Which vector databases are covered in this skill?

This skill provides configuration and implementation guidance for Pinecone, Weaviate, Chroma, Milvus, Qdrant, and FAISS.

How does this skill handle document chunking?

It includes strategies for recursive character splitting, token-based splitting, semantic chunking, and markdown-aware header splitting.

Does it support hybrid search patterns?

Yes, it provides code patterns for combining dense (semantic) and sparse (keyword-based) retrieval using ensemble techniques.

Can I use this to improve the accuracy of my LLM responses?

Absolutely. It focuses on reducing hallucinations through grounding prompts, reranking relevant context, and implementing source citations.

RAG Implementation Expert

Name: RAG Implementation Expert
Author: HermeticOrmus

byHermeticOrmus

0•

データサイエンスとML

Builds robust Retrieval-Augmented Generation (RAG) systems using vector databases and semantic search to ground AI responses in external data.

The RAG Implementation skill provides comprehensive guidance for building production-grade Retrieval-Augmented Generation pipelines within LLM applications. It covers the entire technical stack, from document loading and sophisticated chunking strategies to vector database integration with leaders like Pinecone and Chroma. Developers can leverage advanced retrieval patterns such as hybrid search, multi-query generation, and reranking to significantly improve the accuracy and groundedness of AI responses. This skill is essential for anyone building documentation assistants, enterprise search tools, or proprietary knowledge-base bots that require high factual reliability and source citation.

主な機能

01Standardized RAG evaluation metrics for accuracy and groundedness

020 GitHub stars

03Advanced document chunking including semantic and recursive splitting

04Integration guides for Pinecone, Chroma, Weaviate, and FAISS

05Sophisticated retrieval patterns like Hybrid Search and Contextual Compression

06Reranking implementation using Cross-Encoders and Cohere API

ユースケース

01Developing internal Q&A systems over proprietary company documentation

02Building research tools that provide accurate source citations and context

03Reducing AI hallucinations by grounding responses in verified external data

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add hermeticormus/alqvimia-contador rag-implementation

For use in Claude.ai and ChatGPT

Download Skill