Community생산성 & 협업github.com

wshobson/embedding-strategies

의미 검색 및 RAG 애플리케이션에 적합한 임베딩 모델을 선택하고 최적화합니다. 임베딩 모델 선택, 청킹 전략 구현, 특정 도메인에 맞는 임베딩 품질 최적화 시 사용하세요.

embedding-strategies란 무엇인가요?

이 스킬은 의미 검색(semantic search)과 RAG(Retrieval-Augmented Generation) 애플리케이션을 위한 임베딩 모델 선택 및 최적화를 지원합니다. 주어진 텍스트를 고차원 벡터로 변환하는 임베딩 모델의 선택은 검색 품질에 큰 영향을 미치며, 적절한 청킹 전략(chunking strategy)과 결합되어야 최적의 성능을 발휘합니다. 이 스킬은 다양한 오픈소스 및 상용 임베딩 모델(예: OpenAI, Cohere, sentence-transformers)을 평가하고, 특정 도메인(법률, 의료, 기술 문서 등)에 맞게 파인튜닝하거나 대안을 제시하는 방법을 설명합니다. 또한 효율적인 벡터 저장과 검색을 위해 차원 축소, 양자화, 인덱싱 기법을 제안하며, 유사도 측정(코사인 유사도, 내적)과 평가 메트릭(MRR, Recall@k)을 통해 성능을 정량적으로 분석할 수 있도록 돕습니다. LangChain, LlamaIndex 등 주요 RAG 프레임워크와의 통합 예제를 포함하여 실무에 바로 적용할 수 있습니다.

지원 대상~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/wshobson/agents/tree/main/skills/embedding-strategies

Installed? Explore more 생산성 & 협업 skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →

즐겨 사용하는 AI에게 물어보기

이 에이전트 스킬이 미리 로드된 새 채팅을 엽니다.

문서

embedding-strategies은(는) 무엇을 하나요?

의미 검색 및 RAG 애플리케이션에 적합한 임베딩 모델을 선택하고 최적화합니다. 임베딩 모델 선택, 청킹 전략 구현, 특정 도메인에 맞는 임베딩 품질 최적화 시 사용하세요.

개요

이 스킬은 의미 검색(semantic search)과 RAG(Retrieval-Augmented Generation) 시스템에서 임베딩(embedding)의 역할과 최적화 방법을 다룹니다. 적절한 임베딩 전략은 검색 정확도와 응답 품질을 크게 향상시킵니다.

주요 기능

  • 임베딩 모델 선택: OpenAI, Cohere, sentence-transformers, Instructor 등 다양한 모델 평가 및 선택
  • 청킹 전략: 문서 분할 크기, 중첩(overlap), 섹션 기반 청킹 등 최적화
  • 도메인 최적화: 특정 분야(법률, 의료, 기술 등)에 맞는 임베딩 조정 및 파인튜닝
  • 성능 평가: MRR, Recall@k, 코사인 유사도 등 메트릭을 통한 정량적 평가
  • 차원 축소 및 양자화: PCA, t-SNE, 이진 양자화를 통한 저장 및 검색 효율화
  • 프레임워크 통합: LangChain, LlamaIndex, Chroma, Pinecone 등과의 통합 예제

사용 방법

이 스킬을 호출하면 다음 정보를 제공하세요:

  1. 사용 목적: 의미 검색, RAG, 추천 시스템 등
  2. 데이터 특성: 문서 유형, 언어, 도메인, 크기(문서 수 및 평균 길이)
  3. 성능 요구사항: 정확도 우선, 속도 우선, 리소스 제약 등
  4. 기존 환경: 사용 중인 프레임워크, 벡터 데이터베이스, 예산

예제 명령어

# 임베딩 모델 비교 스크립트
python -m embedding_strategies.compare --models text-embedding-3-small,all-MiniLM-L6-v2 --data ./sample_docs
from embedding_strategies import ChunkOptimizer, EmbeddingSelector

# 최적 청크 크기 찾기
optimizer = ChunkOptimizer(chunk_sizes=[256, 512, 1024], overlap=50)
results = optimizer.evaluate_on(data)

print("최적 청크 크기:", results.best_chunk_size)
print("MRR 점수:", results.mrr)

지원 플랫폼

  • 임베딩 API: OpenAI, Cohere, Hugging Face
  • 로컬 모델: sentence-transformers, Instructor, BGE
  • 벡터 DB: Pinecone, Weaviate, Chroma, Qdrant, Milvus
  • 프레임워크: LangChain, LlamaIndex, Haystack

주의 사항

  • 임베딩 모델 선택 시 토큰 한도 및 비용 고려
  • 청킹 전략은 문서 구조에 따라 조정 필요 (예: 법률 문서는 섹션 단위 청킹)
  • 테스트 환경과 프로덕션 환경의 차이 (데이터 분포, 지연 시간) 반영
  • 개인정보 보호가 중요한 경우 로컬 모델 사용 권장

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

wshobson/accessibility-compliance

Implement WCAG 2.2 compliant interfaces with mobile accessibility, inclusive design patterns, and assistive technology support. Use when auditing accessibility, implementing ARIA patterns, building for screen readers, or ensuring inclusive user experiences.

wshobson/airflow-dag-patterns

Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.

wshobson/angular-migration

Migrate from AngularJS to Angular using hybrid mode, incremental component rewriting, and dependency injection updates. Use when upgrading AngularJS applications, planning framework migrations, or modernizing legacy Angular code.

wshobson/anti-reversing-techniques

Understand anti-reversing, obfuscation, and protection techniques encountered during software analysis. Use this skill when analyzing malware evasion techniques, when implementing anti-debugging protections for CTF challenges, when reverse engineering packed binaries, or when building security research tools that need to detect virtualized environments.

wshobson/api-design-principles

Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.

wshobson/architecture-decision-records

Write and maintain Architecture Decision Records (ADRs) following best practices for technical decision documentation. Use when documenting significant technical decisions, reviewing past architectural choices, or establishing decision processes.

wshobson/architecture-patterns

Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use this skill when designing clean architecture for a new microservice, when refactoring a monolith to use bounded contexts, when implementing hexagonal or onion architecture patterns, or when debugging dependency cycles between application layers.

wshobson/async-python-patterns

Master Python asyncio, concurrent programming, and async/await patterns for high-performance applications. Use when building async APIs, concurrent systems, or I/O-bound applications requiring non-blocking operations.

wshobson/attack-tree-construction

Build comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.

wshobson/auth-implementation-patterns

Master authentication and authorization patterns including JWT, OAuth2, session management, and RBAC to build secure, scalable access control systems. Use when implementing auth systems, securing APIs, or debugging security issues.

wshobson/avoid-ai-writing

Audit and rewrite prose so it stops reading as machine-generated. Use this skill when asked to remove AI-isms, clean up AI writing, edit a draft for AI tells, audit a README, changelog, release note, PR description, or blog post for machine-sounding prose, or make text sound less like AI. Supports a detect-only mode, a rewrite mode, and an edit-in-place mode, with optional voice and context profiles.

wshobson/backtesting-frameworks

Build robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and transaction costs. Use when developing trading algorithms, validating strategies, or building backtesting infrastructure.

wshobson/bash-defensive-patterns

Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.

wshobson/bats-testing-patterns

Master Bash Automated Testing System (Bats) for comprehensive shell script testing. Use when writing tests for shell scripts, CI/CD pipelines, or requiring test-driven development of shell utilities.

wshobson/bazel-build-optimization

Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.

wshobson/before-you-build

Pre-build product and feature risk review for founders, product managers, and AI-assisted builders. Use this skill when the user is about to build a landing page, MVP, SaaS product, internal tool, agent workflow, or major feature and needs to check demand, positioning, monetization, retention, trust, distribution, and adoption risk before implementation starts.

wshobson/billing-automation

Build automated billing systems for recurring payments, invoicing, subscription lifecycle, and dunning management. Use when implementing subscription billing, automating invoicing, or managing recurring payment systems.

wshobson/binary-analysis-patterns

Master binary analysis patterns including disassembly, decompilation, control flow analysis, and code pattern recognition. Use when analyzing executables, understanding compiled code, or performing static analysis on binaries.

wshobson/block-no-verify-hook

Configure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code projects that enforce commit quality gates.

wshobson/brand-landingpage

Brand-first landing page designer — runs a brand-identity interview (colors, typography, shape language), then generates and iterates on a polished landing page via Stitch with deployment-ready HTML. Use when the user asks to create, design, or build a landing page, homepage, or marketing page and has no established visual direction. Skip when they have a design mockup, need a dashboard or app UI, are working at component level, building a multi-page app, or restyling with known design tokens — use frontend-design instead.

관련 스킬