mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-05 15:18:32 +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()
```
62 lines
2.0 KiB
Python
62 lines
2.0 KiB
Python
"""Test the loading function for evaluators."""
|
|
|
|
from typing import List
|
|
|
|
import pytest
|
|
from langchain.evaluation.loading import EvaluatorType, load_evaluators
|
|
from langchain.evaluation.schema import PairwiseStringEvaluator, StringEvaluator
|
|
from langchain_core.embeddings import FakeEmbeddings
|
|
|
|
from tests.unit_tests.llms.fake_chat_model import FakeChatModel
|
|
from tests.unit_tests.llms.fake_llm import FakeLLM
|
|
|
|
|
|
@pytest.mark.requires("rapidfuzz")
|
|
@pytest.mark.parametrize("evaluator_type", EvaluatorType)
|
|
def test_load_evaluators(evaluator_type: EvaluatorType) -> None:
|
|
"""Test loading evaluators."""
|
|
fake_llm = FakeChatModel()
|
|
embeddings = FakeEmbeddings(size=32)
|
|
load_evaluators([evaluator_type], llm=fake_llm, embeddings=embeddings)
|
|
|
|
# Test as string
|
|
load_evaluators(
|
|
[evaluator_type.value], # type: ignore
|
|
llm=fake_llm,
|
|
embeddings=embeddings,
|
|
)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"evaluator_types",
|
|
[
|
|
[EvaluatorType.LABELED_CRITERIA],
|
|
[EvaluatorType.LABELED_PAIRWISE_STRING],
|
|
[EvaluatorType.LABELED_SCORE_STRING],
|
|
[EvaluatorType.QA],
|
|
[EvaluatorType.CONTEXT_QA],
|
|
[EvaluatorType.COT_QA],
|
|
[EvaluatorType.COT_QA, EvaluatorType.LABELED_CRITERIA],
|
|
[
|
|
EvaluatorType.COT_QA,
|
|
EvaluatorType.LABELED_CRITERIA,
|
|
EvaluatorType.LABELED_PAIRWISE_STRING,
|
|
],
|
|
[EvaluatorType.JSON_EQUALITY],
|
|
[EvaluatorType.EXACT_MATCH, EvaluatorType.REGEX_MATCH],
|
|
],
|
|
)
|
|
def test_eval_chain_requires_references(evaluator_types: List[EvaluatorType]) -> None:
|
|
"""Test loading evaluators."""
|
|
fake_llm = FakeLLM(
|
|
queries={"text": "The meaning of life\nCORRECT"}, sequential_responses=True
|
|
)
|
|
evaluators = load_evaluators(
|
|
evaluator_types,
|
|
llm=fake_llm,
|
|
)
|
|
for evaluator in evaluators:
|
|
if not isinstance(evaluator, (StringEvaluator, PairwiseStringEvaluator)):
|
|
raise ValueError("Evaluator is not a [pairwise]string evaluator")
|
|
assert evaluator.requires_reference
|