Guide design of RAG systems with chunking, embedding, and hybrid search.
npx skills add https://github.com/Serg28/demosite --skill rag-architect-serg28
Please help me install this Agent Skill. Skill: rag-architect Source: https://github.com/Serg28/demosite/tree/main/.agents/skills/rag-architect Command: npx skills add https://github.com/Serg28/demosite --skill rag-architect-serg28
This Skill enables the development of scalable and production-grade RAG systems by providing structured guidance on document chunking, embedding strategies, vector store design, and retrieval pipelines.
Use the rag-architect skill to set up and evaluate a vector retrieval system for your knowledge domain.
High-intent search queries and answers about installing and using this skill.
Designing a production-level retrieval-augmented system requires structuring document chunking, embedding strategies, and vector store architecture. This Skill provides guidance on building scalable pipelines with hybrid search and reranking to ensure accurate semantic retrieval.
To optimize a vector retrieval pipeline, integrate hybrid search techniques and reranking methods to improve retrieval quality. This Skill guides the implementation of advanced embedding strategies and evaluation methods for scalable knowledge base retrieval.
Document chunking directly impacts embedding-based indexing by determining the granularity of semantic context retrieved. This Skill offers structured guidance on advanced chunking strategies to ensure accurate document retrieval and context augmentation in AI applications.
Yes, you can build a knowledge base with semantic search for customer support FAQs to enable fast and accurate responses. This Skill facilitates architecture planning for contextual retrieval and context augmentation in scalable AI assistive applications.
No specific vector store dependencies are required to implement hybrid search and reranking. This Skill provides architecture planning and best practices for designing vector store layouts and retrieval pipelines that integrate these advanced techniques.
Irrelevant semantic retrieval results often stem from suboptimal document chunking, poor embedding strategies, or lack of reranking. This Skill guides evaluation methods and pipeline optimization techniques to improve retrieval quality and accuracy.
giuseppe-trisciuoglioBuild retrieval-augmented generation pipelines with vector databases and embedding models.
spideynoloveCompare embedding models and define chunking strategies for RAG pipelines.
CyangZhouAnalyze images and generate multimodal responses grounded in visual context.
andrewblockernstImplements vector-based semantic search for documents using AgentDB and Node.js.
