Files
LEANN/tests/test_main_cli.py
Andy Lee 8c988cf98b refactor: improve test structure and fix main_cli example
- Move pytest configuration from pytest.ini to pyproject.toml
- Remove unnecessary run_tests.py script (use test extras instead)
- Fix main_cli_example.py to properly use command line arguments for LLM config
- Add test_readme_examples.py to test code examples from README
- Refactor tests to use pytest fixtures and parametrization
- Update test documentation to reflect new structure
- Set proper environment variables in CI for test execution
2025-07-28 14:25:48 -07:00

115 lines
3.4 KiB
Python

"""
Test main_cli_example functionality using pytest.
"""
import os
import subprocess
import sys
import tempfile
from pathlib import Path
import pytest
@pytest.fixture
def test_data_dir():
"""Return the path to test data directory."""
return Path("examples/data")
def test_main_cli_simulated(test_data_dir):
"""Test main_cli with simulated LLM."""
with tempfile.TemporaryDirectory() as temp_dir:
cmd = [
sys.executable,
"examples/main_cli_example.py",
"--llm",
"simulated",
"--embedding-model",
"facebook/contriever",
"--embedding-mode",
"sentence-transformers",
"--index-dir",
temp_dir,
"--data-dir",
str(test_data_dir),
"--query",
"What is Pride and Prejudice about?",
]
env = os.environ.copy()
env["HF_HUB_DISABLE_SYMLINKS"] = "1"
env["TOKENIZERS_PARALLELISM"] = "false"
result = subprocess.run(cmd, capture_output=True, text=True, timeout=600, env=env)
# Check return code
assert result.returncode == 0, f"Command failed: {result.stderr}"
# Verify output
output = result.stdout + result.stderr
assert "Leann index built at" in output or "Using existing index" in output
assert "This is a simulated answer" in output
@pytest.mark.skipif(not os.environ.get("OPENAI_API_KEY"), reason="OpenAI API key not available")
def test_main_cli_openai(test_data_dir):
"""Test main_cli with OpenAI embeddings."""
with tempfile.TemporaryDirectory() as temp_dir:
cmd = [
sys.executable,
"examples/main_cli_example.py",
"--llm",
"simulated", # Use simulated LLM to avoid GPT-4 costs
"--embedding-model",
"text-embedding-3-small",
"--embedding-mode",
"openai",
"--index-dir",
temp_dir,
"--data-dir",
str(test_data_dir),
"--query",
"What is Pride and Prejudice about?",
]
env = os.environ.copy()
env["TOKENIZERS_PARALLELISM"] = "false"
result = subprocess.run(cmd, capture_output=True, text=True, timeout=600, env=env)
assert result.returncode == 0, f"Command failed: {result.stderr}"
# Verify cosine distance was used
output = result.stdout + result.stderr
assert any(
msg in output
for msg in [
"distance_metric='cosine'",
"Automatically setting distance_metric='cosine'",
"Using cosine distance",
]
)
@pytest.mark.xfail(sys.platform == "darwin", reason="May fail on macOS due to C++ ABI issues")
def test_main_cli_error_handling(test_data_dir):
"""Test main_cli with invalid parameters."""
with tempfile.TemporaryDirectory() as temp_dir:
cmd = [
sys.executable,
"examples/main_cli_example.py",
"--llm",
"invalid_llm_type",
"--index-dir",
temp_dir,
"--data-dir",
str(test_data_dir),
]
result = subprocess.run(cmd, capture_output=True, text=True, timeout=60)
# Should fail with invalid LLM type
assert result.returncode != 0
assert "Unknown LLM type" in result.stderr or "invalid_llm_type" in result.stderr