Does this support PostgreSQL?

Yes, it includes specialized templates for implementing hybrid search using the pgvector extension alongside PostgreSQL's native full-text search capabilities.

When should I use this skill?

Use this skill when building Retrieval-Augmented Generation (RAG) systems where pure vector search might miss specific product codes, names, or domain-specific vocabulary.

What is hybrid search?

Hybrid search is a retrieval technique that combines semantic vector search (which understands meaning) with traditional keyword-based search (which matches exact terms) to provide more accurate results.

What is Reciprocal Rank Fusion (RRF)?

RRF is a mathematical method used to combine multiple ranked result lists into a single ranking. It is highly effective for hybrid search because it doesn't require different search algorithms to have comparable score scales.

Hybrid Search Implementation

Name: Hybrid Search Implementation
Author: rajasekarm

byrajasekarm

0•

データサイエンスとML

Combines vector similarity and keyword-based search to improve information retrieval accuracy in RAG systems and search engines.

This skill provides standardized patterns and implementation templates for hybrid search, effectively merging semantic vector embeddings with traditional keyword matching. It addresses common retrieval failures where vector search misses exact terms or keyword search lacks conceptual understanding. By offering battle-tested configurations for Reciprocal Rank Fusion (RRF), PostgreSQL pgvector, and Elasticsearch, it enables developers to build more robust Retrieval-Augmented Generation (RAG) pipelines and search interfaces with significantly higher recall and precision.

主な機能

01Elasticsearch hybrid search configurations with dense vector support

02Reciprocal Rank Fusion (RRF) and linear score combination templates

030 GitHub stars

04Domain-specific vocabulary handling for specialized search terms

05Cross-encoder reranking patterns for high-precision results

06Native PostgreSQL integration using pgvector and full-text search

ユースケース

01Enhancing LLM performance by providing more relevant context through improved retrieval pipelines

02Building RAG systems that require both semantic understanding and exact keyword matching

03Developing enterprise search engines for technical documentation containing codes and specific terminology

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add rajasekarm/skills hybrid-search-implementation

For use in Claude.ai and ChatGPT

Download Skill