skills.rest
leonardoteodoroo
leonardoteodorooCOMMUNITY
Explore all skills by this author →
GitHub

hybrid-search-implementation

Implement hybrid search combining vector similarity with keyword matching for RAG systems.

Updated Feb 3, 2026
Search Tags:#rag#search#retrieval#vector#hybrid#keyword#fusion
One-click install
npx skills add https://github.com/leonardoteodoroo/amino-advanced --skill hybrid-search-implementation-leonardoteodoroo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hybrid-search-implementation
Source: https://github.com/leonardoteodoroo/amino-advanced/tree/main/.agent/skills/hybrid-search-implementation
Command: npx skills add https://github.com/leonardoteodoroo/amino-advanced --skill hybrid-search-implementation-leonardoteodoroo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Hybrid search blends vector similarity with keyword matching to improve retrieval quality in RAG systems and search platforms.

Core Features & Use Cases

  • Hybrid architecture that combines semantic and exact-term matching
  • Multiple fusion strategies (RRF, Linear, Cross-encoder, Cascade) and adaptable weighting
  • Example implementations for PostgreSQL, Elasticsearch, and custom pipelines to build end-to-end search solutions
  • Real-world use cases in RAG workflows, domain-specific vocabularies, and large document collections

Quick Start

Provide a query and receive a fused ranking that combines vector similarity with keyword matching for enhanced retrieval.

Frequently Asked Questions about hybrid-search-implementation

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

FAQPage Schema
How does hybrid search improve RAG retrieval quality?▼

Hybrid search improves RAG retrieval by blending vector similarity with keyword matching, ensuring both semantic meaning and exact terms are captured. This combination increases recall and delivers more relevant documents across large document collections and domain-specific vocabularies.

What fusion strategies can I use for combining vector and keyword search?▼

You can use multiple fusion strategies including Reciprocal Rank Fusion (RRF), Linear, Cross-encoder, and Cascade. These approaches allow adaptable weighting and reranking to optimize the final fused ranking of your search results.

Can I implement hybrid search using PostgreSQL or Elasticsearch?▼

Yes, hybrid search supports pluggable backends including PostgreSQL and Elasticsearch. It provides example implementations for both platforms, allowing you to build end-to-end search solutions within your existing database or search engine infrastructure.

How do I configure weighting between semantic and exact-term matching?▼

Hybrid search provides configurable weighting and reranking options to adjust the balance between semantic vector similarity and exact keyword matching. This allows you to tune retrieval behavior based on your specific domain vocabulary and dataset requirements.

When should I use hybrid search instead of pure vector similarity?▼

Use hybrid search when both semantic meaning and exact terms matter, such as querying domain-specific vocabularies or large document repositories. Pure vector similarity may miss exact matches, while hybrid search ensures precise terms are still prioritized in the fused ranking.

Related Skills

Explore More Software Engineering Skills→
ArogyaReddyArogyaReddy

hybrid-search-implementation

Combine vector similarity and keyword matching with RRF, Linear, Cross-encoder, or Cascade fusion.

Community
Advanced
BagelHoleBagelHole
46

rag-infrastructure

Build and operate RAG infrastructure with vector stores and hybrid search.

Community
Advanced
drgaciwdrgaciw

rag-implementation

Implement RAG systems integrating vector databases and semantic search for LLM applications.

Community
Advanced
emilneuraz-aiemilneuraz-ai

hybrid-search-implementation

Combines vector similarity and keyword matching for hybrid search.

Community
Advanced