skills.rest
haxlys
haxlysCOMMUNITY
Explore all skills by this author →
GitHub

hybrid-search-implementation

Combine vector similarity with keyword matching using RRF or linear fusion.

1|Updated Apr 27, 2026
Search Tags:#rag#reranking#vector-search#information-retrieval#hybrid-search#keyword-search#fusion
One-click install
npx skills add https://github.com/haxlys/skills --skill hybrid-search-implementation-haxlys
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hybrid-search-implementation
Source: https://github.com/haxlys/skills/tree/main/vendored/wshobson-agents/plugins/llm-application-dev/skills/hybrid-search-implementation
Command: npx skills add https://github.com/haxlys/skills --skill hybrid-search-implementation-haxlys

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Combine vector similarity with keyword matching to retrieve highly relevant documents in a unified way, enabling more accurate results than either method alone.

Core Features & Use Cases

  • Architecture: parallel vector and keyword search pipelines with a fusion layer.
  • Fusion Methods: supports RRF, linear combination, and optional reranking for improved relevance.
  • Templates & Pipelines: ready-made patterns for PostgreSQL, Elasticsearch, and custom pipelines to deploy in RAG workflows.

Quick Start

Instantiate the hybrid search module with your vector and keyword stores and run a query to obtain fused results.

Frequently Asked Questions about hybrid-search-implementation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I combine vector search and keyword search for RAG retrieval?▼

You can combine vector and keyword search by running parallel pipelines and applying fusion methods like RRF or linear combination, which unifies semantic meaning and exact terms for improved RAG retrieval.

What is the best way to fuse vector and keyword search results?▼

The best way to fuse vector and keyword search results is using Reciprocal Rank Fusion (RRF) or linear combination, with optional reranking applied afterward to further improve relevance.

Does hybrid search work with PostgreSQL and Elasticsearch?▼

Yes, hybrid search works with PostgreSQL and Elasticsearch, providing ready-made templates and pipelines to deploy fused vector and keyword queries within existing RAG workflows.

When do I need hybrid search instead of pure vector search?▼

You need hybrid search instead of pure vector search when your queries require exact term matching alongside semantic meaning, which is common in domains like code, documentation, and research retrieval.

Can I plug custom vector and text indexes into a hybrid search pipeline?▼

Yes, you can plug custom vector and text indexes into the hybrid search pipeline, as it supports pluggable indexes that execute parallel queries before the fusion layer.

Related Skills

Explore More Data & Analytics Skills→
patrykkopycinskipatrykkopycinski
6

rag-pipeline

Set up a RAG pipeline with Elasticsearch for vector retrieval.

Community
Intermediate
JeffallanJeffallan
10.9k

rag-architect

Design and implement retrieval-augmented generation pipelines with vector stores and hybrid search.

Community
Advanced
ccfccf

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications.

Community
Intermediate
Division6066Division6066

hybrid-search-implementation

Combine vector similarity with keyword matching for hybrid search retrieval.

Community
Advanced