mirror of
https://github.com/hwchase17/langchain.git
synced 2025-10-22 09:41:52 +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()
```
74 lines
2.4 KiB
Python
74 lines
2.4 KiB
Python
"""Test WatsonxEmbeddings.
|
|
|
|
You'll need to set WATSONX_APIKEY and WATSONX_PROJECT_ID environment variables.
|
|
"""
|
|
|
|
import os
|
|
|
|
from ibm_watsonx_ai import APIClient # type: ignore
|
|
from ibm_watsonx_ai.metanames import EmbedTextParamsMetaNames # type: ignore
|
|
|
|
from langchain_ibm import WatsonxEmbeddings
|
|
|
|
WX_APIKEY = os.environ.get("WATSONX_APIKEY", "")
|
|
WX_PROJECT_ID = os.environ.get("WATSONX_PROJECT_ID", "")
|
|
|
|
URL = "https://us-south.ml.cloud.ibm.com"
|
|
MODEL_ID = "ibm/slate-125m-english-rtrvr"
|
|
|
|
DOCUMENTS = ["What is a generative ai?", "What is a loan and how does it works?"]
|
|
|
|
|
|
def test_01_generate_embed_documents() -> None:
|
|
watsonx_embedding = WatsonxEmbeddings(
|
|
model_id=MODEL_ID,
|
|
url=URL, # type: ignore[arg-type]
|
|
project_id=WX_PROJECT_ID, # type: ignore[arg-type]
|
|
)
|
|
generate_embedding = watsonx_embedding.embed_documents(texts=DOCUMENTS)
|
|
assert len(generate_embedding) == len(DOCUMENTS)
|
|
assert all(isinstance(el, float) for el in generate_embedding[0])
|
|
|
|
|
|
def test_02_generate_embed_query() -> None:
|
|
watsonx_embedding = WatsonxEmbeddings(
|
|
model_id=MODEL_ID,
|
|
url=URL, # type: ignore[arg-type]
|
|
project_id=WX_PROJECT_ID,
|
|
)
|
|
generate_embedding = watsonx_embedding.embed_query(text=DOCUMENTS[0])
|
|
assert isinstance(generate_embedding, list) and isinstance(
|
|
generate_embedding[0], float
|
|
)
|
|
|
|
|
|
def test_03_generate_embed_documents_with_param() -> None:
|
|
embed_params = {
|
|
EmbedTextParamsMetaNames.TRUNCATE_INPUT_TOKENS: 3,
|
|
}
|
|
watsonx_embedding = WatsonxEmbeddings(
|
|
model_id=MODEL_ID,
|
|
url=URL, # type: ignore[arg-type]
|
|
project_id=WX_PROJECT_ID,
|
|
params=embed_params, # type: ignore[arg-type]
|
|
)
|
|
generate_embedding = watsonx_embedding.embed_documents(texts=DOCUMENTS)
|
|
assert len(generate_embedding) == len(DOCUMENTS)
|
|
assert all(isinstance(el, float) for el in generate_embedding[0])
|
|
|
|
|
|
def test_10_generate_embed_query_with_client_initialization() -> None:
|
|
watsonx_client = APIClient(
|
|
credentials={
|
|
"url": URL,
|
|
"apikey": WX_APIKEY,
|
|
}
|
|
)
|
|
watsonx_embedding = WatsonxEmbeddings(
|
|
model_id=MODEL_ID, project_id=WX_PROJECT_ID, watsonx_client=watsonx_client
|
|
)
|
|
generate_embedding = watsonx_embedding.embed_query(text=DOCUMENTS[0])
|
|
assert isinstance(generate_embedding, list) and isinstance(
|
|
generate_embedding[0], float
|
|
)
|