mirror of
https://github.com/hwchase17/langchain.git
synced 2025-04-27 11:41:51 +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()
```
78 lines
2.9 KiB
Python
78 lines
2.9 KiB
Python
from typing import Callable, Dict, Iterator, Optional
|
|
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.document_loaders.base import BaseLoader
|
|
from langchain_community.utilities.tensorflow_datasets import TensorflowDatasets
|
|
|
|
|
|
class TensorflowDatasetLoader(BaseLoader):
|
|
"""Load from `TensorFlow Dataset`.
|
|
|
|
Attributes:
|
|
dataset_name: the name of the dataset to load
|
|
split_name: the name of the split to load.
|
|
load_max_docs: a limit to the number of loaded documents. Defaults to 100.
|
|
sample_to_document_function: a function that converts a dataset sample
|
|
into a Document
|
|
|
|
Example:
|
|
.. code-block:: python
|
|
|
|
from langchain_community.document_loaders import TensorflowDatasetLoader
|
|
|
|
def mlqaen_example_to_document(example: dict) -> Document:
|
|
return Document(
|
|
page_content=decode_to_str(example["context"]),
|
|
metadata={
|
|
"id": decode_to_str(example["id"]),
|
|
"title": decode_to_str(example["title"]),
|
|
"question": decode_to_str(example["question"]),
|
|
"answer": decode_to_str(example["answers"]["text"][0]),
|
|
},
|
|
)
|
|
|
|
tsds_client = TensorflowDatasetLoader(
|
|
dataset_name="mlqa/en",
|
|
split_name="test",
|
|
load_max_docs=100,
|
|
sample_to_document_function=mlqaen_example_to_document,
|
|
)
|
|
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
dataset_name: str,
|
|
split_name: str,
|
|
load_max_docs: Optional[int] = 100,
|
|
sample_to_document_function: Optional[Callable[[Dict], Document]] = None,
|
|
):
|
|
"""Initialize the TensorflowDatasetLoader.
|
|
|
|
Args:
|
|
dataset_name: the name of the dataset to load
|
|
split_name: the name of the split to load.
|
|
load_max_docs: a limit to the number of loaded documents. Defaults to 100.
|
|
sample_to_document_function: a function that converts a dataset sample
|
|
into a Document.
|
|
"""
|
|
self.dataset_name: str = dataset_name
|
|
self.split_name: str = split_name
|
|
self.load_max_docs = load_max_docs
|
|
"""The maximum number of documents to load."""
|
|
self.sample_to_document_function: Optional[Callable[[Dict], Document]] = (
|
|
sample_to_document_function
|
|
)
|
|
"""Custom function that transform a dataset sample into a Document."""
|
|
|
|
self._tfds_client = TensorflowDatasets( # type: ignore[call-arg]
|
|
dataset_name=self.dataset_name,
|
|
split_name=self.split_name,
|
|
load_max_docs=self.load_max_docs, # type: ignore[arg-type]
|
|
sample_to_document_function=self.sample_to_document_function,
|
|
)
|
|
|
|
def lazy_load(self) -> Iterator[Document]:
|
|
yield from self._tfds_client.lazy_load()
|