2023-12-11 21:53:30 +00:00
|
|
|
"""Util that calls SceneXplain.
|
|
|
|
|
|
|
|
|
|
In order to set this up, you need API key for the SceneXplain API.
|
|
|
|
|
You can obtain a key by following the steps below.
|
|
|
|
|
- Sign up for a free account at https://scenex.jina.ai/.
|
|
|
|
|
- Navigate to the API Access page (https://scenex.jina.ai/api) and create a new API key.
|
|
|
|
|
"""
|
infra: update mypy 1.10, ruff 0.5 (#23721)
```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()
```
2024-07-03 17:33:27 +00:00
|
|
|
|
2024-09-13 21:38:45 +00:00
|
|
|
from typing import Any, Dict
|
2023-12-11 21:53:30 +00:00
|
|
|
|
|
|
|
|
import requests
|
2024-09-13 21:38:45 +00:00
|
|
|
from langchain_core.utils import from_env, get_from_dict_or_env
|
|
|
|
|
from pydantic import BaseModel, Field, model_validator
|
2023-12-11 21:53:30 +00:00
|
|
|
|
|
|
|
|
|
2024-09-13 21:38:45 +00:00
|
|
|
class SceneXplainAPIWrapper(BaseModel):
|
2023-12-11 21:53:30 +00:00
|
|
|
"""Wrapper for SceneXplain API.
|
|
|
|
|
|
|
|
|
|
In order to set this up, you need API key for the SceneXplain API.
|
|
|
|
|
You can obtain a key by following the steps below.
|
|
|
|
|
- Sign up for a free account at https://scenex.jina.ai/.
|
|
|
|
|
- Navigate to the API Access page (https://scenex.jina.ai/api)
|
|
|
|
|
and create a new API key.
|
|
|
|
|
"""
|
|
|
|
|
|
2024-09-13 21:38:45 +00:00
|
|
|
scenex_api_key: str = Field(..., default_factory=from_env("SCENEX_API_KEY"))
|
2023-12-11 21:53:30 +00:00
|
|
|
scenex_api_url: str = "https://api.scenex.jina.ai/v1/describe"
|
|
|
|
|
|
|
|
|
|
def _describe_image(self, image: str) -> str:
|
|
|
|
|
headers = {
|
|
|
|
|
"x-api-key": f"token {self.scenex_api_key}",
|
|
|
|
|
"content-type": "application/json",
|
|
|
|
|
}
|
|
|
|
|
payload = {
|
|
|
|
|
"data": [
|
|
|
|
|
{
|
|
|
|
|
"image": image,
|
|
|
|
|
"algorithm": "Ember",
|
|
|
|
|
"languages": ["en"],
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
response = requests.post(self.scenex_api_url, headers=headers, json=payload)
|
|
|
|
|
response.raise_for_status()
|
|
|
|
|
result = response.json().get("result", [])
|
|
|
|
|
img = result[0] if result else {}
|
|
|
|
|
|
|
|
|
|
return img.get("text", "")
|
|
|
|
|
|
2024-09-13 21:38:45 +00:00
|
|
|
@model_validator(mode="before")
|
|
|
|
|
@classmethod
|
|
|
|
|
def validate_environment(cls, values: Dict) -> Any:
|
2023-12-11 21:53:30 +00:00
|
|
|
"""Validate that api key exists in environment."""
|
|
|
|
|
scenex_api_key = get_from_dict_or_env(
|
|
|
|
|
values, "scenex_api_key", "SCENEX_API_KEY"
|
|
|
|
|
)
|
|
|
|
|
values["scenex_api_key"] = scenex_api_key
|
|
|
|
|
|
|
|
|
|
return values
|
|
|
|
|
|
|
|
|
|
def run(self, image: str) -> str:
|
|
|
|
|
"""Run SceneXplain image explainer."""
|
|
|
|
|
description = self._describe_image(image)
|
|
|
|
|
if not description:
|
|
|
|
|
return "No description found."
|
|
|
|
|
|
|
|
|
|
return description
|
