mirror of
https://github.com/hwchase17/langchain.git
synced 2025-06-06 15:13:56 +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()
```
117 lines
3.7 KiB
Python
117 lines
3.7 KiB
Python
"""test Databricks LLM"""
|
|
|
|
from pathlib import Path
|
|
from typing import Any, Dict
|
|
|
|
import pytest
|
|
from pytest import MonkeyPatch
|
|
|
|
from langchain_community.llms.databricks import (
|
|
Databricks,
|
|
_load_pickled_fn_from_hex_string,
|
|
)
|
|
from langchain_community.llms.loading import load_llm
|
|
from tests.integration_tests.llms.utils import assert_llm_equality
|
|
|
|
|
|
class MockDatabricksServingEndpointClient:
|
|
def __init__(
|
|
self,
|
|
host: str,
|
|
api_token: str,
|
|
endpoint_name: str,
|
|
databricks_uri: str,
|
|
task: str,
|
|
):
|
|
self.host = host
|
|
self.api_token = api_token
|
|
self.endpoint_name = endpoint_name
|
|
self.databricks_uri = databricks_uri
|
|
self.task = task
|
|
|
|
|
|
def transform_input(**request: Any) -> Dict[str, Any]:
|
|
request["messages"] = [{"role": "user", "content": request["prompt"]}]
|
|
del request["prompt"]
|
|
return request
|
|
|
|
|
|
@pytest.mark.requires("cloudpickle")
|
|
def test_serde_transform_input_fn(monkeypatch: MonkeyPatch) -> None:
|
|
import cloudpickle
|
|
|
|
monkeypatch.setattr(
|
|
"langchain_community.llms.databricks._DatabricksServingEndpointClient",
|
|
MockDatabricksServingEndpointClient,
|
|
)
|
|
monkeypatch.setenv("DATABRICKS_HOST", "my-default-host")
|
|
monkeypatch.setenv("DATABRICKS_TOKEN", "my-default-token")
|
|
|
|
llm = Databricks(
|
|
endpoint_name="some_end_point_name", # Value should not matter for this test
|
|
transform_input_fn=transform_input,
|
|
allow_dangerous_deserialization=True,
|
|
)
|
|
params = llm._default_params
|
|
pickled_string = cloudpickle.dumps(transform_input).hex()
|
|
assert params["transform_input_fn"] == pickled_string
|
|
|
|
request = {"prompt": "What is the meaning of life?"}
|
|
fn = _load_pickled_fn_from_hex_string(
|
|
data=params["transform_input_fn"],
|
|
allow_dangerous_deserialization=True,
|
|
)
|
|
assert fn(**request) == transform_input(**request)
|
|
|
|
|
|
def test_saving_loading_llm(monkeypatch: MonkeyPatch, tmp_path: Path) -> None:
|
|
monkeypatch.setattr(
|
|
"langchain_community.llms.databricks._DatabricksServingEndpointClient",
|
|
MockDatabricksServingEndpointClient,
|
|
)
|
|
monkeypatch.setenv("DATABRICKS_HOST", "my-default-host")
|
|
monkeypatch.setenv("DATABRICKS_TOKEN", "my-default-token")
|
|
|
|
llm = Databricks(
|
|
endpoint_name="chat",
|
|
temperature=0.1,
|
|
)
|
|
llm.save(file_path=tmp_path / "databricks.yaml")
|
|
|
|
loaded_llm = load_llm(tmp_path / "databricks.yaml")
|
|
assert_llm_equality(llm, loaded_llm)
|
|
|
|
|
|
@pytest.mark.requires("cloudpickle")
|
|
def test_saving_loading_llm_dangerous_serde_check(
|
|
monkeypatch: MonkeyPatch, tmp_path: Path
|
|
) -> None:
|
|
monkeypatch.setattr(
|
|
"langchain_community.llms.databricks._DatabricksServingEndpointClient",
|
|
MockDatabricksServingEndpointClient,
|
|
)
|
|
monkeypatch.setenv("DATABRICKS_HOST", "my-default-host")
|
|
monkeypatch.setenv("DATABRICKS_TOKEN", "my-default-token")
|
|
|
|
llm1 = Databricks(
|
|
endpoint_name="chat",
|
|
temperature=0.1,
|
|
transform_input_fn=lambda x, y, **kwargs: {},
|
|
)
|
|
llm1.save(file_path=tmp_path / "databricks1.yaml")
|
|
|
|
with pytest.raises(ValueError, match="This code relies on the pickle module."):
|
|
load_llm(tmp_path / "databricks1.yaml")
|
|
|
|
load_llm(tmp_path / "databricks1.yaml", allow_dangerous_deserialization=True)
|
|
|
|
llm2 = Databricks(
|
|
endpoint_name="chat", temperature=0.1, transform_output_fn=lambda x: "test"
|
|
)
|
|
llm2.save(file_path=tmp_path / "databricks2.yaml")
|
|
|
|
with pytest.raises(ValueError, match="This code relies on the pickle module."):
|
|
load_llm(tmp_path / "databricks2.yaml")
|
|
|
|
load_llm(tmp_path / "databricks2.yaml", allow_dangerous_deserialization=True)
|