What question did this study set out to answer?

The study aims to compare the performance of different retrieval strategies in a RAG system built on PostgreSQL.

April 5, 2026Open Access

Hybrid Retrieval-Augmented Generation on Serverless PostgreSQL: A Comparative Evaluation of HyDE, Graph-Based, and Fusion Retrieval Strategies

Key Points

The study aims to compare the performance of different retrieval strategies in a RAG system built on PostgreSQL.
Implementation of hybrid search using Reciprocal Rank Fusion (RRF), HyDE, and graph-based retrieval.
Evaluation conducted on a 427-document Spanish-language corpus with 22 ground-truth pairs.
Performance metrics included Precision at 5 (P@5) and Mean Reciprocal Rank (MRR).
HyDE achieved the highest performance with P@5 of 0.595 and MRR of 0.838.
Graph-based retrieval was particularly effective on relational queries.
The system demonstrated effective operation on serverless infrastructure.

Abstract

We present a lightweight RAG architecture built entirely on PostgreSQL with pgvector and serverless edge functions. Our system implements and evaluates four retrieval strategies: hybrid search with Reciprocal Rank Fusion (RRF), Hypothetical Document Embeddings (HyDE), multi-query expansion, and graph-based retrieval over an automatically constructed knowledge graph. Evaluation on a 427-document Spanish-language corpus with 22 ground-truth pairs shows HyDE achieves the best performance (P@5: 0.595, MRR: 0.838, Hit Rate: 1.0), while graph-based retrieval excels on relational queries. We demonstrate that production-grade RAG systems can operate effectively on commodity serverless infrastructure.

Hybrid Retrieval-Augmented Generation on Serverless PostgreSQL: A Comparative Evaluation of HyDE, Graph-Based, and Fusion Retrieval Strategies

Key Points

Abstract

Cite This Study

Also Consider

Also Consider