skills.rest
CarlosAndresBF1
CarlosAndresBF1COMMUNITY
Explore all skills by this author →
GitHub

rag-implementation

Build RAG pipelines with vector stores and retrieval strategies for document Q&A.

Updated Mar 16, 2026
Search Tags:#embeddings#rag#semantic-search#vector-databases#retrieval-augmented-generation#document-qa#knowledge-grounded-ai
One-click install
npx skills add https://github.com/CarlosAndresBF1/RAG-SERVER-2026 --skill rag-implementation-carlosandresbf1
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-implementation
Source: https://github.com/CarlosAndresBF1/RAG-SERVER-2026/tree/main/.agents/skills/rag-implementation
Command: npx skills add https://github.com/CarlosAndresBF1/RAG-SERVER-2026 --skill rag-implementation-carlosandresbf1

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Retrieve-grounded generation enabling LLMs to access external knowledge sources and produce accurate, sourced responses, reducing hallucinations.

Core Features & Use Cases

  • End-to-end RAG pipelines using vector stores, embeddings, and retrieval strategies to answer questions over proprietary documents.
  • Flexible backends (Pinecone, Weaviate, Milvus, pgvector) with optional reranking to improve answer relevance.
  • Use cases include knowledge-grounded chatbots, document Q&A, and research tooling with traceable sources.

Quick Start

Create a complete RAG pipeline against your document set and run an example question to validate grounded responses.

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?▼

Building a RAG pipeline for document Q&A involves connecting vector stores, embedding models, and retrieval strategies to ground LLM outputs with external knowledge sources. This Skill implements end-to-end workflows that connect your proprietary documents to LLMs, enabling accurate, traceable responses.

What is retrieval-augmented generation and how does it reduce hallucinations?▼

Retrieval-augmented generation (RAG) reduces hallucinations by grounding LLM outputs in external knowledge sources before generation. By retrieving relevant information from proprietary documents via semantic search, the system ensures answers are accurate, sourced, and traceable.

Does this RAG implementation support Pinecone, Weaviate, and pgvector?▼

Yes, this RAG implementation supports flexible vector database backends including Pinecone, Weaviate, Milvus, and pgvector. It integrates these vector stores with embedding models and optional reranking to improve answer relevance over your proprietary documents.

What's the best way to improve retrieval relevance in a RAG system?▼

The best way to improve retrieval relevance in a RAG system is by applying optional reranking patterns alongside semantic search and embedding models. This Skill implements retrieval and re-ranking strategies within graph-based orchestration to enhance the accuracy of retrieved document chunks.

Can I use graph-based orchestration for my RAG pipelines?▼

Yes, you can use graph-based orchestration for your RAG pipelines. This Skill implements graph-based orchestration to manage end-to-end workflows, coordinating vector stores, embedding models, and retrieval strategies to answer questions over proprietary documents.

Related Skills

Explore More Software Engineering Skills→
theslashdojotheslashdojo

vectors

Store and search vector embeddings in Postgres using pgvector and HNSW indexing.

Official
Advanced
melikhanmutlumelikhanmutlu

rag-implementation

Build retrieval-augmented generation pipelines with vector databases and semantic search.

Community
Advanced
Greenmamba29Greenmamba29

vector-embedder

Generate and store vector embeddings for semantic search pipelines.

Community
Intermediate
cuoreinpacecuoreinpace

rag-implementation

Implement RAG systems with vector databases and semantic search for LLM applications.

Community
Advanced