skills.rest
wshobson
wshobsonCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

rag-implementation

Builds RAG systems for LLM apps with vector databases and retrieval strategies.

38.6k|4.1k|Updated Jul 24, 2025
Search Tags:#semantic search#llm#rag#vector database#document q&a#knowledge grounding
One-click install
npx skills add https://github.com/wshobson/agents --skill rag-implementation-wshobson
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-implementation
Source: https://github.com/wshobson/agents/tree/main/plugins/llm-application-dev/skills/rag-implementation
Command: npx skills add https://github.com/wshobson/agents --skill rag-implementation-wshobson

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables the creation of LLM applications that can access and utilize external knowledge bases, ensuring responses are accurate, factual, and grounded in provided data, thereby reducing hallucinations.

Core Features & Use Cases

  • Vector Databases: Integrates with various vector stores (Pinecone, Weaviate, Chroma, etc.) for efficient storage and retrieval of embeddings.
  • Embedding Models: Supports multiple embedding models for converting text to vectors.
  • Retrieval Strategies: Implements diverse retrieval methods like dense, sparse, hybrid search, multi-query, and HyDE.
  • Reranking: Enhances retrieval quality using methods like cross-encoders and MMR.
  • Use Case: Building a Q&A system over a company's internal documentation, where users can ask natural language questions and receive answers directly supported by the documentation.

Quick Start

Use the rag-implementation skill to build a Q&A system over your documents.

Frequently Asked Questions about rag-implementation

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

FAQPage Schema
How do I build a knowledge-grounded LLM app that answers questions from my company documentation?▼

To build a knowledge-grounded LLM app, you develop a Retrieval-Augmented Generation (RAG) system that integrates vector databases, embedding models, and retrieval strategies to enable document Q&A and reduce hallucinations.

What is the best way to reduce LLM hallucinations with external data sources?▼

Retrieval-Augmented Generation (RAG) reduces LLM hallucinations by grounding responses in external knowledge bases, ensuring answers are accurate, factual, and directly supported by your provided documents.

How do I implement semantic search over internal documents using vector databases?▼

Implement semantic search by converting text to vectors using embedding models, then storing and retrieving them via vector databases like Pinecone, Weaviate, or Chroma for efficient knowledge retrieval.

Does RAG support hybrid search and reranking methods for document retrieval?▼

RAG supports diverse retrieval methods including dense, sparse, and hybrid search, and enhances retrieval quality using reranking techniques like cross-encoders and Maximal Marginal Relevance (MMR).

Can I use multi-query and HyDE strategies to improve my LLM retrieval accuracy?▼

Yes, you can improve LLM retrieval accuracy by implementing advanced strategies like multi-query and HyDE alongside embedding models to fetch highly relevant context from your vector store.

Related Skills

Explore More Software Engineering Skills→
patornpatorn

langchain-rag

Build end-to-end RAG pipelines with LangChain document loaders, embeddings, and vector stores.

Community
Advanced
zsutxzzsutxz
5

rag-implementation

Build RAG systems integrating vector stores and retrieval strategies.

Community
Advanced
RightNow-AIRightNow-AI
18.1k

prompt-engineer

Design prompts for chain-of-thought, few-shot learning, and structured output.

Official
Intermediate
AmidVoshakulAmidVoshakul

rag-engineer

Design and optimize RAG pipelines with vector databases and hybrid search.

Community
Advanced