test_vectorstore.py

"""Test script to verify the vectorstore connection and retrieval"""

from dotenv import load_dotenv
from src.vectorstore import create_vectorstore

# Load environment variables
load_dotenv()

print("Initializing vectorstore...")
try:
    vectorstore = create_vectorstore()
    print("✓ Vectorstore created successfully")

    # Test with default threshold (should now get good matches with Jina-CLIP-v2)
    print("\nTesting similarity search with Jina-CLIP-v2 embeddings...")
    query = "data visualization storytelling narrative"
    results = vectorstore.similarity_search(query, k=5)

    print(f"\n✓ Found {len(results)} documents")
    print("\nSample results:")
    for i, doc in enumerate(results[:3], 1):
        print(f"\n--- Document {i} ---")
        print(f"Source: {doc.metadata.get('source_id', 'Unknown')}")
        print(f"Type: {doc.metadata.get('source_type', 'N/A')}")
        print(f"Page: {doc.metadata.get('page_number', 'N/A')}")
        print(f"Content preview: {doc.page_content[:150]}...")
        print(f"Similarity: {doc.metadata.get('similarity', 'N/A')}")

    print("\n✓ All tests passed!")

except Exception as e:
    print(f"✗ Error: {e}")
    import traceback
    traceback.print_exc()