Does it support advanced retrieval techniques?

Yes, it covers sophisticated patterns like Hybrid Search (BM25 + Semantic), Multi-Query retrieval, Contextual Compression, and Hypothetical Document Embeddings (HyDE).

Which vector databases are supported in this skill?

The skill provides implementation guidance for several leading options including Pinecone, Weaviate, Chroma, Milvus, Qdrant, and pgvector.

How does this skill help reduce AI hallucinations?

By implementing grounding patterns, the LLM is forced to answer based on retrieved document context, ensuring responses are factually supported by your specific data sources.

What is RAG and why should I use it?

RAG (Retrieval-Augmented Generation) allows LLMs to access external, real-time, or private data to provide accurate and grounded answers without the need for model fine-tuning.

Can I use this for local development?

Absolutely. It includes configurations for local-friendly tools like Chroma DB and local embedding models like BGE-large for testing and development.

RAG Implementation Master

Name: RAG Implementation Master
Author: rajasekarm

byrajasekarm

0•

Data Science & ML

Builds high-performance Retrieval-Augmented Generation (RAG) systems for AI applications using vector databases and semantic search.

The RAG Implementation skill provides comprehensive patterns and best practices for building robust Retrieval-Augmented Generation systems. It streamlines the process of grounding LLM responses in external knowledge bases, covering the entire pipeline from document ingestion and semantic chunking to advanced retrieval strategies like hybrid search and reranking. Whether you are building a documentation assistant, a research tool, or a proprietary Q&A system, this skill offers the architectures needed to minimize hallucinations and maximize the accuracy of your AI applications using tools like LangGraph, Pinecone, and Voyage AI.

Key Features

01Comprehensive document chunking strategies (Semantic, Recursive, and Markdown)

02Optimized reranking and contextual compression to improve result relevance

03Ready-to-use integrations for Pinecone, Weaviate, Chroma, and pgvector

04Advanced retrieval patterns including Hybrid Search, Multi-Query, and HyDE

05LangGraph-based RAG workflow templates for production-grade AI agents

060 GitHub stars

Use Cases

01Creating research assistants that provide source-cited factual answers

02Developing internal Q&A systems for proprietary company documentation

03Implementing semantic search capabilities for complex content repositories

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add rajasekarm/skills rag-implementation

For use in Claude.ai and ChatGPT

Download Skill