[Multi-vector]Add timing instrumentation and multi-dataset support for multi-vector…

[yichuan-w]

… retrieval

• Add timing measurements for search operations (load and core time)
• Increase embedding batch size from 1 to 32 for better performance
• Add explicit memory cleanup with del all_embeddings
• Support loading and merging multiple datasets with different splits
• Add CLI arguments for search method selection (ann/exact/exact-all)
• Auto-detect image field names across different dataset structures
• Print candidate doc counts for performance monitoring

🤖 Generated with Claude Code

What does this PR do?

Related Issues

Fixes #

Checklist

• [ ] Tests pass (uv run pytest)
• [ ] Code formatted (ruff format and ruff check)
• [ ] Pre-commit hooks pass (pre-commit run --all-files)