mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-11 10:06:05 +00:00
a0c2281540
```python
"""python scripts/update_mypy_ruff.py"""
import glob
import tomllib
from pathlib import Path
import toml
import subprocess
import re
ROOT_DIR = Path(__file__).parents[1]
def main():
for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True):
print(path)
with open(path, "rb") as f:
pyproject = tomllib.load(f)
try:
pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = (
"^1.10"
)
pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = (
"^0.5"
)
except KeyError:
continue
with open(path, "w") as f:
toml.dump(pyproject, f)
cwd = "/".join(path.split("/")[:-1])
completed = subprocess.run(
"poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color",
cwd=cwd,
shell=True,
capture_output=True,
text=True,
)
logs = completed.stdout.split("\n")
to_ignore = {}
for l in logs:
if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l):
path, line_no, error_type = re.match(
"^(.*)\:(\d+)\: error:.*\[(.*)\]", l
).groups()
if (path, line_no) in to_ignore:
to_ignore[(path, line_no)].append(error_type)
else:
to_ignore[(path, line_no)] = [error_type]
print(len(to_ignore))
for (error_path, line_no), error_types in to_ignore.items():
all_errors = ", ".join(error_types)
full_path = f"{cwd}/{error_path}"
try:
with open(full_path, "r") as f:
file_lines = f.readlines()
except FileNotFoundError:
continue
file_lines[int(line_no) - 1] = (
file_lines[int(line_no) - 1][:-1] + f" # type: ignore[{all_errors}]\n"
)
with open(full_path, "w") as f:
f.write("".join(file_lines))
subprocess.run(
"poetry run ruff format .; poetry run ruff --select I --fix .",
cwd=cwd,
shell=True,
capture_output=True,
text=True,
)
if __name__ == "__main__":
main()
```
99 lines
3.0 KiB
Python
99 lines
3.0 KiB
Python
"""Test Momento cache functionality.
|
|
|
|
To run tests, set the environment variable MOMENTO_AUTH_TOKEN to a valid
|
|
Momento auth token. This can be obtained by signing up for a free
|
|
Momento account at https://gomomento.com/.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import uuid
|
|
from datetime import timedelta
|
|
from typing import Iterator
|
|
|
|
import pytest
|
|
from langchain.globals import set_llm_cache
|
|
from langchain_core.outputs import Generation, LLMResult
|
|
|
|
from langchain_community.cache import MomentoCache
|
|
from tests.unit_tests.llms.fake_llm import FakeLLM
|
|
|
|
|
|
def random_string() -> str:
|
|
return str(uuid.uuid4())
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def momento_cache() -> Iterator[MomentoCache]:
|
|
from momento import CacheClient, Configurations, CredentialProvider
|
|
|
|
cache_name = f"langchain-test-cache-{random_string()}"
|
|
client = CacheClient(
|
|
Configurations.Laptop.v1(),
|
|
CredentialProvider.from_environment_variable("MOMENTO_API_KEY"),
|
|
default_ttl=timedelta(seconds=30),
|
|
)
|
|
try:
|
|
llm_cache = MomentoCache(client, cache_name)
|
|
set_llm_cache(llm_cache)
|
|
yield llm_cache
|
|
finally:
|
|
client.delete_cache(cache_name)
|
|
|
|
|
|
def test_invalid_ttl() -> None:
|
|
from momento import CacheClient, Configurations, CredentialProvider
|
|
|
|
client = CacheClient(
|
|
Configurations.Laptop.v1(),
|
|
CredentialProvider.from_environment_variable("MOMENTO_API_KEY"),
|
|
default_ttl=timedelta(seconds=30),
|
|
)
|
|
with pytest.raises(ValueError):
|
|
MomentoCache(client, cache_name=random_string(), ttl=timedelta(seconds=-1))
|
|
|
|
|
|
def test_momento_cache_miss(momento_cache: MomentoCache) -> None:
|
|
llm = FakeLLM()
|
|
stub_llm_output = LLMResult(generations=[[Generation(text="foo")]])
|
|
assert llm.generate([random_string()]) == stub_llm_output
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"prompts, generations",
|
|
[
|
|
# Single prompt, single generation
|
|
([random_string()], [[random_string()]]),
|
|
# Single prompt, multiple generations
|
|
([random_string()], [[random_string(), random_string()]]),
|
|
# Single prompt, multiple generations
|
|
([random_string()], [[random_string(), random_string(), random_string()]]),
|
|
# Multiple prompts, multiple generations
|
|
(
|
|
[random_string(), random_string()],
|
|
[[random_string()], [random_string(), random_string()]],
|
|
),
|
|
],
|
|
)
|
|
def test_momento_cache_hit(
|
|
momento_cache: MomentoCache, prompts: list[str], generations: list[list[str]]
|
|
) -> None:
|
|
llm = FakeLLM()
|
|
params = llm.dict()
|
|
params["stop"] = None
|
|
llm_string = str(sorted([(k, v) for k, v in params.items()]))
|
|
|
|
llm_generations = [
|
|
[
|
|
Generation(text=generation, generation_info=params)
|
|
for generation in prompt_i_generations
|
|
]
|
|
for prompt_i_generations in generations
|
|
]
|
|
for prompt_i, llm_generations_i in zip(prompts, llm_generations):
|
|
momento_cache.update(prompt_i, llm_string, llm_generations_i)
|
|
|
|
assert llm.generate(prompts) == LLMResult(
|
|
generations=llm_generations, llm_output={}
|
|
)
|