skills.rest
dandudzi
dandudziCOMMUNITY
Explore all skills by this author →
GitHub

rag-implementation

Design and implement RAG pipelines with chunking, embeddings, and vector stores.

2|Updated Mar 15, 2025
Search Tags:#llm#rag#vector database#evaluation#retrieval#chunking#embedding
One-click install
npx skills add https://github.com/dandudzi/dotfiles --skill rag-implementation-dandudzi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-implementation
Source: https://github.com/dandudzi/dotfiles/tree/main/dot_claude/skills/rag-implementation
Command: npx skills add https://github.com/dandudzi/dotfiles --skill rag-implementation-dandudzi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a comprehensive guide to designing, implementing, and evaluating Retrieval-Augmented Generation (RAG) pipelines for LLM applications, enabling efficient knowledge retrieval and context-aware responses.

Core Features & Use Cases

  • RAG Pipeline Design: Understand the end-to-end RAG workflow from document ingestion to LLM generation.
  • Chunking Strategies: Implement various methods (fixed-size, recursive, semantic) for optimal document segmentation.
  • Embedding & Vector Stores: Choose and integrate appropriate embedding models and vector databases (pgvector, Pinecone, Chroma, Weaviate).
  • Retrieval & Reranking: Employ semantic, hybrid, and MMR retrieval, with options for cross-encoder reranking.
  • Evaluation: Utilize RAGAS metrics and Recall@K for assessing retrieval quality.
  • Use Case: Integrate a RAG pipeline into a customer support chatbot to allow it to answer complex product questions by retrieving relevant information from a knowledge base.

Quick Start

Design a RAG pipeline for a knowledge base search by implementing recursive character chunking and using the 'all-MiniLM-L6-v2' embedding model with pgvector.

Frequently Asked Questions about rag-implementation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a RAG pipeline for a knowledge base search?▼

To build a RAG pipeline, you must implement document chunking, select an embedding model, integrate a vector database, and apply retrieval techniques to pass relevant context to an LLM for generation.

What's the best way to chunk documents for retrieval-augmented generation?▼

Optimal document chunking for retrieval-augmented generation involves choosing between fixed-size, recursive, or semantic segmentation strategies to ensure meaningful context is extracted for the embedding models.

How do I evaluate RAG pipeline retrieval quality using RAGAS metrics?▼

Evaluating RAG pipeline retrieval quality using RAGAS metrics involves measuring Recall@K and other evaluation indicators to assess how accurately your system retrieves relevant context from the vector store.

Can I use pgvector or Pinecone as the vector database for my RAG pipeline?▼

Yes, you can integrate vector databases like pgvector, Pinecone, Chroma, or Weaviate into your RAG pipeline to store embeddings and perform semantic, hybrid, or MMR retrieval operations.

Do I need cross-encoder reranking for semantic search integration?▼

Cross-encoder reranking is an optional retrieval technique for semantic search integration that refines initial vector database results to improve the accuracy of context passed to the LLM.

Related Skills

Explore More Software Engineering Skills→
chambear2809chambear2809
36

splunk-github-ta-setup

Render Splunk Add-on for GitHub inputs and validation guidance.

Community
Advanced
hamzashakoor119hamzashakoor119

RAG Chatbot Integrator

Build a RAG chatbot answering from Physical AI textbook content.

Community
Advanced
ArogyaReddyArogyaReddy

hybrid-search-implementation

Combine vector similarity and keyword matching with RRF, Linear, Cross-encoder, or Cascade fusion.

Community
Advanced
evolv3aievolv3ai
3

google-gemini-file-search

Create RAG systems with Google Gemini's managed File Search API.

Community
Advanced