Rag Agent Builder

If you're building document Q&A systems or need to ground LLM responses in your own data, this walks through the full RAG pipeline from chunking strategies to vector databases. The examples cover basic chunk-embed-retrieve patterns, hybrid search with BM25, and agentic RAG where the model decides what to retrieve. You get practical coverage of embedding management, reranking, and corrective RAG that validates retrieval quality before generating answers. The framework comparisons (LangChain, LlamaIndex) and vector DB options (Pinecone, Chroma, Weaviate) give you enough context to pick the right stack. Best for anyone moving past simple prompts into systems that need real-time knowledge or proprietary documents in the loop.

skills.sh installs: 261
GitHub stars: 48
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add qodex-ai/ai-agent-skills --skill rag-agent-builder --agent claude-code

Installs into .claude/skills of the current project.

Files

RAG Agent Builder

Build powerful Retrieval-Augmented Generation (RAG) applications that enhance LLM capabilities with external knowledge sources, enabling accurate, contextualized AI responses.

Quick Start

Get started with RAG implementations in the examples and utilities:

Examples: See examples/ directory for complete implementations:
- basic_rag.py - Simple chunk-embed-retrieve-generate pipeline
- retrieval_strategies.py - Hybrid search, reranking, and filtering
- agentic_rag.py - Agent-controlled retrieval with iterative refinement
Utilities: See scripts/ directory for helper modules:
- embedding_management.py - Embedding generation, normalization, and caching
- vector_db_manager.py - Vector database abstraction and factory
- rag_evaluation.py - Retrieval and answer quality metrics