Which vector databases does this skill support?

The skill includes configurations and best practices for Pinecone, Weaviate, Milvus, Chroma, Qdrant, and pgvector (PostgreSQL).

What is the primary benefit of using this RAG skill?

It provides standardized, production-ready patterns to connect LLMs to external data, which drastically reduces hallucinations and allows the model to answer questions about specific, private, or recent information.

Can I use this for local AI development?

Absolutely. It features specific setups for local-first tools like Chroma and pgvector, making it suitable for both development and production environments.

How does it handle large documents?

It provides multiple chunking strategies, including recursive character splitting and semantic chunking, to ensure context windows are used efficiently without losing meaning.

Does it support hybrid search?

Yes, it includes implementation patterns for combining dense semantic search with sparse keyword matching (BM25) using Reciprocal Rank Fusion (RRF).

RAG System Implementation

Name: RAG System Implementation
Author: Microck

byMicrock

•

Data Science & ML

Builds high-performance Retrieval-Augmented Generation (RAG) systems to ground LLM applications in external knowledge bases and private documentation.

This skill provides a comprehensive framework for architecting and deploying Retrieval-Augmented Generation (RAG) systems within Claude-powered applications. It guides developers through the entire pipeline, including optimized document chunking, embedding selection, vector database integration, and sophisticated retrieval strategies like hybrid search and reranking. By implementing these patterns, developers can significantly reduce model hallucinations, ensure factual accuracy, and enable AI agents to interact with proprietary or real-time datasets with high precision and source attribution.

Key Features

01Advanced retrieval patterns such as HyDE, Multi-Query, and Parent Document Retrieval

02Integration of state-of-the-art embedding models like voyage-3-large and text-embedding-3

03Implementation of major vector databases including Pinecone, Weaviate, Chroma, and pgvector

04Reranking and contextual compression techniques to optimize token usage and response relevance

052 GitHub stars

06Comprehensive document chunking strategies including recursive, semantic, and markdown-aware splitting

Use Cases

01Developing research tools that synthesize information from large libraries of technical papers with citations

02Building a Q&A assistant for proprietary company documentation and internal wikis

03Creating fact-grounded customer support bots with real-time access to product catalogs

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add microck/opendots-microck rag-implementation

For use in Claude.ai and ChatGPT

Download Skill