_3, self.chkpnt_3, self.metadata_3, {})
# call method / assertions
query_1 = {"source": "input"} # search by 1 key
query_2 = {
"step": 1,
"writes": {"foo": "bar"},
} # search by multiple keys
query_3: dict[str, Any] = {} # search by no keys, return all checkpoints
query_4 = {"source": "update", "step": 1} # no match
search_results_1 = list(saver.list(None, filter=query_1))
assert len(search_results_1) == 1
assert search_results_1[0].metadata == {
"thread_id": "thread-1",
"thread_ts": "1",
**self.metadata_1,
}
search_results_2 = list(saver.list(None, filter=query_2))
assert len(search_results_2) == 1
assert search_results_2[0].metadata == {
"thread_id": "thread-2",
**self.metadata_2,
}
search_results_3 = list(saver.list(None, filter=query_3))
assert len(search_results_3) == 3
search_results_4 = list(saver.list(None, filter=query_4))
assert len(search_results_4) == 0
# search by config (defaults to checkpoints across all namespaces)
search_results_5 = list(
saver.list({"configurable": {"thread_id": "thread-2"}})
)
assert len(search_results_5) == 2
assert {
search_results_5[0].config["configurable"]["checkpoint_ns"],
search_results_5[1].config["configurable"]["checkpoint_ns"],
} == {"", "inner"}
# TODO: test before and limit params
def test_search_where(self) -> None:
# call method / assertions
expected_predicate_1 = "WHERE json_extract(CAST(metadata AS TEXT), '$.source') = ? AND json_extract(CAST(metadata AS TEXT), '$.step') = ? AND json_extract(CAST(metadata AS TEXT), '$.writes') = ? AND json_extract(CAST(metadata AS TEXT), '$.score') = ? AND checkpoint_id < ?"
expected_param_values_1 = ["input", 2, "{}", 1, "1"]
assert search_where(
None, cast(dict[str, Any], self.metadata_1), self.config_1
) == (
expected_predicate_1,
expected_param_values_1,
)
def test_metadata_predicate(self) -> None:
# call method / assertions
expected_predicate_1 = [
"json_extract(CAST(metadata AS TEXT), '$.source') = ?",
"json_extract(CAST(metadata AS TEXT), '$.step') = ?",
"json_extract(CAST(metadata AS TEXT), '$.writes') = ?",
"json_extract(CAST(metadata AS TEXT), '$.score') = ?",
]
expected_predicate_2 = [
"json_extract(CAST(metadata AS TEXT), '$.source') = ?",
"json_extract(CAST(metadata AS TEXT), '$.step') = ?",
"json_extract(CAST(metadata AS TEXT), '$.writes') = ?",
"json_extract(CAST(metadata AS TEXT), '$.score') IS ?",
]
expected_predicate_3: list[str] = []
expected_param_values_1 = ["input", 2, "{}", 1]
expected_param_values_2 = ["loop", 1, '{"foo":"bar"}', None]
expected_param_values_3: list[Any] = []
assert _metadata_predicate(cast(dict[str, Any], self.metadata_1)) == (
expected_predicate_1,
expected_param_values_1,
)
assert _metadata_predicate(cast(dict[str, Any], self.metadata_2)) == (
expected_predicate_2,
expected_param_values_2,
)
assert _metadata_predicate(cast(dict[str, Any], self.metadata_3)) == (
expected_predicate_3,
expected_param_values_3,
)
async def test_informative_async_errors(self) -> None:
with SqliteSaver.from_conn_string(":memory:") as saver:
# call method / assertions
with pytest.raises(NotImplementedError, match="AsyncSqliteSaver"):
await saver.aget(self.config_1)
with pytest.raises(NotImplementedError, match="AsyncSqliteSaver"):
await saver.aget_tuple(self.config_1)
with pytest.raises(NotImplementedError, match="AsyncSqliteSaver"):
async for _ in saver.alist(self.config_1):
pass