TBNilles/LEANN
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: resolve all ruff linting errors and add lint CI check

Browse Source 
- Fix ambiguous fullwidth characters (commas, parentheses) in strings and comments
- Replace Chinese comments with English equivalents
- Fix unused imports with proper noqa annotations for intentional imports
- Fix bare except clauses with specific exception types
- Fix redefined variables and undefined names
- Add ruff noqa annotations for generated protobuf files
- Add lint and format check to GitHub Actions CI pipeline
This commit is contained in:
Andy Lee
2025-07-26 22:35:12 -07:00
parent 8537a6b17e
commit b3e9ee96fa
53 changed files with 5655 additions and 5220 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
examples/openai_hnsw_example.py
View File

@@ -6,22 +6,24 @@ Complete example showing how to build and search with OpenAI embeddings using HN
"""
import os
import dotenv
from pathlib import Path
import dotenv
from leann.api import LeannBuilder, LeannSearcher
# Load environment variables
dotenv.load_dotenv()
def main():
# Check if OpenAI API key is available
api_key = os.getenv("OPENAI_API_KEY")
if not api_key:
print("ERROR: OPENAI_API_KEY environment variable not set")
return False
print(f"✅ OpenAI API key found: {api_key[:10]}...")
# Sample texts
sample_texts = [
"Machine learning is a powerful technology that enables computers to learn from data.",
@@ -33,15 +35,15 @@ def main():
"Artificial intelligence aims to create machines that can perform human-like tasks.",
"Python is a popular programming language used extensively in data science and AI.",
"Neural networks are inspired by the structure and function of the human brain.",
"Big data refers to extremely large datasets that require special tools to process."
"Big data refers to extremely large datasets that require special tools to process.",
]
INDEX_DIR = Path("./simple_openai_test_index")
INDEX_PATH = str(INDEX_DIR / "simple_test.leann")
print(f"\n=== Building Index with OpenAI Embeddings ===")
print("\n=== Building Index with OpenAI Embeddings ===")
print(f"Index path: {INDEX_PATH}")
try:
# Use proper configuration for OpenAI embeddings
builder = LeannBuilder(
@@ -49,60 +51,63 @@ def main():
embedding_model="text-embedding-3-small",
embedding_mode="openai",
# HNSW settings for OpenAI embeddings
M=16, # Smaller graph degree
efConstruction=64, # Smaller construction complexity
is_compact=True, # Enable compact storage for recompute
is_recompute=True, # MUST enable for OpenAI embeddings
M=16, # Smaller graph degree
efConstruction=64, # Smaller construction complexity
is_compact=True, # Enable compact storage for recompute
is_recompute=True, # MUST enable for OpenAI embeddings
num_threads=1,
)
print(f"Adding {len(sample_texts)} texts to the index...")
for i, text in enumerate(sample_texts):
metadata = {"id": f"doc_{i}", "topic": "AI"}
builder.add_text(text, metadata)
print("Building index...")
builder.build_index(INDEX_PATH)
print(f"✅ Index built successfully!")
print("✅ Index built successfully!")
except Exception as e:
print(f"❌ Error building index: {e}")
import traceback
traceback.print_exc()
return False
print(f"\n=== Testing Search ===")
print("\n=== Testing Search ===")
try:
searcher = LeannSearcher(INDEX_PATH)
test_queries = [
"What is machine learning?",
"How do neural networks work?",
"Programming languages for data science"
"Programming languages for data science",
]
for query in test_queries:
print(f"\n🔍 Query: '{query}'")
results = searcher.search(query, top_k=3)
print(f" Found {len(results)} results:")
for i, result in enumerate(results):
print(f" {i+1}. Score: {result.score:.4f}")
print(f" {i + 1}. Score: {result.score:.4f}")
print(f" Text: {result.text[:80]}...")
print(f"\n✅ Search test completed successfully!")
print("\n✅ Search test completed successfully!")
return True
except Exception as e:
print(f"❌ Error during search: {e}")
import traceback
traceback.print_exc()
return False
if __name__ == "__main__":
success = main()
if success:
print(f"\n🎉 Simple OpenAI index test completed successfully!")
print("\n🎉 Simple OpenAI index test completed successfully!")
else:
print(f"\n💥 Simple OpenAI index test failed!")
print("\n💥 Simple OpenAI index test failed!")