skills.rest
atrawog
atrawogCOMMUNITY
Explore all skills by this author →
Website𝕏@atrawogGitHub

rag

Retrieve knowledge base context to ground LLM answers with RAG.

Updated Aug 23, 2026
Search Tags:#embeddings#langchain#llm#rag#retrieval-augmented-generation#vector-store#chromadb
One-click install
npx skills add https://github.com/atrawog/overthink-plugins --skill rag-atrawog
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag
Source: https://github.com/atrawog/overthink-plugins/tree/main/overthink-jupyter/skills/rag
Command: npx skills add https://github.com/atrawog/overthink-plugins --skill rag-atrawog

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

LLMs often hallucinate or rely on outdated knowledge; RAG grounds answers by retrieving relevant documents before generation.

Core Features & Use Cases

  • Document chunking into manageable segments
  • Embeddings and vector stores for fast similarity search
  • Conversational RAG pipelines across multi-turn dialogs
  • Use cases: Q&A over corporate knowledge bases, legal research, customer support knowledge bases

Quick Start

Ask the AI to answer questions using retrieved context from your knowledge base.

Frequently Asked Questions about rag

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

FAQPage Schema
How does retrieval-augmented generation ground LLM answers with external knowledge?▼

Retrieval-augmented generation grounds LLM answers by retrieving relevant documents from a knowledge base before generation, preventing hallucinations and ensuring responses rely on provided context.

How do I build a conversational RAG pipeline for multi-turn dialogs using LangChain?▼

You can build a conversational RAG pipeline using LangChain to manage multi-turn dialogs, retrieving context from a vector store like ChromaDB to inform LLM responses across the conversation.

What's the best way to chunk documents for similarity search in a vector store?▼

Chunking documents into manageable segments is the best way to prepare text for similarity search, allowing embeddings to accurately represent content for fast retrieval in a vector store.

Can I use ChromaDB and LangChain to create a Q&A system over corporate knowledge bases?▼

Yes, you can use ChromaDB and LangChain to implement a Q&A system over corporate knowledge bases, leveraging document chunking and embeddings to retrieve context for LLM generation.

Why do LLMs hallucinate and when do I need a RAG pipeline to fix it?▼

LLMs hallucinate when relying on outdated knowledge; you need a RAG pipeline to fix this by retrieving relevant external documents before generation to ground answers in factual context.

Related Skills

Explore More Software Engineering Skills→
ShipFailShipFail
1

Memory Manager

Chunk text and documents into semantic pieces with metadata for Vector.Store.

Official
Intermediate
LuisSambranoLuisSambrano
7

rag-mastery

Develop and optimize Retrieval-Augmented Generation systems with chunking, embedding models, vector stores, and retrieval strategies.

Community
Advanced
patornpatorn

langchain-rag

Build end-to-end RAG pipelines with LangChain document loaders, embeddings, and vector stores.

Community
Advanced
JhabbigJhabbig

rag-implementation

Build retrieval-augmented generation systems that ground LLM answers in external knowledge.

Community
Advanced