Hybrid Search Implementation

hybrid-search-implementation

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

wshobson/agents·10.3Kinstalls40.2Kstars

SKILL.md

Full skill instructions

Hybrid Search Implementation

Patterns for combining vector similarity and keyword-based search.

When to Use This Skill

Building RAG systems with improved recall
Combining semantic understanding with exact matching
Handling queries with specific terms (names, codes)
Improving search for domain-specific vocabulary
When pure vector search misses keyword matches

Core Concepts

1. Hybrid Search Architecture

Query → ┬─► Vector Search ──► Candidates ─┐
        │                                  │
        └─► Keyword Search ─► Candidates ─┴─► Fusion ─► Results

2. Fusion Methods

Method	Description	Best For
RRF	Reciprocal Rank Fusion	General purpose
Linear	Weighted sum of scores	Tunable balance
Cross-encoder	Rerank with neural model	Highest quality
Cascade	Filter then rerank	Efficiency

Templates and detailed worked examples

Full template library and detailed worked examples live in references/details.md. Read that file when you need the concrete templates.

Best Practices

Do's

Tune weights empirically - Test on your data
Use RRF for simplicity - Works well without tuning
Add reranking - Significant quality improvement
Log both scores - Helps with debugging
A/B test - Measure real user impact

Don'ts

Don't assume one size fits all - Different queries need different weights
Don't skip keyword search - Handles exact matches better
Don't over-fetch - Balance recall vs latency
Don't ignore edge cases - Empty results, single word queries

Install skill

Copy and run in your terminal

npx -y skills add https://github.com/wshobson/agents --skill hybrid-search-implementation

View on GitHub

hybrid-search-implementation

typescript-advanced-types
Advanced TypeScript type system patterns for building type-safe, reusable components and utilities.
83.8K installs
tailwind-design-system
CSS-first design system framework for Tailwind v4 with tokens, components, and responsive patterns.
67.4K installs
nodejs-backend-patterns
Production-ready Node.js backend patterns with Express/Fastify, middleware, authentication, and database integration.
47.1K installs
brand-landingpage
Brand-first landing page designer that interviews your brand identity, then generates and iterates on deployment-ready HTML.
39K installs

More skills from wshobson

wshobson/agents

python-testing-patterns

Comprehensive testing strategies for Python using pytest, fixtures, mocking, and test-driven development.

40.2K 34.6K

View

wshobson/agents

python-performance-optimization

Profile and optimize Python code using cProfile, memory profilers, and performance best practices.

40.2K 34.4K

View

wshobson/agents

nextjs-app-router-patterns

Comprehensive patterns for Next.js 14+ App Router, Server Components, and modern full-stack React development.

40.2K 31.5K

View

wshobson/agents

code-review-excellence

Systematic code review practices for constructive feedback, bug detection, and team knowledge sharing.

40.2K 29.4K

View

wshobson/agents

api-design-principles

REST and GraphQL API design principles for building scalable, developer-friendly APIs.

40.2K 29.4K

View

wshobson/agents

postgresql-table-design

Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features

40.2K 26.9K

View

wshobson/agents

postgresql-table-design

Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features

40.2K 26.9K

View

wshobson/agents