skills.rest
spideynolove
spideynoloveCOMMUNITY
Explore all skills by this author →
Website𝕏@spideynoloveGitHub

hybrid-search-implementation

Fuse vector similarity with keyword search using RRF or linear fusion.

2|1|Updated Feb 27, 2026
Search Tags:#rag#retrieval#vector-search#information-retrieval#hybrid-search#keyword-search
One-click install
npx skills add https://github.com/spideynolove/claude-code-in-action --skill hybrid-search-implementation-spideynolove
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hybrid-search-implementation
Source: https://github.com/spideynolove/claude-code-in-action/tree/main/27-tdd-conductor-llmdev/.claude/skills/hybrid-search-implementation
Command: npx skills add https://github.com/spideynolove/claude-code-in-action --skill hybrid-search-implementation-spideynolove

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill blends vector similarity and keyword matching to improve information retrieval when neither approach alone yields sufficient recall.

Core Features & Use Cases

  • Hybrid search architecture combines vector and keyword signals to produce richer candidate sets.
  • Fusion methods include RRF and linear weighting, with optional cross-encoder reranking for high-quality results.
  • Use cases span RAG systems, domain-specific search, and any application requiring both semantic understanding and exact-term matches.

Quick Start

Provide a query and embeddings to obtain a fused set of top results from vector and keyword sources.

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 recall compared to vector search alone?▼

Hybrid search improves RAG retrieval recall by fusing vector similarity with keyword matching, producing richer candidate sets when neither vector nor keyword signals alone yield sufficient results.

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

The best way to fuse vector and keyword search results is using fusion methods like Reciprocal Rank Fusion (RRF) or linear weighting, with optional cross-encoder reranking for higher quality outcomes.

Can I configure weighting and filtering across vector and keyword search results?▼

Yes, you can configure weighting and filtering across vector and keyword results, running parallel candidate retrieval before applying fusion methods to produce the final top results.

When do I need hybrid search for domain-specific queries?▼

You need hybrid search for domain-specific queries when your application requires both semantic understanding and exact-term matches that neither vector nor keyword signals can achieve independently.

How do I start implementing hybrid search for RAG systems?▼

To start implementing hybrid search for RAG systems, provide a query and embeddings to obtain a fused set of top results retrieved in parallel from vector and keyword sources.

Related Skills

Explore More Software Engineering Skills→
ivanshamaevivanshamaev
14

rag-data-pipeline

Build RAG ingestion and query pipelines with hybrid retrieval and reranking.

Community
Advanced
artgaurav16420-ossartgaurav16420-oss

advanced-rag-optimizer

Optimizes Retrieval-Augmented Generation pipelines for source-backed answers with chunking, hybrid search, reranking, and evaluation workflows.

Community
Advanced
yunqiqiliangyunqiqiliang
8

clickzetta-ai-vector-search

Implement vector storage, indexing, and ANN retrieval in ClickZetta Lakehouse.

Community
Advanced
ccfccf

hybrid-search-implementation

Combine vector similarity with keyword matching for hybrid retrieval.

Community
Intermediate