Optimize embedding, indexing, and retrieval strategies for RAG systems.
npx skills add https://github.com/melikhanmutlu/web_ar --skill rag-engineer-melikhanmutlu
Please help me install this Agent Skill. Skill: rag-engineer Source: https://github.com/melikhanmutlu/web_ar/tree/main/skills-extra/rag-engineer Command: npx skills add https://github.com/melikhanmutlu/web_ar --skill rag-engineer-melikhanmutlu
Retrieval quality in LLM workflows is critical to accuracy; this skill addresses the gap by optimizing how documents are embedded, chunked, and retrieved for use in RAG systems.
Configure embeddings and a retrieval pipeline to run a RAG workflow on your documents.
High-intent search queries and answers about installing and using this skill.
Build a RAG pipeline by optimizing document chunking, generating vector embeddings, and configuring semantic search retrieval. This skill guides embedding model selection and indexing strategies to improve retrieval quality across diverse document types.
Effective document chunking splits text into manageable segments to preserve context for embedding models. This skill provides chunking strategies that optimize semantic search accuracy and ensure relevant information is retrieved within context window limits.
Hybrid search improves retrieval quality by combining keyword and semantic search methods. This approach captures both exact term matches and conceptual meaning, enhancing the accuracy of retrieval pipelines and providing better context for LLMs.
Yes, you can integrate vector databases into your semantic search pipeline. The skill supports scalable vector database integration, allowing you to store embeddings and execute fast similarity searches across large document collections.
Irrelevant semantic search results often stem from poor embedding model selection or suboptimal chunking strategies. This skill addresses retrieval quality gaps by optimizing how documents are embedded, indexed, and retrieved in RAG systems.
You need to select an appropriate embedding model that aligns with your document types and retrieval goals. This skill helps configure embeddings and context window optimization to ensure efficient and accurate retrieval pipeline performance.
patricio0312revAutomate document embedding pipelines for semantic search.
h4vzzOptimize raw context chunks for AI models within a token budget.
Nuwanda04Analyze prompts, evaluate RAG systems, and design agentic workflows.
giosuetedeschi-specDesign and optimize Retrieval-Augmented Generation pipelines for improved context retrieval.
