skills.rest
ekremmkasap
ekremmkasapCOMMUNITY
Explore all skills by this author →
GitHub

rag-implementation

Build Retrieval-Augmented Generation systems that ground LLM outputs in external knowledge sources.

Updated Mar 18, 2026
Search Tags:#embeddings#rag#semantic-search#retrieval-augmented-generation#vector-database#document-qa
One-click install
npx skills add https://github.com/ekremmkasap/jarvis --skill rag-implementation-ekremmkasap
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-implementation
Source: https://github.com/ekremmkasap/jarvis/tree/main/server/agent_prompts/wshobson/plugins/llm-application-dev/skills/rag-implementation
Command: npx skills add https://github.com/ekremmkasap/jarvis --skill rag-implementation-ekremmkasap

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables developers to build Retrieval-Augmented Generation (RAG) systems that ground LLM outputs in external knowledge sources, reducing hallucinations and enabling source-cited results.

Core Features & Use Cases

  • Grounded Q&A over proprietary documents with contextual retrieval and citation support.
  • Document-based chat assistants that stay up-to-date by querying vector stores and knowledge bases.
  • Research tooling to assemble end-to-end RAG pipelines with embedding models, vector stores, and reranking.

Quick Start

Ask your AI to assemble a complete RAG pipeline using your vectors and documents.

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 outputs in my own documents?▼

To build a RAG pipeline, you connect LLMs to external knowledge sources using vector stores and embeddings. This process grounds model outputs in your proprietary documents, reducing hallucinations and enabling cited answers for document-based chat.

What is retrieval-augmented generation and when do I need it for document Q&A?▼

Retrieval-augmented generation is a technique that fetches relevant context from a vector database before generating responses. You need it for document-based chat and research tools requiring current information, cited sources, and grounded Q&A over proprietary knowledge bases.

How do I implement semantic search and reranking for a knowledge-grounded chat assistant?▼

You implement semantic search by generating embeddings from your documents and storing them in a vector database. Reranking refines the retrieved results to ensure the most relevant context is passed into structured prompts for your chat assistant.

Can I use this to create a document chat assistant that cites its sources?▼

Yes, you can create a document chat assistant that stays up-to-date by querying vector stores and knowledge bases. The system uses contextual retrieval and structured prompts to generate responses with citation support for grounded Q&A.

What components are needed for an end-to-end RAG system with vector stores?▼

An end-to-end RAG system requires embedding models to vectorize text, a vector database for storage, retrieval strategies to fetch relevant context, and reranking components to refine results before feeding them into structured prompts for the LLM.

Why does my LLM hallucinate when answering questions about my proprietary documents?▼

LLMs hallucinate without external context because they lack access to your proprietary information. Implementing a RAG pipeline grounds the model by retrieving relevant document chunks via semantic search, ensuring responses are based on factual, cited sources.

Related Skills

Explore More Software Engineering Skills→
Clay-HHKClay-HHK
2

chroma

Store embeddings and metadata for semantic and full-text retrieval.

Community
Intermediate
Dianshu-LiaoDianshu-Liao
2

rag-implementation

Build retrieval-augmented generation systems with citation-ready outputs from external documents.

Community
Intermediate
JFrangelJFrangel

chunk-scoring

Optimize RAG pipelines with semantic chunking, embedding selection, and vector database configuration.

Community
Advanced
JhabbigJhabbig

rag-implementation

Build retrieval-augmented generation systems that ground LLM answers in external knowledge.

Community
Advanced