RAG Implementer

Name: RAG Implementer
Availability: InStock
Author: daffy0208

Implement Retrieval-Augmented Generation pipelines with vector stores and hybrid search.

34|7|Updated Oct 22, 2025

Search Tags:#embeddings #vector database #knowledge base #LLM #RAG #retrieval #AI-native

Ready to run

npx skills add https://github.com/daffy0208/ai-dev-standards --skill rag-implementer

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: RAG Implementer
Source: https://github.com/daffy0208/ai-dev-standards/tree/main/SKILLS/rag-implementer
Command: npx skills add https://github.com/daffy0208/ai-dev-standards --skill rag-implementer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solves? This Skill addresses the challenge of making Large Language Models (LLMs) reliable and factual by grounding their responses in up-to-date, domain-specific, or proprietary data, thereby reducing hallucinations and providing source attribution.

Core Features & Use Cases

Knowledge Base Design: Guides through data source mapping, intelligent chunking strategies, and metadata enrichment for effective retrieval.
Retrieval Pipeline: Implements advanced techniques like hybrid search, re-ranking, and query enhancement to fetch the most relevant information.
Evaluation & Monitoring: Establishes metrics for retrieval and generation quality, ensuring production-ready performance and continuous improvement.

Quick Start

Fastest path to RAG:

Define knowledge scope
- Identify data sources
- Choose chunking strategy (500-1000 tokens)
- Add metadata for filtering
Choose embedding model
- General: text-embedding-3-large (OpenAI)
- Code: code-search-babbage-code-001
- Test on sample queries
Set up vector store
- Managed: Pinecone
- Self-hosted: Weaviate or Qdrant
- Lightweight: Chroma or pgvector

Frequently Asked Questions about RAG Implementer

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

FAQPage Schema

How do I reduce hallucinations in LLM responses using external data?▼

Grounding LLMs in external data through RAG (Retrieval-Augmented Generation) reduces hallucinations by fetching relevant information before generation. The Skill implements production-ready RAG pipelines covering data preparation, embedding selection, vector stores, retrieval strategies, and evaluation to ensure factual, sourced outputs.

What's the best way to set up a vector database for knowledge retrieval?▼

Choose a vector store based on your infrastructure: managed services like Pinecone for simplicity, self-hosted options like Weaviate or Qdrant for control, or lightweight solutions like Chroma or pgvector for local development. The Skill guides configuration, embedding model selection, and hybrid retrieval setup for optimal performance.

How do I chunk and prepare documents for embedding in a knowledge base?▼

Effective knowledge base design requires mapping data sources, applying intelligent chunking strategies (typically 500–1000 tokens), and enriching chunks with metadata for filtering. The Skill covers data preparation workflows and metadata strategies to maximize retrieval relevance and coverage.

Can I combine multiple retrieval techniques like hybrid search and re-ranking?▼

Yes. Advanced retrieval pipelines combine hybrid search, re-ranking, and query enhancement to fetch the most relevant information. The Skill implements these techniques alongside context assembly and source attribution to improve retrieval quality.

How do I evaluate and monitor RAG pipeline quality in production?▼

Establish metrics for both retrieval quality and generation quality to measure performance and catch degradation early. The Skill covers evaluation frameworks and monitoring approaches to ensure production-ready performance and enable continuous improvement.