skills.rest
Axel-DaMage
Axel-DaMageCOMMUNITY
Explore all skills by this author →
GitHub

rag-architect

Design and implement RAG systems with document chunking, embeddings, and hybrid search.

2|Updated Jun 29, 2026
Search Tags:#semantic search#rag#vector search#retrieval-augmented generation#embedding
One-click install
npx skills add https://github.com/Axel-DaMage/opencode-config --skill rag-architect-axel-damage
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/Axel-DaMage/opencode-config/tree/main/skills/rag-architect
Command: npx skills add https://github.com/Axel-DaMage/opencode-config --skill rag-architect-axel-damage

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, qdrant, cohere, langchain, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill empowers you to design and implement production-grade Retrieval-Augmented Generation (RAG) systems, streamlining the process of chunking documents, generating embeddings, configuring vector stores, and building hybrid search pipelines.

Core Features & Use Cases

  • RAG System Design: Designs and implements RAG systems by chunking documents, generating embeddings, configuring vector stores, and building hybrid search pipelines.
  • Hybrid Search: Combines vector and BM25 search to achieve high precision in document retrieval.
  • Reranking: Improves the ranking of search results based on relevance.
  • Evaluation & Iteration: Evaluates retrieval quality and iterates on the design to improve accuracy.
  • Use Case: Imagine you are developing a knowledge base application. Use this Skill to design and implement an efficient RAG system for retrieving and ranking relevant documents based on user queries.

Quick Start

Use the rag-architect skill to create a new RAG system for your knowledge base, specifying the document corpus and vector database configuration.

Frequently Asked Questions about rag-architect

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

FAQPage Schema
How do I build a retrieval-augmented generation system for semantic search?▼

Building a RAG system involves chunking documents, generating embeddings, configuring vector stores, and implementing hybrid search pipelines. This approach handles the complete workflow from document ingestion to retrieval evaluation.

What is hybrid search and how does it improve document retrieval?▼

Hybrid search combines vector search with BM25 search to achieve high precision in document retrieval. This dual approach leverages both semantic understanding and keyword matching to significantly improve search result relevance.

How do I improve search result relevance with reranking in a RAG pipeline?▼

Reranking improves the ranking of search results based on relevance within a RAG pipeline. After retrieving documents via hybrid search, a reranking model reorders the results to prioritize the most contextually accurate matches.

Does this RAG implementation work with Qdrant and Cohere?▼

Yes, this RAG implementation works with Qdrant for vector store configuration and Cohere for reranking. It also requires OpenAI and LangChain Python libraries to support various components of the retrieval pipeline.

What is the best way to evaluate retrieval quality in a RAG system?▼

The best way to evaluate retrieval quality in a RAG system is to assess search accuracy and iterate on the design. Evaluating retrieval quality helps identify weaknesses in chunking or embedding generation to improve overall accuracy.

Related Skills

Explore More Software Engineering Skills→
ancolemanancoleman
503

using-vector-databases

Implement vector databases for AI/ML semantic search and RAG systems.

Community
Advanced
as4584as4584
2

embedding-strategies

Compare embedding models and implement pipelines with chunking and retrieval metrics.

Community
Intermediate
jhl-labsjhl-labs
50

RAG & Vector Search

Retrieve relevant documents and augment LLM prompts with vector search.

Official
Advanced
neverinfamousneverinfamous
19

rag-pipelines

Design RAG pipelines with chunking, hybrid search, and cross-encoder reranking.

Community
Advanced