ab339886dd
- Add --distance-metric parameter to diskann_embedding_server.py for consistency with other backends - Remove pytest.skip and pytest.xfail markers for macOS C++ ABI issues as they have been fixed - Fix test assertions to handle SearchResult objects correctly - All tests now pass on macOS with the C++ ABI compatibility fixes
86 lines
2.5 KiB
Python
86 lines
2.5 KiB
Python
"""
|
|
Basic functionality tests for CI pipeline using pytest.
|
|
"""
|
|
|
|
import tempfile
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
|
|
def test_imports():
|
|
"""Test that all packages can be imported."""
|
|
|
|
# Test C++ extensions
|
|
|
|
|
|
@pytest.mark.parametrize("backend_name", ["hnsw", "diskann"])
|
|
def test_backend_basic(backend_name):
|
|
"""Test basic functionality for each backend."""
|
|
from leann.api import LeannBuilder, LeannSearcher, SearchResult
|
|
|
|
# Create temporary directory for index
|
|
with tempfile.TemporaryDirectory() as temp_dir:
|
|
index_path = str(Path(temp_dir) / f"test.{backend_name}")
|
|
|
|
# Test with small data
|
|
texts = [f"This is document {i} about topic {i % 5}" for i in range(100)]
|
|
|
|
# Configure builder based on backend
|
|
if backend_name == "hnsw":
|
|
builder = LeannBuilder(
|
|
backend_name="hnsw",
|
|
embedding_model="facebook/contriever",
|
|
embedding_mode="sentence-transformers",
|
|
M=16,
|
|
efConstruction=200,
|
|
)
|
|
else: # diskann
|
|
builder = LeannBuilder(
|
|
backend_name="diskann",
|
|
embedding_model="facebook/contriever",
|
|
embedding_mode="sentence-transformers",
|
|
num_neighbors=32,
|
|
search_list_size=50,
|
|
)
|
|
|
|
# Add texts
|
|
for text in texts:
|
|
builder.add_text(text)
|
|
|
|
# Build index
|
|
builder.build_index(index_path)
|
|
|
|
# Test search
|
|
searcher = LeannSearcher(index_path)
|
|
results = searcher.search("document about topic 2", top_k=5)
|
|
|
|
# Verify results
|
|
assert len(results) > 0
|
|
assert isinstance(results[0], SearchResult)
|
|
assert "topic 2" in results[0].text or "document" in results[0].text
|
|
|
|
|
|
def test_large_index():
|
|
"""Test with larger dataset."""
|
|
from leann.api import LeannBuilder, LeannSearcher
|
|
|
|
with tempfile.TemporaryDirectory() as temp_dir:
|
|
index_path = str(Path(temp_dir) / "test_large.hnsw")
|
|
texts = [f"Document {i}: {' '.join([f'word{j}' for j in range(50)])}" for i in range(1000)]
|
|
|
|
builder = LeannBuilder(
|
|
backend_name="hnsw",
|
|
embedding_model="facebook/contriever",
|
|
embedding_mode="sentence-transformers",
|
|
)
|
|
|
|
for text in texts:
|
|
builder.add_text(text)
|
|
|
|
builder.build_index(index_path)
|
|
|
|
searcher = LeannSearcher(index_path)
|
|
results = searcher.search(["word10 word20"], top_k=10)
|
|
assert len(results[0]) == 10
|