mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-01 13:26:15 +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()
```
86 lines
2.3 KiB
Python
86 lines
2.3 KiB
Python
"""Test dashscope embeddings."""
|
|
|
|
import numpy as np
|
|
|
|
from langchain_community.embeddings.dashscope import DashScopeEmbeddings
|
|
|
|
|
|
def test_dashscope_embedding_documents() -> None:
|
|
"""Test dashscope embeddings."""
|
|
documents = ["foo bar"]
|
|
embedding = DashScopeEmbeddings(model="text-embedding-v1") # type: ignore[call-arg]
|
|
output = embedding.embed_documents(documents)
|
|
assert len(output) == 1
|
|
assert len(output[0]) == 1536
|
|
|
|
|
|
def test_dashscope_embedding_documents_multiple() -> None:
|
|
"""Test dashscope embeddings."""
|
|
documents = [
|
|
"foo bar",
|
|
"bar foo",
|
|
"foo",
|
|
"foo0",
|
|
"foo1",
|
|
"foo2",
|
|
"foo3",
|
|
"foo4",
|
|
"foo5",
|
|
"foo6",
|
|
"foo7",
|
|
"foo8",
|
|
"foo9",
|
|
"foo10",
|
|
"foo11",
|
|
"foo12",
|
|
"foo13",
|
|
"foo14",
|
|
"foo15",
|
|
"foo16",
|
|
"foo17",
|
|
"foo18",
|
|
"foo19",
|
|
"foo20",
|
|
"foo21",
|
|
"foo22",
|
|
"foo23",
|
|
"foo24",
|
|
]
|
|
embedding = DashScopeEmbeddings(model="text-embedding-v1") # type: ignore[call-arg]
|
|
output = embedding.embed_documents(documents)
|
|
assert len(output) == 28
|
|
assert len(output[0]) == 1536
|
|
assert len(output[1]) == 1536
|
|
assert len(output[2]) == 1536
|
|
|
|
|
|
def test_dashscope_embedding_query() -> None:
|
|
"""Test dashscope embeddings."""
|
|
document = "foo bar"
|
|
embedding = DashScopeEmbeddings(model="text-embedding-v1") # type: ignore[call-arg]
|
|
output = embedding.embed_query(document)
|
|
assert len(output) == 1536
|
|
|
|
|
|
def test_dashscope_embedding_with_empty_string() -> None:
|
|
"""Test dashscope embeddings with empty string."""
|
|
import dashscope
|
|
|
|
document = ["", "abc"]
|
|
embedding = DashScopeEmbeddings(model="text-embedding-v1") # type: ignore[call-arg]
|
|
output = embedding.embed_documents(document)
|
|
assert len(output) == 2
|
|
assert len(output[0]) == 1536
|
|
expected_output = dashscope.TextEmbedding.call(
|
|
input="", model="text-embedding-v1", text_type="document"
|
|
).output["embeddings"][0]["embedding"]
|
|
assert np.allclose(output[0], expected_output)
|
|
assert len(output[1]) == 1536
|
|
|
|
|
|
if __name__ == "__main__":
|
|
test_dashscope_embedding_documents()
|
|
test_dashscope_embedding_documents_multiple()
|
|
test_dashscope_embedding_query()
|
|
test_dashscope_embedding_with_empty_string()
|