skills.rest
ACGSpgp
ACGSpgpOFFICIAL
Explore all skills by this author →
WebsiteGitHub

rag-implementation

Implement RAG systems with vector databases, embedding models, and retrieval strategies.

Updated Aug 23, 2026
Search Tags:#knowledge retrieval#semantic search#embeddings#llm#rag#vector database
One-click install
npx skills add https://github.com/ACGSpgp/ACGS --skill rag-implementation-acgspgp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-implementation
Source: https://github.com/ACGSpgp/ACGS/tree/main/.agent/workflows/llm-application-dev/1.2.1/skills/rag-implementation
Command: npx skills add https://github.com/ACGSpgp/ACGS --skill rag-implementation-acgspgp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

This Skill enables the creation of LLM applications that can accurately answer questions and generate text grounded in external knowledge sources, significantly reducing hallucinations.

Core Features & Use Cases

  • Vector Databases: Store and retrieve document embeddings for efficient semantic search.
  • Embeddings: Convert text into numerical vectors for similarity matching.
  • Retrieval Strategies: Implement various methods like dense, sparse, and hybrid search.
  • Reranking: Improve the quality and relevance of retrieved documents.
  • Use Case: Build a Q&A system over your company's internal documentation, allowing employees to ask natural language questions and receive accurate answers directly from the knowledge base.

Quick Start

Use the rag-implementation skill to build a Q&A system over documents in the './docs' directory using OpenAI embeddings and Chroma as the vector store.

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 knowledge-grounded LLM Q&A system over my internal documents?▼

You can build a knowledge-grounded LLM Q&A system by implementing retrieval-augmented generation, integrating vector databases like Chroma or Pinecone with embedding models to store and retrieve document text. This enables natural language questions to receive accurate answers from your knowledge base.

How do embeddings and vector databases work together for semantic search?▼

Embeddings convert text into numerical vectors, which vector databases store for efficient similarity matching. Semantic search queries the database to retrieve relevant document chunks, grounding LLM text generation in external knowledge.

Can I use OpenAI embeddings with Pinecone for retrieval-augmented generation?▼

Yes, you can configure retrieval-augmented generation systems using OpenAI embeddings with Pinecone as the vector store. The Skill requires selecting and configuring compatible embedding models and vector stores.

What's the best way to improve the relevance of retrieved documents in a RAG pipeline?▼

To improve relevance in a retrieval-augmented generation pipeline, implement reranking techniques and hybrid search strategies. Retrieval strategies like dense, sparse, and hybrid search combined with reranking improve retrieved document quality.

Why does my LLM hallucinate answers instead of using my external knowledge base?▼

LLMs hallucinate without external knowledge grounding. Retrieval-augmented generation solves this by integrating vector databases and embedding models to fetch relevant context, grounding generated text in external knowledge sources.

Does the rag-implementation Skill support sparse and dense retrieval strategies?▼

Yes, the rag-implementation Skill supports implementing various retrieval strategies including dense, sparse, and hybrid search methods to facilitate knowledge-grounded AI and document Q&A.

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
AI-Foundry-CoreAI-Foundry-Core
4

rag-implementation

Retrieve relevant documents to ground LLM outputs with citations.

Official
Advanced
anukkrit149anukkrit149

rag-implementation

Build Retrieval-Augmented Generation systems grounding LLM answers in vector databases.

Community
Advanced
tiankong0101-bytetiankong0101-byte

openviking

Retrieve relevant stored content using hybrid semantic and keyword search.

Community
Advanced