How does this skill help reduce AI hallucinations?

It provides specific prompt engineering templates and retrieval strategies that force the model to answer based only on provided context and include source citations.

Which vector databases does this skill support?

This skill includes implementation patterns for popular vector databases including Pinecone, Weaviate, Milvus, Chroma, Qdrant, and FAISS.

What is a RAG system?

RAG (Retrieval-Augmented Generation) is an architectural pattern that retrieves relevant documents from an external knowledge base to provide context to an LLM, ensuring responses are grounded in factual data.

Does it support hybrid search methods?

Yes, it covers patterns for combining dense retrieval (semantic similarity) with sparse retrieval (BM25 keyword matching) for more accurate results.

RAG Implementation Expert

Name: RAG Implementation Expert
Author: ovachiever

byovachiever

•

Data Science & ML

Implements robust Retrieval-Augmented Generation systems using vector databases and semantic search to ground AI responses in external knowledge.

This skill provides comprehensive guidance for building production-ready RAG architectures, enabling LLMs to access proprietary data and real-time information. It covers the entire pipeline from document chunking and embedding generation to advanced retrieval strategies like hybrid search, reranking, and contextual compression. Whether you're building a documentation assistant, a research tool, or a domain-specific Q&A system, this skill ensures your AI applications provide accurate, cited, and hallucination-free responses by leveraging industry-standard tools and implementation patterns.

Key Features

01Implementation patterns for vector databases including Pinecone, Chroma, and Weaviate

02Reranking and contextual compression to improve retrieval precision

035 GitHub stars

04Advanced document chunking and metadata management strategies

05Semantic, keyword, and hybrid search optimization techniques

06Standardized evaluation frameworks for grounding and accuracy

Use Cases

01Building AI-powered Q&A systems for proprietary documentation or internal knowledge bases

02Creating research tools with automated source citation and multi-query retrieval

03Reducing model hallucinations by grounding responses in factual source material

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add ovachiever/droid-tings rag-implementation

For use in Claude.ai and ChatGPT

Download Skill