rag-implementation

Build Retrieval-Augmented Generation pipelines grounding LLM responses in external knowledge sources.

Updated Apr 10, 2026

Search Tags:#embeddings #rag #reranking #llm-workflows #semantic-search #vector-database #document-retrieval

Ready to run

npx skills add https://github.com/LuizEduPP/skills --skill rag-implementation-luizedupp

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: rag-implementation
Source: https://github.com/LuizEduPP/skills/tree/main/rag-implementation
Command: npx skills add https://github.com/LuizEduPP/skills --skill rag-implementation-luizedupp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill keeps LLM responses grounded by connecting them to retrieval pipelines, vector databases, and embeddings so the system can rely on factual, timely knowledge instead of hallucination-prone reasoning.

Core Features & Use Cases

Vector database guidance: Compare Pinecone, Weaviate, Milvus, Chroma, Qdrant, and pgvector to store document embeddings and tune similarity searches.
Embedding and retrieval patterns: Orchestrate LangGraph flows, dense/sparse/hybrid searches, reranking, HyDE, contextual compression, and parent document strategies.
Operational readiness: Document chunking, prompt engineering with citations, structured outputs, and evaluation metrics make this ideal for document Q&A, knowledge-base assistants, and research tools.

Quick Start

Ask this skill to assemble a LangGraph RAG flow that retrieves document context and answers your current question with citations.

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 that grounds LLM responses in external knowledge?▼

To build a RAG pipeline, orchestrate vector stores, embeddings, and retrieval patterns like LangGraph flows. This connects LLM responses to factual external knowledge sources, preventing hallucination-prone reasoning in document question answering.

What is the best way to compare vector databases for storing document embeddings?▼

Comparing vector databases involves evaluating Pinecone, Weaviate, Milvus, Chroma, Qdrant, and pgvector. You compare their capabilities to store document embeddings and tune similarity searches for your specific retrieval-augmented generation requirements.

How does reranking improve retrieval-augmented generation results?▼

Reranking improves retrieval-augmented generation by ordering retrieved document chunks more accurately. Combined with HyDE, contextual compression, and hybrid searches, reranking ensures the LLM receives the most relevant context for factual answers.

Can I use LangGraph to orchestrate dense and sparse retrieval patterns?▼

Yes, you can use LangGraph to orchestrate dense, sparse, and hybrid search patterns. This workflow manages document retrieval, reranking, and contextual compression to feed precise external knowledge into LLM responses with citations.

Do I need prompt engineering and chunking for a knowledge-base chatbot?▼

Yes, document chunking and prompt engineering with citations are required for a knowledge-base chatbot. These operational readiness steps ensure the retrieval pipeline supplies properly segmented context and structured outputs for factual responses.

Why does my LLM hallucinate instead of using retrieved document context?▼

An LLM hallucinates without proper retrieval pipelines connecting it to vector databases and embeddings. Implementing contextual compression, parent document strategies, and evaluation metrics keeps the generated answers grounded in factual knowledge.