#rag
3 papers
-
whitepaper
Fine-Tuning, RAG, or Prompting: An Engineering Decision
Three techniques can improve LLM output quality: prompt engineering, retrieval-augmented generation, and fine-tuning. Each solves a different problem. Choosing the wrong one wastes months and produces worse results than the right one done simply.
-
inspiration
Embeddings Are Not Optional
Every RAG pipeline, semantic search index, and similarity feature runs on embeddings. The generation model gets the credit. The embedding model does the work.
-
inspiration
Retrieval Is the Weakest Link
RAG systems fail at retrieval, not generation. Engineers blame the LLM. The problem is upstream.