skills.rest
Sir-chawakorn
Sir-chawakornCOMMUNITY
Explore all skills by this author →
GitHub

rag-pipeline

Build and tune retrieval-augmented-generation pipelines for private corpora.

9|3|Updated Jun 13, 2026
Search Tags:#embeddings#rag#retrieval#ai-architecture#vector-database#llm-grounding
One-click install
npx skills add https://github.com/Sir-chawakorn/sanook-cli --skill rag-pipeline-sir-chawakorn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-pipeline
Source: https://github.com/Sir-chawakorn/sanook-cli/tree/main/skills/rag-pipeline
Command: npx skills add https://github.com/Sir-chawakorn/sanook-cli --skill rag-pipeline-sir-chawakorn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the challenge of grounding AI responses in private, large-scale, or domain-specific datasets, preventing hallucinations and ensuring high-relevance retrieval.

Core Features & Use Cases

  • Pipeline Orchestration: Provides a structured methodology for chunking, embedding, indexing, and reranking data.
  • Relevance Optimization: Includes strategies for hybrid search (dense + BM25) and cross-encoder reranking to ensure the most accurate context reaches the LLM.
  • Use Case: Use this to build a reliable "chat over my codebase" or "query my internal documentation" system that cites sources and admits when it lacks information.

Quick Start

Use the rag-pipeline skill to design a retrieval architecture for my internal technical documentation that supports hybrid search and citation-based grounding.

Frequently Asked Questions about rag-pipeline

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

FAQPage Schema
How do I build a retrieval-augmented-generation pipeline for private technical documentation?▼

A retrieval-augmented-generation pipeline grounds AI responses in private datasets by chunking, embedding, and storing data in a vector database. This pipeline uses hybrid search and reranking to ensure factual consistency and high retrieval relevance.

What is the best way to prevent LLM hallucinations on internal knowledge bases?▼

Grounding LLM responses in private, domain-specific datasets prevents hallucinations by ensuring the model relies on retrieved context. This skill uses deterministic embeddings and grounding prompt engineering to maintain factual consistency across internal knowledge bases.

How do I implement hybrid search for RAG pipelines over a codebase?▼

Implement hybrid search for RAG pipelines by combining dense vector embeddings with BM25 retrieval strategies. This skill orchestrates both approaches alongside cross-encoder reranking to deliver the most accurate context to the LLM over a codebase.

Does this RAG architecture support complex chunking and reranking for large-scale data?▼

Yes, this RAG architecture supports complex document processing including chunking, embedding, and cross-encoder reranking for large-scale private data. It is designed to handle complex corpora and tune retrieval accuracy for production-grade environments.

Why does my RAG system retrieve irrelevant context from my vector database?▼

Your RAG system retrieves irrelevant context if it lacks hybrid search strategies and cross-encoder reranking. This skill addresses relevance optimization by combining dense and BM25 search to ensure the most accurate context reaches the LLM.

Related Skills

Explore More Software Engineering Skills→
mahg-esmahg-es
3

rag-pipeline

Implement end-to-end RAG pipelines with chunking, embeddings, and hybrid search.

Official
Advanced
magicseekmagicseek
33

nblm

Query Google NotebookLM notebooks for source-grounded, citation-backed answers via Gemini.

Community
Advanced
HermeticOrmusHermeticOrmus

RAG Patterns

Provide expert patterns for building RAG systems with pgvector, BM25, and RAGAS evaluation.

Community
Advanced
zli5460zli5460
2

unsloth

Fine-tune large language models with LoRA, QLoRA, and full fine-tuning.

Community
Intermediate