mirror of
https://github.com/hwchase17/langchain.git
synced 2025-06-02 04:58:46 +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()
```
125 lines
3.9 KiB
Python
125 lines
3.9 KiB
Python
"""Test openai embeddings."""
|
|
|
|
import os
|
|
from typing import Any
|
|
|
|
import numpy as np
|
|
import pytest
|
|
|
|
from langchain_community.embeddings import AzureOpenAIEmbeddings
|
|
|
|
OPENAI_API_VERSION = os.environ.get("AZURE_OPENAI_API_VERSION", "")
|
|
OPENAI_API_BASE = os.environ.get("AZURE_OPENAI_API_BASE", "")
|
|
OPENAI_API_KEY = os.environ.get("AZURE_OPENAI_API_KEY", "")
|
|
DEPLOYMENT_NAME = os.environ.get(
|
|
"AZURE_OPENAI_DEPLOYMENT_NAME",
|
|
os.environ.get("AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME", ""),
|
|
)
|
|
|
|
|
|
def _get_embeddings(**kwargs: Any) -> AzureOpenAIEmbeddings:
|
|
return AzureOpenAIEmbeddings( # type: ignore[call-arg]
|
|
azure_deployment=DEPLOYMENT_NAME,
|
|
api_version=OPENAI_API_VERSION,
|
|
openai_api_base=OPENAI_API_BASE,
|
|
openai_api_key=OPENAI_API_KEY,
|
|
**kwargs,
|
|
)
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
def test_azure_openai_embedding_documents() -> None:
|
|
"""Test openai embeddings."""
|
|
documents = ["foo bar"]
|
|
embedding = _get_embeddings()
|
|
output = embedding.embed_documents(documents)
|
|
assert len(output) == 1
|
|
assert len(output[0]) == 1536
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
def test_azure_openai_embedding_documents_multiple() -> None:
|
|
"""Test openai embeddings."""
|
|
documents = ["foo bar", "bar foo", "foo"]
|
|
embedding = _get_embeddings(chunk_size=2)
|
|
embedding.embedding_ctx_length = 8191
|
|
output = embedding.embed_documents(documents)
|
|
assert embedding.chunk_size == 2
|
|
assert len(output) == 3
|
|
assert len(output[0]) == 1536
|
|
assert len(output[1]) == 1536
|
|
assert len(output[2]) == 1536
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
def test_azure_openai_embedding_documents_chunk_size() -> None:
|
|
"""Test openai embeddings."""
|
|
documents = ["foo bar"] * 20
|
|
embedding = _get_embeddings()
|
|
embedding.embedding_ctx_length = 8191
|
|
output = embedding.embed_documents(documents)
|
|
# Max 16 chunks per batch on Azure OpenAI embeddings
|
|
assert embedding.chunk_size == 16
|
|
assert len(output) == 20
|
|
assert all([len(out) == 1536 for out in output])
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
async def test_azure_openai_embedding_documents_async_multiple() -> None:
|
|
"""Test openai embeddings."""
|
|
documents = ["foo bar", "bar foo", "foo"]
|
|
embedding = _get_embeddings(chunk_size=2)
|
|
embedding.embedding_ctx_length = 8191
|
|
output = await embedding.aembed_documents(documents)
|
|
assert len(output) == 3
|
|
assert len(output[0]) == 1536
|
|
assert len(output[1]) == 1536
|
|
assert len(output[2]) == 1536
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
def test_azure_openai_embedding_query() -> None:
|
|
"""Test openai embeddings."""
|
|
document = "foo bar"
|
|
embedding = _get_embeddings()
|
|
output = embedding.embed_query(document)
|
|
assert len(output) == 1536
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
async def test_azure_openai_embedding_async_query() -> None:
|
|
"""Test openai embeddings."""
|
|
document = "foo bar"
|
|
embedding = _get_embeddings()
|
|
output = await embedding.aembed_query(document)
|
|
assert len(output) == 1536
|
|
|
|
|
|
@pytest.mark.skip(reason="Unblock scheduled testing. TODO: fix.")
|
|
def test_azure_openai_embedding_with_empty_string() -> None:
|
|
"""Test openai embeddings with empty string."""
|
|
import openai
|
|
|
|
document = ["", "abc"]
|
|
embedding = _get_embeddings()
|
|
output = embedding.embed_documents(document)
|
|
assert len(output) == 2
|
|
assert len(output[0]) == 1536
|
|
expected_output = openai.Embedding.create(input="", model="text-embedding-ada-002")[
|
|
"data"
|
|
][0]["embedding"]
|
|
assert np.allclose(output[0], expected_output)
|
|
assert len(output[1]) == 1536
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
def test_embed_documents_normalized() -> None:
|
|
output = _get_embeddings().embed_documents(["foo walked to the market"])
|
|
assert np.isclose(np.linalg.norm(output[0]), 1.0)
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
def test_embed_query_normalized() -> None:
|
|
output = _get_embeddings().embed_query("foo walked to the market")
|
|
assert np.isclose(np.linalg.norm(output), 1.0)
|