mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-01 05:15:17 +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()
```
37 lines
1.7 KiB
Python
37 lines
1.7 KiB
Python
"""Test SparkLLM Text Embedding."""
|
||
|
||
from langchain_community.embeddings.sparkllm import SparkLLMTextEmbeddings
|
||
|
||
|
||
def test_baichuan_embedding_documents() -> None:
|
||
"""Test SparkLLM Text Embedding for documents."""
|
||
documents = [
|
||
"iFLYTEK is a well-known intelligent speech and artificial intelligence "
|
||
"publicly listed company in the Asia-Pacific Region. Since its establishment,"
|
||
"the company is devoted to cornerstone technological research "
|
||
"in speech and languages, natural language understanding, machine learning,"
|
||
"machine reasoning, adaptive learning, "
|
||
"and has maintained the world-leading position in those "
|
||
"domains. The company actively promotes the development of A.I. "
|
||
"products and their sector-based "
|
||
"applications, with visions of enabling machines to listen and speak, "
|
||
"understand and think, "
|
||
"creating a better world with artificial intelligence."
|
||
]
|
||
embedding = SparkLLMTextEmbeddings() # type: ignore[call-arg]
|
||
output = embedding.embed_documents(documents)
|
||
assert len(output) == 1 # type: ignore[arg-type]
|
||
assert len(output[0]) == 2560 # type: ignore[index]
|
||
|
||
|
||
def test_baichuan_embedding_query() -> None:
|
||
"""Test SparkLLM Text Embedding for query."""
|
||
document = (
|
||
"iFLYTEK Open Platform was launched in 2010 by iFLYTEK as China’s "
|
||
"first Artificial Intelligence open platform for Mobile Internet "
|
||
"and intelligent hardware developers"
|
||
)
|
||
embedding = SparkLLMTextEmbeddings() # type: ignore[call-arg]
|
||
output = embedding.embed_query(document)
|
||
assert len(output) == 2560 # type: ignore[arg-type]
|