mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-02 21:58:46 +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
2.7 KiB
Python
76 lines
2.7 KiB
Python
"""Test FastEmbed embeddings."""
|
|
|
|
import pytest
|
|
|
|
from langchain_community.embeddings.fastembed import FastEmbedEmbeddings
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"model_name", ["sentence-transformers/all-MiniLM-L6-v2", "BAAI/bge-small-en-v1.5"]
|
|
)
|
|
@pytest.mark.parametrize("max_length", [50, 512])
|
|
@pytest.mark.parametrize("doc_embed_type", ["default", "passage"])
|
|
@pytest.mark.parametrize("threads", [0, 10])
|
|
def test_fastembed_embedding_documents(
|
|
model_name: str, max_length: int, doc_embed_type: str, threads: int
|
|
) -> None:
|
|
"""Test fastembed embeddings for documents."""
|
|
documents = ["foo bar", "bar foo"]
|
|
embedding = FastEmbedEmbeddings( # type: ignore[call-arg]
|
|
model_name=model_name,
|
|
max_length=max_length,
|
|
doc_embed_type=doc_embed_type, # type: ignore[arg-type]
|
|
threads=threads,
|
|
)
|
|
output = embedding.embed_documents(documents)
|
|
assert len(output) == 2
|
|
assert len(output[0]) == 384
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"model_name", ["sentence-transformers/all-MiniLM-L6-v2", "BAAI/bge-small-en-v1.5"]
|
|
)
|
|
@pytest.mark.parametrize("max_length", [50, 512])
|
|
def test_fastembed_embedding_query(model_name: str, max_length: int) -> None:
|
|
"""Test fastembed embeddings for query."""
|
|
document = "foo bar"
|
|
embedding = FastEmbedEmbeddings(model_name=model_name, max_length=max_length) # type: ignore[call-arg]
|
|
output = embedding.embed_query(document)
|
|
assert len(output) == 384
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"model_name", ["sentence-transformers/all-MiniLM-L6-v2", "BAAI/bge-small-en-v1.5"]
|
|
)
|
|
@pytest.mark.parametrize("max_length", [50, 512])
|
|
@pytest.mark.parametrize("doc_embed_type", ["default", "passage"])
|
|
@pytest.mark.parametrize("threads", [0, 10])
|
|
async def test_fastembed_async_embedding_documents(
|
|
model_name: str, max_length: int, doc_embed_type: str, threads: int
|
|
) -> None:
|
|
"""Test fastembed embeddings for documents."""
|
|
documents = ["foo bar", "bar foo"]
|
|
embedding = FastEmbedEmbeddings( # type: ignore[call-arg]
|
|
model_name=model_name,
|
|
max_length=max_length,
|
|
doc_embed_type=doc_embed_type, # type: ignore[arg-type]
|
|
threads=threads,
|
|
)
|
|
output = await embedding.aembed_documents(documents)
|
|
assert len(output) == 2
|
|
assert len(output[0]) == 384
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"model_name", ["sentence-transformers/all-MiniLM-L6-v2", "BAAI/bge-small-en-v1.5"]
|
|
)
|
|
@pytest.mark.parametrize("max_length", [50, 512])
|
|
async def test_fastembed_async_embedding_query(
|
|
model_name: str, max_length: int
|
|
) -> None:
|
|
"""Test fastembed embeddings for query."""
|
|
document = "foo bar"
|
|
embedding = FastEmbedEmbeddings(model_name=model_name, max_length=max_length) # type: ignore[call-arg]
|
|
output = await embedding.aembed_query(document)
|
|
assert len(output) == 384
|