mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-23 11:30:37 +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()
```
30 lines
964 B
Python
30 lines
964 B
Python
"""Integration test for video captioning."""
|
|
|
|
from langchain_openai import ChatOpenAI
|
|
|
|
from langchain_experimental.video_captioning.base import VideoCaptioningChain
|
|
|
|
|
|
def test_video_captioning_hard() -> None:
|
|
"""Test input that is considered hard for this chain to process."""
|
|
URL = """
|
|
https://ia904700.us.archive.org/22/items/any-chibes/X2Download.com
|
|
-FXX%20USA%20%C2%ABPromo%20Noon%20-%204A%20Every%20Day%EF%BF%BD%EF
|
|
%BF%BD%C2%BB%20November%202021%EF%BF%BD%EF%BF%BD-%281080p60%29.mp4
|
|
"""
|
|
chain = VideoCaptioningChain( # type: ignore[call-arg]
|
|
llm=ChatOpenAI(
|
|
model="gpt-4",
|
|
max_tokens=4000,
|
|
)
|
|
)
|
|
srt_content = chain.run(video_file_path=URL)
|
|
|
|
assert (
|
|
"mustache" in srt_content
|
|
and "Any chives?" in srt_content
|
|
and "How easy? A little tighter." in srt_content
|
|
and "it's a little tight in" in srt_content
|
|
and "every day" in srt_content
|
|
)
|