skills.rest
zzafergok
zzafergokCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

rag-implementation

Design and build RAG systems grounding LLM outputs in external knowledge sources.

1|1|Updated Mar 22, 2026
Search Tags:#embeddings#llm#rag#semantic-search#vector-databases#knowledge-grounded#retrieval-augmented-generation
One-click install
npx skills add https://github.com/zzafergok/skills --skill rag-implementation-zzafergok
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-implementation
Source: https://github.com/zzafergok/skills/tree/main/01-ai-intelligence/rag-implementation
Command: npx skills add https://github.com/zzafergok/skills --skill rag-implementation-zzafergok

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Grounding LLMs to external knowledge sources to avoid hallucinations and provide verifiable answers.

Core Features & Use Cases

  • Vector databases for storing embeddings
  • Embeddings and retrieval strategies (dense, sparse, hybrid)
  • Reranking and citation of source documents
  • Use cases: knowledge bases, document QA, enterprise assistants

Quick Start

Provide a concise plan to set up a RAG pipeline using a document collection, a vector store, and an embedding model to answer user questions.

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 retrieval-augmented generation pipeline to ground LLM outputs in external knowledge?▼

To build a retrieval-augmented generation pipeline, you need a vector database for storing embeddings, an embedding model, and retrieval strategies to index and query document collections, grounding LLM outputs in external knowledge sources to avoid hallucinations.

What is the best way to implement semantic search for a document Q&A system?▼

The best way to implement semantic search for document Q&A is using dense, sparse, or hybrid retrieval strategies combined with reranking to fetch relevant context from a vector database, ensuring verifiable answers from your enterprise knowledge base.

Do I need a vector database to set up a knowledge-grounded LLM assistant?▼

Yes, you need a vector database to store embeddings and support the indexing and querying pipelines required for a knowledge-grounded LLM assistant to retrieve relevant information from unstructured and structured data sources.

How does reranking improve retrieval-augmented generation for enterprise knowledge tools?▼

Reranking improves retrieval-augmented generation by reordering retrieved documents based on relevance, enhancing the accuracy of citations and ensuring the LLM receives the most pertinent context from the external knowledge base.

Can I use retrieval-augmented generation with structured and unstructured data?▼

Yes, retrieval-augmented generation supports both structured and unstructured data across domains, allowing you to build versatile document Q&A systems and enterprise assistants that ground LLM outputs in diverse external knowledge sources.

Why does my LLM hallucinate when answering questions from my knowledge base?▼

Your LLM hallucinates because it lacks grounding in external knowledge sources; implementing a retrieval-augmented generation pipeline with vector databases, embeddings, and proper retrieval strategies provides verifiable context to eliminate hallucinations.

Related Skills

Explore More Software Engineering Skills→
rukikotoorukikotoo
6

rag

Query the econometrics RAG knowledge base to retrieve relevant document chunks.

Community
Intermediate
AxelooooAxeloooo

rag-implementation

Implement RAG pipelines with vector retrieval and context-grounded generation.

Community
Intermediate
qcmuuqcmuu

pinecone

Manage Pinecone indexes for upsert, query, and delete operations on dense and sparse vectors.

Community
Intermediate
fabioc-alohafabioc-aloha
1

RAG Architecture Skill

Build RAG pipelines with document processing, chunking, embedding, and vector storage.

Community
Advanced