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()
```
76 lines
2.3 KiB
Python
76 lines
2.3 KiB
Python
"""This file is for LLMRails Embedding"""
|
|
|
|
from typing import Dict, List, Optional
|
|
|
|
import requests
|
|
from langchain_core.embeddings import Embeddings
|
|
from langchain_core.pydantic_v1 import BaseModel, Extra, SecretStr, root_validator
|
|
from langchain_core.utils import convert_to_secret_str, get_from_dict_or_env
|
|
|
|
|
|
class LLMRailsEmbeddings(BaseModel, Embeddings):
|
|
"""LLMRails embedding models.
|
|
|
|
To use, you should have the environment
|
|
variable ``LLM_RAILS_API_KEY`` set with your API key or pass it
|
|
as a named parameter to the constructor.
|
|
|
|
Model can be one of ["embedding-english-v1","embedding-multi-v1"]
|
|
|
|
Example:
|
|
.. code-block:: python
|
|
|
|
from langchain_community.embeddings import LLMRailsEmbeddings
|
|
cohere = LLMRailsEmbeddings(
|
|
model="embedding-english-v1", api_key="my-api-key"
|
|
)
|
|
"""
|
|
|
|
model: str = "embedding-english-v1"
|
|
"""Model name to use."""
|
|
|
|
api_key: Optional[SecretStr] = None
|
|
"""LLMRails API key."""
|
|
|
|
class Config:
|
|
"""Configuration for this pydantic object."""
|
|
|
|
extra = Extra.forbid
|
|
|
|
@root_validator()
|
|
def validate_environment(cls, values: Dict) -> Dict:
|
|
"""Validate that api key exists in environment."""
|
|
api_key = convert_to_secret_str(
|
|
get_from_dict_or_env(values, "api_key", "LLM_RAILS_API_KEY")
|
|
)
|
|
values["api_key"] = api_key
|
|
return values
|
|
|
|
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
"""Call out to Cohere's embedding endpoint.
|
|
|
|
Args:
|
|
texts: The list of texts to embed.
|
|
|
|
Returns:
|
|
List of embeddings, one for each text.
|
|
"""
|
|
response = requests.post(
|
|
"https://api.llmrails.com/v1/embeddings",
|
|
headers={"X-API-KEY": self.api_key.get_secret_value()}, # type: ignore[union-attr]
|
|
json={"input": texts, "model": self.model},
|
|
timeout=60,
|
|
)
|
|
return [item["embedding"] for item in response.json()["data"]]
|
|
|
|
def embed_query(self, text: str) -> List[float]:
|
|
"""Call out to Cohere's embedding endpoint.
|
|
|
|
Args:
|
|
text: The text to embed.
|
|
|
|
Returns:
|
|
Embeddings for the text.
|
|
"""
|
|
return self.embed_documents([text])[0]
|