skills.rest
anukkrit149
anukkrit149COMMUNITY
Explore all skills by this author →
Website𝕏@anukkritGitHub

rag-implementation

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

Updated May 26, 2026
Search Tags:#embeddings#rag#vector search#langgraph#reranking#document q&a#semantic retrieval
One-click install
npx skills add https://github.com/anukkrit149/anukkrit-skills --skill rag-implementation-anukkrit149
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-implementation
Source: https://github.com/anukkrit149/anukkrit-skills/tree/main/cloud/skills/rag-implementation
Command: npx skills add https://github.com/anukkrit149/anukkrit-skills --skill rag-implementation-anukkrit149

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Retrieval-Augmented Generation solves the problem of LLM hallucinations and outdated answers by grounding responses in relevant external documents.

Core Features & Use Cases

  • Build RAG over your knowledge: Set up end-to-end flows that index documents and answer questions using retrieved context for accurate, source-grounded responses.
  • Use semantic search + robust retrieval: Implement vector databases, embeddings, and retrieval strategies (dense, sparse, hybrid, multi-query, HyDE) to improve recall.
  • Improve answer quality with reranking, chunking, and evaluation: Apply reranking and context management (compression, parent/child retrievers) and measure faithfulness and retrieval metrics.

Quick Start

Implement a RAG pipeline that chunks documents, embeds them into a vector store, retrieves top matching passages for a user question, and prompts the LLM to answer using only that retrieved context.

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 RAG pipeline for document Q&A?▼

To build a RAG pipeline, chunk documents into passages, embed them into a vector database, retrieve top semantic matches for a query, and constrain the LLM generation prompt to answer using only that retrieved context.

What is the best way to improve RAG retrieval recall?▼

Improve RAG retrieval recall by using hybrid search strategies, multi-query generation, or HyDE, alongside dense and sparse retrievers to fetch broader and more relevant context passages before generation.

Why does my retrieval-augmented generation system still hallucinate?▼

Retrieval-augmented generation hallucinations often stem from unranked context or poor chunking; applying reranking, context compression, and strict generation prompts that constrain output to retrieved passages mitigates this.

Do I need embeddings and vector search for semantic retrieval?▼

Yes, embeddings and vector search are required for semantic retrieval, as they map natural language queries and documents into vector space to find top matching passages for grounded generation.

How does reranking and context compression affect RAG answer quality?▼

Reranking and context compression improve RAG answer quality by filtering and prioritizing the most relevant retrieved passages, reducing noise, and allowing the generation prompt to focus strictly on high-fidelity context.

Can I use LangGraph to manage retrieval-augmented research workflows?▼

LangGraph can manage retrieval-augmented research workflows by orchestrating the semantic retrieval, context compression, and generation steps required to ground external knowledge in document Q&A systems.

Related Skills

Explore More Software Engineering Skills→
Greenmamba29Greenmamba29

vector-embedder

Generate and store vector embeddings for semantic search pipelines.

Community
Intermediate
marchattonmarchatton
5

evaluate-rag

Evaluate RAG pipelines with Recall@k, Precision@k, MRR, and NDCG@k metrics.

Community
Advanced
AxelooooAxeloooo

rag-implementation

Implement RAG pipelines with vector retrieval and context-grounded generation.

Community
Intermediate
patronus-aipatronus-ai
2

rag-implementation

Build RAG systems using vector databases and semantic search.

Official
Intermediate