mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-28 23:07:11 +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()
```
121 lines
4.6 KiB
Python
121 lines
4.6 KiB
Python
"""Tool for the Exa Search API.""" # type: ignore[import-not-found, import-not-found]
|
|
|
|
from typing import Dict, List, Optional, Union
|
|
|
|
from exa_py import Exa # type: ignore
|
|
from exa_py.api import HighlightsContentsOptions, TextContentsOptions # type: ignore
|
|
from langchain_core.callbacks import (
|
|
CallbackManagerForToolRun,
|
|
)
|
|
from langchain_core.pydantic_v1 import Field, SecretStr, root_validator
|
|
from langchain_core.tools import BaseTool
|
|
|
|
from langchain_exa._utilities import initialize_client
|
|
|
|
|
|
class ExaSearchResults(BaseTool):
|
|
"""Tool that queries the Metaphor Search API and gets back json."""
|
|
|
|
name: str = "exa_search_results_json"
|
|
description: str = (
|
|
"A wrapper around Exa Search. "
|
|
"Input should be an Exa-optimized query. "
|
|
"Output is a JSON array of the query results"
|
|
)
|
|
client: Exa = Field(default=None)
|
|
exa_api_key: SecretStr = Field(default=None)
|
|
|
|
@root_validator(pre=True)
|
|
def validate_environment(cls, values: Dict) -> Dict:
|
|
"""Validate the environment."""
|
|
values = initialize_client(values)
|
|
return values
|
|
|
|
def _run(
|
|
self,
|
|
query: str,
|
|
num_results: int,
|
|
text_contents_options: Optional[Union[TextContentsOptions, bool]] = None,
|
|
highlights: Optional[Union[HighlightsContentsOptions, bool]] = None,
|
|
include_domains: Optional[List[str]] = None,
|
|
exclude_domains: Optional[List[str]] = None,
|
|
start_crawl_date: Optional[str] = None,
|
|
end_crawl_date: Optional[str] = None,
|
|
start_published_date: Optional[str] = None,
|
|
end_published_date: Optional[str] = None,
|
|
use_autoprompt: Optional[bool] = None,
|
|
run_manager: Optional[CallbackManagerForToolRun] = None,
|
|
) -> Union[List[Dict], str]:
|
|
"""Use the tool."""
|
|
try:
|
|
return self.client.search_and_contents(
|
|
query,
|
|
num_results=num_results,
|
|
text=text_contents_options, # type: ignore
|
|
highlights=highlights, # type: ignore
|
|
include_domains=include_domains,
|
|
exclude_domains=exclude_domains,
|
|
start_crawl_date=start_crawl_date,
|
|
end_crawl_date=end_crawl_date,
|
|
start_published_date=start_published_date,
|
|
end_published_date=end_published_date,
|
|
use_autoprompt=use_autoprompt,
|
|
) # type: ignore
|
|
except Exception as e:
|
|
return repr(e)
|
|
|
|
|
|
class ExaFindSimilarResults(BaseTool):
|
|
"""Tool that queries the Metaphor Search API and gets back json."""
|
|
|
|
name: str = "exa_find_similar_results_json"
|
|
description: str = (
|
|
"A wrapper around Exa Find Similar. "
|
|
"Input should be an Exa-optimized query. "
|
|
"Output is a JSON array of the query results"
|
|
)
|
|
client: Exa = Field(default=None)
|
|
exa_api_key: SecretStr = Field(default=None)
|
|
exa_base_url: Optional[str] = None
|
|
|
|
@root_validator(pre=True)
|
|
def validate_environment(cls, values: Dict) -> Dict:
|
|
"""Validate the environment."""
|
|
values = initialize_client(values)
|
|
return values
|
|
|
|
def _run(
|
|
self,
|
|
url: str,
|
|
num_results: int,
|
|
text_contents_options: Optional[Union[TextContentsOptions, bool]] = None,
|
|
highlights: Optional[Union[HighlightsContentsOptions, bool]] = None,
|
|
include_domains: Optional[List[str]] = None,
|
|
exclude_domains: Optional[List[str]] = None,
|
|
start_crawl_date: Optional[str] = None,
|
|
end_crawl_date: Optional[str] = None,
|
|
start_published_date: Optional[str] = None,
|
|
end_published_date: Optional[str] = None,
|
|
exclude_source_domain: Optional[bool] = None,
|
|
category: Optional[str] = None,
|
|
run_manager: Optional[CallbackManagerForToolRun] = None,
|
|
) -> Union[List[Dict], str]:
|
|
"""Use the tool."""
|
|
try:
|
|
return self.client.find_similar_and_contents(
|
|
url,
|
|
num_results=num_results,
|
|
text=text_contents_options, # type: ignore
|
|
highlights=highlights, # type: ignore
|
|
include_domains=include_domains,
|
|
exclude_domains=exclude_domains,
|
|
start_crawl_date=start_crawl_date,
|
|
end_crawl_date=end_crawl_date,
|
|
start_published_date=start_published_date,
|
|
end_published_date=end_published_date,
|
|
exclude_source_domain=exclude_source_domain,
|
|
category=category,
|
|
) # type: ignore
|
|
except Exception as e:
|
|
return repr(e)
|