Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

checkpoint: Add support for serializing more python types #1311

Merged
merged 3 commits into from
Aug 13, 2024
Merged

checkpoint: Add support for serializing more python types #1311

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
685db62
checkpoint: Add support for serializing more python types
nfcampos Aug 12, 2024
fdc5aec
Add Decimal
nfcampos Aug 12, 2024
a64c0a2
Add pathlib.Path and re.Pattern
nfcampos Aug 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
42 changes: 40 additions & 2 deletions libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,13 +1,26 @@
import dataclasses
import decimal
import importlib
import json
from datetime import datetime, timedelta, timezone
import pathlib
import re
from collections import deque
from datetime import date, datetime, time, timedelta, timezone
from enum import Enum
from ipaddress import (
IPv4Address,
IPv4Interface,
IPv4Network,
IPv6Address,
IPv6Interface,
IPv6Network,
)
from typing import Any, Optional
from uuid import UUID

from langchain_core.load.load import Reviver
from langchain_core.load.serializable import Serializable
from zoneinfo import ZoneInfo

from langgraph.checkpoint.serde.base import SerializerProtocol
from langgraph.checkpoint.serde.types import SendProtocol
Expand Down Expand Up @@ -40,20 +53,45 @@ def _default(self, obj):
return self._encode_constructor_args(obj.__class__, kwargs=obj.model_dump())
elif hasattr(obj, "dict") and callable(obj.dict):
return self._encode_constructor_args(obj.__class__, kwargs=obj.dict())
elif isinstance(obj, pathlib.Path):
return self._encode_constructor_args(pathlib.Path, args=obj.parts)
elif isinstance(obj, re.Pattern):
return self._encode_constructor_args(
re.compile, args=[obj.pattern, obj.flags]
)
elif isinstance(obj, UUID):
return self._encode_constructor_args(UUID, args=[obj.hex])
elif isinstance(obj, (set, frozenset)):
elif isinstance(obj, decimal.Decimal):
return self._encode_constructor_args(decimal.Decimal, args=[str(obj)])
elif isinstance(obj, (set, frozenset, deque)):
return self._encode_constructor_args(type(obj), args=[list(obj)])
elif isinstance(obj, (IPv4Address, IPv4Interface, IPv4Network)):
return self._encode_constructor_args(obj.__class__, args=[str(obj)])
elif isinstance(obj, (IPv6Address, IPv6Interface, IPv6Network)):
return self._encode_constructor_args(obj.__class__, args=[str(obj)])

elif isinstance(obj, datetime):
return self._encode_constructor_args(
datetime, method="fromisoformat", args=[obj.isoformat()]
)
elif isinstance(obj, timezone):
return self._encode_constructor_args(timezone, args=obj.__getinitargs__())
elif isinstance(obj, ZoneInfo):
return self._encode_constructor_args(ZoneInfo, args=[obj.key])
elif isinstance(obj, timedelta):
return self._encode_constructor_args(
timedelta, args=[obj.days, obj.seconds, obj.microseconds]
)
elif isinstance(obj, date):
return self._encode_constructor_args(
date, args=[obj.year, obj.month, obj.day]
)
elif isinstance(obj, time):
return self._encode_constructor_args(
time,
args=[obj.hour, obj.minute, obj.second, obj.microsecond, obj.tzinfo],
kwargs={"fold": obj.fold},
)
elif dataclasses.is_dataclass(obj):
return self._encode_constructor_args(
obj.__class__,
Expand Down
27 changes: 23 additions & 4 deletions libs/checkpoint/tests/test_jsonplus.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,13 +1,19 @@
import dataclasses
import pathlib
import re
import sys
import uuid
from datetime import datetime, timezone
from collections import deque
from datetime import date, datetime, time, timezone
from decimal import Decimal
from enum import Enum
from ipaddress import IPv4Address

import dataclasses_json
from langchain_core.pydantic_v1 import BaseModel as LcBaseModel
from langchain_core.runnables import RunnableMap
from pydantic import BaseModel
from zoneinfo import ZoneInfo

from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer

Expand Down Expand Up @@ -60,11 +66,24 @@ class Person:

def test_serde_jsonplus() -> None:
uid = uuid.UUID(int=1)
current_time = datetime(2024, 4, 19, 23, 4, 57, 51022, timezone.max)
deque_instance = deque([1, 2, 3])
tzn = ZoneInfo("America/New_York")
ip4 = IPv4Address("192.168.0.1")
current_date = date(2024, 4, 19)
current_time = time(23, 4, 57, 51022, timezone.max)
current_timestamp = datetime(2024, 4, 19, 23, 4, 57, 51022, timezone.max)

to_serialize = {
"uid": uid,
"path": pathlib.Path("foo", "bar"),
"re": re.compile(r"foo", re.DOTALL),
"decimal": Decimal("1.10101"),
"ip4": ip4,
"deque": deque_instance,
"tzn": tzn,
"date": current_date,
"time": current_time,
"uid": uid,
"timestamp": current_timestamp,
"my_slotted_class": MyDataclassWSlots("bar", 2),
"my_dataclass": MyDataclass("foo", 1),
"my_enum": MyEnum.FOO,
Expand Down Expand Up @@ -103,7 +122,7 @@ def test_serde_jsonplus() -> None:

assert dumped == (
"json",
b"""{"uid": {"lc": 2, "type": "constructor", "id": ["uuid", "UUID"], "method": null, "args": ["00000000000000000000000000000001"], "kwargs": {}}, "time": {"lc": 2, "type": "constructor", "id": ["datetime", "datetime"], "method": "fromisoformat", "args": ["2024-04-19T23:04:57.051022+23:59"], "kwargs": {}}, "my_slotted_class": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyDataclassWSlots"], "method": null, "args": [], "kwargs": {"foo": "bar", "bar": 2}}, "my_dataclass": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyDataclass"], "method": null, "args": [], "kwargs": {"foo": "foo", "bar": 1}}, "my_enum": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyEnum"], "method": null, "args": ["foo"], "kwargs": {}}, "my_pydantic": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyPydantic"], "method": null, "args": [], "kwargs": {"foo": "foo", "bar": 1}}, "my_funny_pydantic": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyFunnyPydantic"], "method": null, "args": [], "kwargs": {"foo": "foo", "bar": 1}}, "person": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "Person"], "method": null, "args": [], "kwargs": {"name": "foo"}}, "a_bool": true, "a_none": null, "a_str": "foo", "a_str_nuc": "foo\\u0000", "a_str_uc": "foo \xe2\x9b\xb0\xef\xb8\x8f", "a_str_ucuc": "foo \xe2\x9b\xb0\xef\xb8\x8f\\u0000", "a_str_ucucuc": "foo \\\\u26f0\\\\ufe0f", "text": ["Hello", "Python", "Surrogate", "Example", "String", "With", "Surrogates", "Embedded", "In", "The", "Text", "\xe6\x94\xb6\xe8\x8a\xb1\xf0\x9f\x99\x84\xc2\xb7\xe5\x88\xb0"], "an_int": 1, "a_float": 1.1, "runnable_map": {"lc": 1, "type": "constructor", "id": ["langchain", "schema", "runnable", "RunnableParallel"], "kwargs": {"steps__": {}}, "name": "RunnableParallel<>", "graph": {"nodes": [{"id": 0, "type": "schema", "data": "Parallel<>Input"}, {"id": 1, "type": "schema", "data": "Parallel<>Output"}], "edges": []}}}""",
b"""{"path": {"lc": 2, "type": "constructor", "id": ["pathlib", "Path"], "method": null, "args": ["foo", "bar"], "kwargs": {}}, "re": {"lc": 2, "type": "constructor", "id": ["re", "compile"], "method": null, "args": ["foo", 48], "kwargs": {}}, "decimal": {"lc": 2, "type": "constructor", "id": ["decimal", "Decimal"], "method": null, "args": ["1.10101"], "kwargs": {}}, "ip4": {"lc": 2, "type": "constructor", "id": ["ipaddress", "IPv4Address"], "method": null, "args": ["192.168.0.1"], "kwargs": {}}, "deque": {"lc": 2, "type": "constructor", "id": ["collections", "deque"], "method": null, "args": [[1, 2, 3]], "kwargs": {}}, "tzn": {"lc": 2, "type": "constructor", "id": ["zoneinfo", "ZoneInfo"], "method": null, "args": ["America/New_York"], "kwargs": {}}, "date": {"lc": 2, "type": "constructor", "id": ["datetime", "date"], "method": null, "args": [2024, 4, 19], "kwargs": {}}, "time": {"lc": 2, "type": "constructor", "id": ["datetime", "time"], "method": null, "args": [23, 4, 57, 51022, {"lc": 2, "type": "constructor", "id": ["datetime", "timezone"], "method": null, "args": [{"lc": 2, "type": "constructor", "id": ["datetime", "timedelta"], "method": null, "args": [0, 86340, 0], "kwargs": {}}], "kwargs": {}}], "kwargs": {"fold": 0}}, "uid": {"lc": 2, "type": "constructor", "id": ["uuid", "UUID"], "method": null, "args": ["00000000000000000000000000000001"], "kwargs": {}}, "timestamp": {"lc": 2, "type": "constructor", "id": ["datetime", "datetime"], "method": "fromisoformat", "args": ["2024-04-19T23:04:57.051022+23:59"], "kwargs": {}}, "my_slotted_class": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyDataclassWSlots"], "method": null, "args": [], "kwargs": {"foo": "bar", "bar": 2}}, "my_dataclass": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyDataclass"], "method": null, "args": [], "kwargs": {"foo": "foo", "bar": 1}}, "my_enum": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyEnum"], "method": null, "args": ["foo"], "kwargs": {}}, "my_pydantic": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyPydantic"], "method": null, "args": [], "kwargs": {"foo": "foo", "bar": 1}}, "my_funny_pydantic": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyFunnyPydantic"], "method": null, "args": [], "kwargs": {"foo": "foo", "bar": 1}}, "person": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "Person"], "method": null, "args": [], "kwargs": {"name": "foo"}}, "a_bool": true, "a_none": null, "a_str": "foo", "a_str_nuc": "foo\\u0000", "a_str_uc": "foo \xe2\x9b\xb0\xef\xb8\x8f", "a_str_ucuc": "foo \xe2\x9b\xb0\xef\xb8\x8f\\u0000", "a_str_ucucuc": "foo \\\\u26f0\\\\ufe0f", "text": ["Hello", "Python", "Surrogate", "Example", "String", "With", "Surrogates", "Embedded", "In", "The", "Text", "\xe6\x94\xb6\xe8\x8a\xb1\xf0\x9f\x99\x84\xc2\xb7\xe5\x88\xb0"], "an_int": 1, "a_float": 1.1, "runnable_map": {"lc": 1, "type": "constructor", "id": ["langchain", "schema", "runnable", "RunnableParallel"], "kwargs": {"steps__": {}}, "name": "RunnableParallel<>", "graph": {"nodes": [{"id": 0, "type": "schema", "data": "Parallel<>Input"}, {"id": 1, "type": "schema", "data": "Parallel<>Output"}], "edges": []}}}""",
)

assert serde.loads_typed(dumped) == {
Expand Down
Loading