Which vector databases does this skill support?

It includes implementation patterns for popular vector stores including Pinecone, Chroma, Weaviate, Milvus, Qdrant, and FAISS.

Can I use this for local document processing?

Absolutely. It covers local embedding models and lightweight vector stores like Chroma and FAISS for private, local-first RAG implementations.

Does it support hybrid search?

Yes, it provides code patterns for combining semantic (dense) retrieval with keyword-based (sparse) retrieval to improve search relevance.

How does this skill reduce AI hallucinations?

By implementing semantic retrieval and prompt engineering patterns that force the AI to answer based strictly on the provided context with source citations.

Retrieval-Augmented Generation (RAG) is an architectural pattern that provides LLMs with access to external, authoritative data to ensure responses are accurate and grounded.

RAG Implementation

Name: RAG Implementation
Author: HermeticOrmus

byHermeticOrmus

•

데이터 과학 및 ML

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

RAG Implementation provides a comprehensive framework for building LLM applications that leverage external data sources to ensure factual accuracy and domain-specific relevance. It covers the entire pipeline from document ingestion and semantic chunking to vector database integration and advanced retrieval strategies like hybrid search and reranking. This skill is essential for developers looking to minimize hallucinations, implement document Q&A systems, and create AI assistants that can reference proprietary or real-time information with verified source citations.

주요 기능

01Hybrid search and reranking for high-precision retrieval

02Vector database integration for Pinecone, Chroma, and Weaviate

03Evaluation metrics for measuring RAG accuracy and performance

044 GitHub stars

05Advanced document chunking and embedding strategies

06Implementation patterns for source citations and grounding

사용 사례

01Building a Q&A assistant over proprietary company documentation

02Developing research tools that provide verifiable source citations

03Creating factual chatbots with real-time knowledge grounding

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add hermeticormus/claude-code-game-development rag-implementation

For use in Claude.ai and ChatGPT

Download Skill