Add PASE: PostgreSQL Ultra-High-Dimensional Approximate Nearest Neigh…

[rshri2004]

This pull request adds support for the [PASE](PostgreSQL Approximate Search Extension) algorithm to the ANN-Benchmarks framework.

What's included:

• New algorithm folder: ann_benchmarks/algorithms/pase/
• module.py: Python wrapper for PASE
• Dockerfile: Container for benchmarking PASE
• config.yml: Hyperparameters and settings for benchmark runs

About PASE: PASE is a high-performance vector search index extension that is developed for PostgreSQL. PASE uses two well-developed, stable, and efficient approximate nearest neighbor (ANN) search algorithms, IVFFlat and HNSW, to query vectors from PostgreSQL databases at a high speed. PASE does not support the extraction or output of feature vectors. You must retrieve the feature vectors of the entities that you want to query. PASE only implements a similarity search among a large number of vectors that are identified based on the retrieved feature vectors

PASE documentation: https://www.alibabacloud.com/help/en/rds/apsaradb-rds-for-postgresql/use-pase-for-efficient-vector-search

Looking forward to feedback. Let me know if there's anything else you'd like me to test or adjust. Thanks!