skills.rest
thejordanleopold
thejordanleopoldCOMMUNITY
Explore all skills by this author →
Website𝕏@jordansleopoldGitHub

rag-and-vector-search

Implement retrieval-augmented generation pipelines with vector search.

4|Updated Apr 9, 2026
Search Tags:#embeddings#rag#evaluation#retrieval#semantic-search#vector-search#document-qa
One-click install
npx skills add https://github.com/thejordanleopold/claude-code-skills-distilled --skill rag-and-vector-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-and-vector-search
Source: https://github.com/thejordanleopold/claude-code-skills-distilled/tree/main/rag-and-vector-search
Command: npx skills add https://github.com/thejordanleopold/claude-code-skills-distilled --skill rag-and-vector-search

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Retrieval-augmented generation pipelines rely on high-quality retrieval to ground the generated content. This skill provides a structured approach to building, evaluating, and debugging RAG systems with vector search.

Core Features & Use Cases

  • Design and implement end-to-end RAG pipelines including ingestion, embedding, vector storage, retrieval, and generation.
  • Evaluate retrieval quality, faithfulness, and grounding; optimize chunking, reranking, and context windows.
  • Compare vector databases and embedding models; debug failures like hallucination and retrieval misses.

Quick Start

Construct a minimal RAG pipeline over a sample document collection and verify that retrieved context improves answer correctness.

Frequently Asked Questions about rag-and-vector-search

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

FAQPage Schema
How do I build a retrieval-augmented generation pipeline for document QA?▼

To build a retrieval-augmented generation pipeline for document QA, you must implement end-to-end stages covering document ingestion, embedding, vector storage, retrieval, and generation to ground the output content.

What's the best way to evaluate retrieval quality and faithfulness in RAG systems?▼

Evaluating retrieval quality and faithfulness in RAG systems requires applying specific evaluation metrics to measure answer correctness, ensuring retrieved context improves relevance and prevents hallucination failures.

How does chunking strategy and embedding model selection affect semantic search?▼

Chunking strategy and embedding model selection directly affect semantic search by controlling bounded context and retrieval accuracy. Optimizing these factors ensures vector search queries retrieve highly relevant document segments.

Can I compare vector databases and embedding models for my RAG pipeline?▼

Yes, you can compare vector databases and embedding models for your RAG pipeline. Comparing these technical components helps debug retrieval misses and optimize the overall grounding mechanism.

Why does my RAG pipeline return irrelevant context or hallucinate answers?▼

Your RAG pipeline returns irrelevant context or hallucinates answers due to suboptimal chunking, poor reranking, or bad embedding model choices. Debugging retrieval misses requires evaluating context window boundaries and retrieval tactics.

Do I need a specific vector database to implement vector search for RAG?▼

You do not need one specific vector database to implement vector search for RAG. The pipeline supports comparing multiple vector database choices to fit your domain's technical requirements and scale.

Related Skills

Explore More Data & Analytics Skills→
giuseppe-trisciuogliogiuseppe-trisciuoglio
322

chunking-strategy

Chunk documents into semantically meaningful segments for RAG systems.

Community
Advanced
floflo777floflo777
33

rag-eval

Evaluate RAG systems using retrieval, generation, and latency metrics.

Community
Intermediate
Dianshu-LiaoDianshu-Liao
2

rag-implementation

Build retrieval-augmented generation systems with citation-ready outputs from external documents.

Community
Intermediate
winsorllcwinsorllc

Embedding Search

Provides semantic search across documents with Tunrsity and Tunrsity-like features.

Community
Intermediate