메뉴
Use when building retrieval-augmented generation. Covers chunking strategy, embedding choice, vector stores, hybrid + reranking retrieval, prompt assembly, and evaluating retrieval and answer quality.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | rag-pipeline |
| description | Use when building retrieval-augmented generation. Covers chunking strategy, embedding choice, vector stores, hybrid + reranking retrieval, prompt assembly, and evaluating retrieval and answer quality. |
RAG grounds an LLM in your data by retrieving relevant context at query time. Most RAG quality problems are retrieval problems, not generation problems — if the right chunk isn't retrieved, no prompt can save the answer. Optimize retrieval first.
# 1. Dense (semantic) + 2. Sparse (BM25 keyword) -> union
dense_hits = vstore.search(embed(query), k=20)
sparse_hits = bm25.search(query, k=20)
candidates = dedupe(dense_hits + sparse_hits)
# 3. Cross-encoder rerank for precision
from sentence_transformers import CrossEncoder
reranker = CrossEncoder("cross-encoder/ms-marco-MiniLM-L-6-v2")
ranked = sorted(candidates,
key=lambda c: reranker.predict([(query, c.text)]),
reverse=True)[:5]
A retriever + generator with a measured retrieval/answer score that model-serving exposes behind an API.
Use when preparing raw data for modeling — handling missing values, duplicates, inconsistent types, outliers, and bad categorical values. Emphasizes fitting all imputation on train-only to avoid leakage.
Use when running ML experiments that need to be compared, reproduced, or shared. Covers MLflow/Weights & Biases logging, what to track, run organization, and model registry basics.
Use when starting on a new dataset, before modeling, or when asked to "explore", "profile", "understand", or "summarize" data. Covers structured EDA, distributions, correlations, target leakage checks, and visualization.
Use when creating, encoding, scaling, or selecting features for ML models. Covers categorical encoding, numeric transforms, datetime/text/aggregation features, and leakage-safe target encoding.
Use when optimizing model hyperparameters. Covers search strategy (random vs Bayesian/Optuna), leakage-safe tuning inside CV, search-space design, early stopping, and budget management.
Use when the target is rare (fraud, churn, disease, anomalies). Covers correct metrics, resampling (SMOTE/undersampling), class weights, threshold tuning, and avoiding the accuracy trap and resampling leakage.