mirror of
https://github.com/hwchase17/langchain.git
synced 2025-11-11 05:32:03 +00:00
```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
1.1 KiB
Python
37 lines
1.1 KiB
Python
# flake8: noqa
|
|
"""Test rwkv wrapper."""
|
|
|
|
import os
|
|
from urllib.request import urlretrieve
|
|
|
|
from langchain_community.llms import RWKV
|
|
import warnings
|
|
import pytest
|
|
|
|
|
|
def _download_model() -> str:
|
|
"""Download model.
|
|
From https://huggingface.co/BlinkDL/rwkv-4-pile-169m/resolve/main/RWKV-4-Pile-169M-20220807-8023.pth,
|
|
"""
|
|
model_url = "https://huggingface.co/BlinkDL/rwkv-4-pile-169m/resolve/main/RWKV-4-Pile-169M-20220807-8023.pth"
|
|
tokenizer_url = (
|
|
"https://github.com/BlinkDL/ChatRWKV/blob/main/v2/20B_tokenizer.json?raw=true"
|
|
)
|
|
local_filename = model_url.split("/")[-1]
|
|
|
|
if not os.path.exists("20B_tokenizer.json"):
|
|
urlretrieve(tokenizer_url, "20B_tokenizer.json")
|
|
if not os.path.exists(local_filename):
|
|
urlretrieve(model_url, local_filename)
|
|
|
|
return local_filename
|
|
|
|
|
|
@pytest.mark.filterwarnings("ignore::UserWarning:")
|
|
def test_rwkv_inference() -> None:
|
|
"""Test valid gpt4all inference."""
|
|
model_path = _download_model()
|
|
llm = RWKV(model=model_path, tokens_path="20B_tokenizer.json", strategy="cpu fp32")
|
|
output = llm.invoke("Say foo:")
|
|
assert isinstance(output, str)
|