skills.rest
ccf
ccfCOMMUNITY
Explore all skills by this author →
𝕏@cfigueirGitHub

rag-implementation

Retrieve information from external documents using vector stores and embeddings.

1|Updated Dec 23, 2025
Search Tags:#embeddings#langchain#rag#citations#retrieval-augmented generation#semantic-search#vector-store
One-click install
npx skills add https://github.com/ccf/claude-code-ccf-marketplace --skill rag-implementation-ccf
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-implementation
Source: https://github.com/ccf/claude-code-ccf-marketplace/tree/main/plugins/llm-application-dev/skills/rag-implementation
Command: npx skills add https://github.com/ccf/claude-code-ccf-marketplace --skill rag-implementation-ccf

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables knowledge-grounded responses by retrieving information from external documents using vector stores and embeddings.

Core Features & Use Cases

  • Retrieval-Augmented Generation pipelines: combine embeddings, vector stores, and LLMs to answer questions with citations.
  • Document Q&A and knowledge-base chat: build chat assistants over proprietary content.
  • Citation-friendly responses: provide source documents for transparency and auditing.

Quick Start

Load your documents into a vector store, configure an embeddings model, create a retrieval QA chain, and query with a question to obtain grounded answers with sources.

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 retrieval-augmented generation pipeline with citations for document Q&A?▼

To build a retrieval-augmented generation pipeline, load documents into a vector store, configure an embeddings model, and create a retrieval QA chain to answer questions with citations. This grounds responses in external content.

What is retrieval-augmented generation and when do I need it for a knowledge-base chatbot?▼

Retrieval-augmented generation (RAG) enables knowledge-grounded responses by retrieving information from external documents using vector stores. You need it for building knowledge-base chatbots requiring current information and source citations.

Does this RAG implementation support both dense and sparse retrieval?▼

Yes, this RAG implementation satisfies both dense and sparse retrieval, along with optional reranking. It applies to building document Q&A systems and research tools requiring current information and citations.

What's the best way to index external documents for semantic search with an LLM?▼

The best way to index documents for semantic search is loading them into a vector store and configuring an embeddings model. This allows the retrieval pipeline to find relevant information and provide citation-friendly responses.

Can I use LangChain to create a retrieval QA chain for proprietary content?▼

Yes, you can use LangChain to create a retrieval QA chain for proprietary content. This Skill combines embeddings, vector stores, and LLMs to build chat assistants over proprietary content with source citations.

Related Skills

Explore More Software Engineering Skills→
vecearvecear

embedding-pipeline-builder

Build document embedding and retrieval pipelines for scalable semantic search.

Community
Advanced
EntelligentsiaEntelligentsia
1

rag

Retrieve external documents and integrate cited sources into LLM answers.

Official
Advanced
neverinfamousneverinfamous
19

rag-pipelines

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

Community
Advanced
DrLuggelsDrLuggels
3

rag-implementation

Develops RAG systems for LLM applications using vector databases and embedding models.

Community
Advanced