mirror of
https://github.com/hwchase17/langchain.git
synced 2025-08-09 04:50:37 +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()
```
99 lines
3.6 KiB
Python
99 lines
3.6 KiB
Python
from typing import ( # type: ignore[import-not-found, import-not-found]
|
|
Any,
|
|
Dict,
|
|
List,
|
|
Literal,
|
|
Optional,
|
|
Union,
|
|
)
|
|
|
|
from exa_py import Exa # type: ignore
|
|
from exa_py.api import HighlightsContentsOptions, TextContentsOptions # type: ignore
|
|
from langchain_core.callbacks import CallbackManagerForRetrieverRun
|
|
from langchain_core.documents import Document
|
|
from langchain_core.pydantic_v1 import Field, SecretStr, root_validator
|
|
from langchain_core.retrievers import BaseRetriever
|
|
|
|
from langchain_exa._utilities import initialize_client
|
|
|
|
|
|
def _get_metadata(result: Any) -> Dict[str, Any]:
|
|
"""Get the metadata from a result object."""
|
|
metadata = {
|
|
"title": result.title,
|
|
"url": result.url,
|
|
"id": result.id,
|
|
"score": result.score,
|
|
"published_date": result.published_date,
|
|
"author": result.author,
|
|
}
|
|
if getattr(result, "highlights"):
|
|
metadata["highlights"] = result.highlights
|
|
if getattr(result, "highlight_scores"):
|
|
metadata["highlight_scores"] = result.highlight_scores
|
|
return metadata
|
|
|
|
|
|
class ExaSearchRetriever(BaseRetriever):
|
|
"""Exa Search retriever."""
|
|
|
|
k: int = 10 # num_results
|
|
"""The number of search results to return."""
|
|
include_domains: Optional[List[str]] = None
|
|
"""A list of domains to include in the search."""
|
|
exclude_domains: Optional[List[str]] = None
|
|
"""A list of domains to exclude from the search."""
|
|
start_crawl_date: Optional[str] = None
|
|
"""The start date for the crawl (in YYYY-MM-DD format)."""
|
|
end_crawl_date: Optional[str] = None
|
|
"""The end date for the crawl (in YYYY-MM-DD format)."""
|
|
start_published_date: Optional[str] = None
|
|
"""The start date for when the document was published (in YYYY-MM-DD format)."""
|
|
end_published_date: Optional[str] = None
|
|
"""The end date for when the document was published (in YYYY-MM-DD format)."""
|
|
use_autoprompt: Optional[bool] = None
|
|
"""Whether to use autoprompt for the search."""
|
|
type: str = "neural"
|
|
"""The type of search, 'keyword' or 'neural'. Default: neural"""
|
|
highlights: Optional[Union[HighlightsContentsOptions, bool]] = None
|
|
"""Whether to set the page content to the highlights of the results."""
|
|
text_contents_options: Union[TextContentsOptions, Literal[True]] = True
|
|
"""How to set the page content of the 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 _get_relevant_documents(
|
|
self, query: str, *, run_manager: CallbackManagerForRetrieverRun
|
|
) -> List[Document]:
|
|
response = self.client.search_and_contents( # type: ignore[misc]
|
|
query,
|
|
num_results=self.k,
|
|
text=self.text_contents_options,
|
|
highlights=self.highlights, # type: ignore
|
|
include_domains=self.include_domains,
|
|
exclude_domains=self.exclude_domains,
|
|
start_crawl_date=self.start_crawl_date,
|
|
end_crawl_date=self.end_crawl_date,
|
|
start_published_date=self.start_published_date,
|
|
end_published_date=self.end_published_date,
|
|
use_autoprompt=self.use_autoprompt,
|
|
)
|
|
|
|
results = response.results
|
|
|
|
return [
|
|
Document(
|
|
page_content=(result.text),
|
|
metadata=_get_metadata(result),
|
|
)
|
|
for result in results
|
|
]
|