mirror of
https://github.com/hwchase17/langchain.git
synced 2025-06-05 06:33:20 +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
2.0 KiB
Python
69 lines
2.0 KiB
Python
"""Util that calls Dataherald."""
|
|
|
|
from typing import Any, Dict, Optional
|
|
|
|
from langchain_core.pydantic_v1 import BaseModel, Extra, root_validator
|
|
from langchain_core.utils import get_from_dict_or_env
|
|
|
|
|
|
class DataheraldAPIWrapper(BaseModel):
|
|
"""Wrapper for Dataherald.
|
|
|
|
Docs for using:
|
|
|
|
1. Go to dataherald and sign up
|
|
2. Create an API key
|
|
3. Save your API key into DATAHERALD_API_KEY env variable
|
|
4. pip install dataherald
|
|
|
|
"""
|
|
|
|
dataherald_client: Any #: :meta private:
|
|
db_connection_id: str
|
|
dataherald_api_key: Optional[str] = None
|
|
|
|
class Config:
|
|
"""Configuration for this pydantic object."""
|
|
|
|
extra = Extra.forbid
|
|
|
|
@root_validator(pre=True)
|
|
def validate_environment(cls, values: Dict) -> Dict:
|
|
"""Validate that api key and python package exists in environment."""
|
|
dataherald_api_key = get_from_dict_or_env(
|
|
values, "dataherald_api_key", "DATAHERALD_API_KEY"
|
|
)
|
|
values["dataherald_api_key"] = dataherald_api_key
|
|
|
|
try:
|
|
import dataherald
|
|
|
|
except ImportError:
|
|
raise ImportError(
|
|
"dataherald is not installed. "
|
|
"Please install it with `pip install dataherald`"
|
|
)
|
|
|
|
client = dataherald.Dataherald(api_key=dataherald_api_key)
|
|
values["dataherald_client"] = client
|
|
|
|
return values
|
|
|
|
def run(self, prompt: str) -> str:
|
|
"""Generate a sql query through Dataherald and parse result."""
|
|
from dataherald.types.sql_generation_create_params import Prompt
|
|
|
|
prompt_obj = Prompt(text=prompt, db_connection_id=self.db_connection_id)
|
|
res = self.dataherald_client.sql_generations.create(prompt=prompt_obj)
|
|
|
|
try:
|
|
answer = res.sql
|
|
if not answer:
|
|
# We don't want to return the assumption alone if answer is empty
|
|
return "No answer"
|
|
else:
|
|
return f"Answer: {answer}"
|
|
|
|
except StopIteration:
|
|
return "Dataherald wasn't able to answer it"
|