mirror of
https://github.com/hwchase17/langchain.git
synced 2025-11-29 18:17:10 +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()
```
77 lines
2.5 KiB
Python
77 lines
2.5 KiB
Python
"""Anyscale embeddings wrapper."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Dict
|
|
|
|
from langchain_core.pydantic_v1 import Field, SecretStr, root_validator
|
|
from langchain_core.utils import convert_to_secret_str, get_from_dict_or_env
|
|
|
|
from langchain_community.embeddings.openai import OpenAIEmbeddings
|
|
from langchain_community.utils.openai import is_openai_v1
|
|
|
|
DEFAULT_API_BASE = "https://api.endpoints.anyscale.com/v1"
|
|
DEFAULT_MODEL = "thenlper/gte-large"
|
|
|
|
|
|
class AnyscaleEmbeddings(OpenAIEmbeddings):
|
|
"""`Anyscale` Embeddings API."""
|
|
|
|
anyscale_api_key: SecretStr = Field(default=None)
|
|
"""AnyScale Endpoints API keys."""
|
|
model: str = Field(default=DEFAULT_MODEL)
|
|
"""Model name to use."""
|
|
anyscale_api_base: str = Field(default=DEFAULT_API_BASE)
|
|
"""Base URL path for API requests."""
|
|
tiktoken_enabled: bool = False
|
|
"""Set this to False for non-OpenAI implementations of the embeddings API"""
|
|
embedding_ctx_length: int = 500
|
|
"""The maximum number of tokens to embed at once."""
|
|
|
|
@property
|
|
def lc_secrets(self) -> Dict[str, str]:
|
|
return {
|
|
"anyscale_api_key": "ANYSCALE_API_KEY",
|
|
}
|
|
|
|
@root_validator()
|
|
def validate_environment(cls, values: dict) -> dict:
|
|
"""Validate that api key and python package exists in environment."""
|
|
values["anyscale_api_key"] = convert_to_secret_str(
|
|
get_from_dict_or_env(
|
|
values,
|
|
"anyscale_api_key",
|
|
"ANYSCALE_API_KEY",
|
|
)
|
|
)
|
|
values["anyscale_api_base"] = get_from_dict_or_env(
|
|
values,
|
|
"anyscale_api_base",
|
|
"ANYSCALE_API_BASE",
|
|
default=DEFAULT_API_BASE,
|
|
)
|
|
try:
|
|
import openai
|
|
|
|
except ImportError:
|
|
raise ImportError(
|
|
"Could not import openai python package. "
|
|
"Please install it with `pip install openai`."
|
|
)
|
|
if is_openai_v1():
|
|
# For backwards compatibility.
|
|
client_params = {
|
|
"api_key": values["anyscale_api_key"].get_secret_value(),
|
|
"base_url": values["anyscale_api_base"],
|
|
}
|
|
values["client"] = openai.OpenAI(**client_params).embeddings
|
|
else:
|
|
values["openai_api_base"] = values["anyscale_api_base"]
|
|
values["openai_api_key"] = values["anyscale_api_key"].get_secret_value()
|
|
values["client"] = openai.Embedding
|
|
return values
|
|
|
|
@property
|
|
def _llm_type(self) -> str:
|
|
return "anyscale-embedding"
|