mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-01 21:35:34 +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()
```
69 lines
2.1 KiB
Python
69 lines
2.1 KiB
Python
"""Test Vertex AI API wrapper.
|
|
In order to run this test, you need to install VertexAI SDK
|
|
pip install google-cloud-aiplatform>=1.35.0
|
|
|
|
Your end-user credentials would be used to make the calls (make sure you've run
|
|
`gcloud auth login` first).
|
|
"""
|
|
|
|
import pytest
|
|
|
|
from langchain_community.embeddings import VertexAIEmbeddings
|
|
|
|
|
|
def test_embedding_documents() -> None:
|
|
documents = ["foo bar"]
|
|
model = VertexAIEmbeddings()
|
|
output = model.embed_documents(documents)
|
|
assert len(output) == 1
|
|
assert len(output[0]) == 768
|
|
assert model.model_name == model.client._model_id
|
|
assert model.model_name == "textembedding-gecko@001"
|
|
|
|
|
|
def test_embedding_query() -> None:
|
|
document = "foo bar"
|
|
model = VertexAIEmbeddings()
|
|
output = model.embed_query(document)
|
|
assert len(output) == 768
|
|
|
|
|
|
def test_large_batches() -> None:
|
|
documents = ["foo bar" for _ in range(0, 251)]
|
|
model_uscentral1 = VertexAIEmbeddings(location="us-central1")
|
|
model_asianortheast1 = VertexAIEmbeddings(location="asia-northeast1")
|
|
model_uscentral1.embed_documents(documents)
|
|
model_asianortheast1.embed_documents(documents)
|
|
assert model_uscentral1.instance["batch_size"] >= 250
|
|
assert model_asianortheast1.instance["batch_size"] < 50
|
|
|
|
|
|
def test_paginated_texts() -> None:
|
|
documents = [
|
|
"foo bar",
|
|
"foo baz",
|
|
"bar foo",
|
|
"baz foo",
|
|
"bar bar",
|
|
"foo foo",
|
|
"baz baz",
|
|
"baz bar",
|
|
]
|
|
model = VertexAIEmbeddings()
|
|
output = model.embed_documents(documents)
|
|
assert len(output) == 8
|
|
assert len(output[0]) == 768
|
|
assert model.model_name == model.client._model_id
|
|
|
|
|
|
def test_warning(caplog: pytest.LogCaptureFixture) -> None:
|
|
_ = VertexAIEmbeddings()
|
|
assert len(caplog.records) == 1
|
|
record = caplog.records[0]
|
|
assert record.levelname == "WARNING"
|
|
expected_message = (
|
|
"Model_name will become a required arg for VertexAIEmbeddings starting from "
|
|
"Feb-01-2024. Currently the default is set to textembedding-gecko@001"
|
|
)
|
|
assert record.message == expected_message
|