skills.rest
haxlys
haxlysCOMMUNITY
Explore all skills by this author →
GitHub

rag-implementation

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

1|Updated Apr 27, 2026
Search Tags:#embeddings#rag#retrieval-augmented generation#semantic-search#vector-databases#llm-integration#document-q&a
One-click install
npx skills add https://github.com/haxlys/skills --skill rag-implementation-haxlys
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-implementation
Source: https://github.com/haxlys/skills/tree/main/vendored/wshobson-agents/plugins/llm-application-dev/skills/rag-implementation
Command: npx skills add https://github.com/haxlys/skills --skill rag-implementation-haxlys

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Builds and orchestrates Retrieval-Augmented Generation (RAG) systems that ground LLM outputs using vector databases, embeddings, and semantic search.

Core Features & Use Cases

  • End-to-end RAG pipelines for knowledge-grounded QA over documents and knowledge bases
  • Integrations with popular vector stores and embedding models to enable scalable retrieval
  • Advanced patterns like HyDE, reranking, and multi-query retrieval to improve accuracy and coverage
  • Real-world use cases include knowledge-base assistants, documentation search, and current-information QA with citations

Quick Start

Connect an LLM, an embeddings model, and a vector store to initialize a retrieval-augmented QA flow and run a sample query.

Frequently Asked Questions about rag-implementation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I implement retrieval-augmented generation for a document QA assistant?▼

Build a retrieval-augmented generation pipeline by connecting an LLM, an embeddings model, and a vector store to enable semantic search over external knowledge sources. This grounds LLM outputs and provides source citations for document QA assistants.

What is the best way to improve RAG retrieval accuracy and coverage?▼

Improve RAG retrieval accuracy and coverage by applying advanced patterns like HyDE, reranking, and multi-query retrieval. These techniques refine semantic search results to provide highly relevant context to the LLM.

Can I use this RAG system for domain-specific chatbots needing current information?▼

Yes, you can build domain-specific chatbots requiring current information. The RAG system connects external knowledge sources to LLMs via semantic search, ensuring responses are grounded and include source citations.

How does semantic search work with vector databases in LLM integration?▼

Semantic search works by converting documents into embeddings and storing them in a vector database. During LLM integration, the system queries the vector store to retrieve embeddings matching the user's input semantic meaning.

Do I need a separate vector store to build a knowledge-base assistant?▼

Yes, you need a vector store to build a knowledge-base assistant. The RAG pipeline requires integrating an embeddings model with a vector database to enable scalable semantic retrieval of external knowledge.

Related Skills

Explore More Software Engineering Skills→
leonardoteodorooleonardoteodoroo

rag-implementation

Builds minimal RAG pipelines combining vector stores and document retrieval for grounded answers.

Community
Advanced
floflo777floflo777
33

rag-eval

Evaluate RAG systems using retrieval, generation, and latency metrics.

Community
Intermediate
Sumeet138Sumeet138
1

rag-implementation

Integrate retrieval-augmented generation workflows with vector databases and embeddings.

Community
Advanced
JeffallanJeffallan
10.9k

fine-tuning-expert

Automate fine-tuning workflows for large language models using LoRA/QLoRA and PEFT methods.

Community
Advanced