More performance improvements in checkpointing and channels (#1685)

* Performance improvements in checkpointer libs

- Use sha1 instead of md5 for hashing (faster in python 3.x)
- Use orjson instead of json for json dumping (sadly can't use for json loading)

* Update tests

* Update

* Use random number instead of hash for get_version_number

* Avoid saving writes for the last task to complete in each step

- only when possible, exceptions for ERROR, INTERRUPT, SEND

* Make Channel.from_checkpoint a regular function

- context manager no longer needed since Context became a managed value

* Use __slots__ for Channels

* Fix for kafka
This commit is contained in:
Nuno Campos
2024-09-12 21:08:30 -07:00
committed by GitHub
parent 8a80b1d3b1
commit 66fc7c96aa
20 changed files with 199 additions and 337 deletions
+11 -1
View File
@@ -114,6 +114,8 @@ def test_serde_jsonplus() -> None:
"an_int": 1,
"a_float": 1.1,
"runnable_map": RunnableMap({}),
"a_bytes": b"my bytes",
"a_bytearray": bytearray([42]),
}
serde = JsonPlusSerializer()
@@ -122,7 +124,7 @@ def test_serde_jsonplus() -> None:
assert dumped == (
"json",
b"""{"path": {"lc": 2, "type": "constructor", "id": ["pathlib", "Path"], "args": ["foo", "bar"]}, "re": {"lc": 2, "type": "constructor", "id": ["re", "compile"], "args": ["foo", 48]}, "decimal": {"lc": 2, "type": "constructor", "id": ["decimal", "Decimal"], "args": ["1.10101"]}, "ip4": {"lc": 2, "type": "constructor", "id": ["ipaddress", "IPv4Address"], "args": ["192.168.0.1"]}, "deque": {"lc": 2, "type": "constructor", "id": ["collections", "deque"], "args": [[1, 2, 3]]}, "tzn": {"lc": 2, "type": "constructor", "id": ["zoneinfo", "ZoneInfo"], "args": ["America/New_York"]}, "date": {"lc": 2, "type": "constructor", "id": ["datetime", "date"], "args": [2024, 4, 19]}, "time": {"lc": 2, "type": "constructor", "id": ["datetime", "time"], "args": [23, 4, 57, 51022, {"lc": 2, "type": "constructor", "id": ["datetime", "timezone"], "args": [{"lc": 2, "type": "constructor", "id": ["datetime", "timedelta"], "args": [0, 86340, 0]}]}], "kwargs": {"fold": 0}}, "uid": {"lc": 2, "type": "constructor", "id": ["uuid", "UUID"], "args": ["00000000000000000000000000000001"]}, "timestamp": {"lc": 2, "type": "constructor", "id": ["datetime", "datetime"], "method": "fromisoformat", "args": ["2024-04-19T23:04:57.051022+23:59"]}, "my_slotted_class": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyDataclassWSlots"], "kwargs": {"foo": "bar", "bar": 2}}, "my_dataclass": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyDataclass"], "kwargs": {"foo": "foo", "bar": 1}}, "my_enum": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyEnum"], "args": ["foo"]}, "my_pydantic": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyPydantic"], "method": [null, "model_construct"], "kwargs": {"foo": "foo", "bar": 1}}, "my_funny_pydantic": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyFunnyPydantic"], "method": [null, "construct"], "kwargs": {"foo": "foo", "bar": 1}}, "person": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "Person"], "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"], "args": ["foo", "bar"]}, "re": {"lc": 2, "type": "constructor", "id": ["re", "compile"], "args": ["foo", 48]}, "decimal": {"lc": 2, "type": "constructor", "id": ["decimal", "Decimal"], "args": ["1.10101"]}, "ip4": {"lc": 2, "type": "constructor", "id": ["ipaddress", "IPv4Address"], "args": ["192.168.0.1"]}, "deque": {"lc": 2, "type": "constructor", "id": ["collections", "deque"], "args": [[1, 2, 3]]}, "tzn": {"lc": 2, "type": "constructor", "id": ["zoneinfo", "ZoneInfo"], "args": ["America/New_York"]}, "date": {"lc": 2, "type": "constructor", "id": ["datetime", "date"], "args": [2024, 4, 19]}, "time": {"lc": 2, "type": "constructor", "id": ["datetime", "time"], "args": [23, 4, 57, 51022, {"lc": 2, "type": "constructor", "id": ["datetime", "timezone"], "args": [{"lc": 2, "type": "constructor", "id": ["datetime", "timedelta"], "args": [0, 86340, 0]}]}], "kwargs": {"fold": 0}}, "uid": {"lc": 2, "type": "constructor", "id": ["uuid", "UUID"], "args": ["00000000000000000000000000000001"]}, "timestamp": {"lc": 2, "type": "constructor", "id": ["datetime", "datetime"], "method": "fromisoformat", "args": ["2024-04-19T23:04:57.051022+23:59"]}, "my_slotted_class": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyDataclassWSlots"], "kwargs": {"foo": "bar", "bar": 2}}, "my_dataclass": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyDataclass"], "kwargs": {"foo": "foo", "bar": 1}}, "my_enum": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyEnum"], "args": ["foo"]}, "my_pydantic": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyPydantic"], "method": [null, "model_construct"], "kwargs": {"foo": "foo", "bar": 1}}, "my_funny_pydantic": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "MyFunnyPydantic"], "method": [null, "construct"], "kwargs": {"foo": "foo", "bar": 1}}, "person": {"lc": 2, "type": "constructor", "id": ["tests", "test_jsonplus", "Person"], "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": []}}, "a_bytes": {"lc": 2, "type": "constructor", "id": ["builtins", "bytes"], "method": "fromhex", "args": ["6d79206279746573"]}, "a_bytearray": {"lc": 2, "type": "constructor", "id": ["builtins", "bytearray"], "method": "fromhex", "args": ["2a"]}}""",
)
assert serde.loads_typed(dumped) == {
@@ -130,6 +132,14 @@ def test_serde_jsonplus() -> None:
"text": [v.encode("utf-8", "ignore").decode() for v in to_serialize["text"]],
}
for key, value in to_serialize.items():
if key == "text":
assert serde.loads_typed(serde.dumps_typed(value)) == [
v.encode("utf-8", "ignore").decode() for v in value
]
else:
assert serde.loads_typed(serde.dumps_typed(value)) == value
def test_serde_jsonplus_bytes() -> None:
serde = JsonPlusSerializer()