rag-infrastructure

What problem does it solve?

This Skill addresses the complexity of building and operating Retrieval-Augmented Generation (RAG) infrastructure, enabling users to create knowledge base Q&A systems and semantic search over large document collections.

Core Features & Use Cases

• RAG Pipeline: Covers the end-to-end process from document ingestion to LLM response generation.
• Embedding & Vector Stores: Integrates with various embedding models and vector databases (Qdrant, Weaviate, Pinecone, pgvector).
• Hybrid Search: Implements combined dense and sparse (BM25) retrieval for improved accuracy.
• Reranking: Enhances relevance by reranking retrieved documents before LLM consumption.
• Use Case: Develop a Q&A system for internal company documentation that provides accurate, context-aware answers to employee queries.

Quick Start

Use the rag-infrastructure skill to ingest documents into a Qdrant vector store using the provided Python scripts.