skills.rest
Hanseooo
HanseoooCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

rag-implementation

Build end-to-end RAG pipelines with embeddings, vector stores, and reranking.

Updated Aug 23, 2026
Search Tags:#embeddings#llm#rag#grounding#vector-databases#retrieval-augmented-generation
One-click install
npx skills add https://github.com/Hanseooo/hanseo-opencode-workflows --skill rag-implementation-hanseooo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-implementation
Source: https://github.com/Hanseooo/hanseo-opencode-workflows/tree/main/skills/rag-implementation
Command: npx skills add https://github.com/Hanseooo/hanseo-opencode-workflows --skill rag-implementation-hanseooo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Retrieval-Augmented Generation enables grounding AI responses in external knowledge sources, reducing hallucinations and improving factual accuracy.

Core Features & Use Cases

  • End-to-end RAG pipelines that connect embeddings, vector stores, and LLMs to produce grounded answers.
  • Supports multiple vector stores and embedding models, with patterns like HyDE, MMR, and contextual compression.
  • Use cases include Q&A over proprietary documents, domain-specific chat assistants, and research tooling.

Quick Start

Build a complete retrieval-augmented generation workflow by configuring your embeddings, vector store, and LLM to answer questions grounded in your 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 to ground LLM answers in my own documents?▼

To build a RAG pipeline, connect embeddings, vector stores, and LLMs to retrieve external documents and generate grounded answers. This end-to-end workflow reduces hallucinations and improves factual accuracy for document Q&A systems.

What is retrieval-augmented generation and when do I need it for my chatbot?▼

Retrieval-augmented generation grounds AI responses in external knowledge sources to reduce hallucinations. You need it for domain-specific chat assistants or research tooling requiring up-to-date, factual information from proprietary documents.

What's the best way to implement MMR and contextual compression for retrieval?▼

Implement MMR and contextual compression by applying these retrieval patterns within your RAG pipeline. They refine the embeddings and vector store results to ensure the LLM receives the most relevant, high-quality context before generating an answer.

Can I use this to create a document QA system with custom embedding models?▼

Yes, you can create a document QA system using custom embedding models. The implementation supports multiple vector stores and embedding models, allowing you to configure the end-to-end retrieval workflow for your proprietary documents.

Does HyDE work with vector databases for improving retrieval accuracy?▼

HyDE works with vector databases by generating hypothetical document embeddings to improve search relevance. This pattern is supported within the retrieval pipeline to enhance the contextual data fetched before the LLM generates its final response.

Related Skills

Explore More Software Engineering Skills→
dotlab-hqdotlab-hq

langchain-rag

Build RAG pipelines that ingest, chunk, embed, and retrieve documents for LLMs.

Official
Intermediate
jpoindexterjpoindexter
1

llm-evals-and-retrieval-quality

Evaluate and improve LLM and RAG systems with retrieval metrics and grounding checks.

Community
Advanced
svssdevasvssdeva
1

rag-implementation

Build Retrieval-Augmented Generation systems with semantic search and vector storage.

Community
Advanced
spideynolovespideynolove
2

rag-implementation

Build knowledge-grounded question-answering systems with RAG, vector databases, and embeddings.

Community
Advanced