- Reproduced the slow search performance issue (15-30s vs expected ~2s)
- Identified root cause: default complexity=64 is too high for fast search
- Created test script demonstrating performance with different complexity values
- Test results show complexity=16-32 achieves ~2s search time (matching paper)
- Added comprehensive analysis document with solutions and recommendations
Key findings:
- Default complexity=64 results in ~36s search time
- Reducing complexity to 16-32 achieves ~2s search time
- beam_width parameter is mainly for DiskANN, not HNSW
- Paper likely used smaller embedding model (~100M) and lower complexity
Solutions provided:
1. Reduce complexity parameter to 16-32 for faster search
2. Consider DiskANN backend for better performance on large datasets
3. Use smaller embedding model if speed is critical
