#rag
Rag: 18 AI articles covering rag news, analysis, and research
Articles
Multi-Vector (Late Interaction) Embedding Models with Sentence⭐9
Learn how multi-vector late interaction models with Sentence Transformers boost retrieval accuracy by preserving token-level context for semantic search and RAG...
Loop Engineering for RAG: Small Loops Within Steps, Big Loops⭐9
Loop engineering in RAG: detecting failures, adjusting, and retrying steps to turn brittle one-shot pipelines into resilient systems that recover and deliver.
Designing a Persistent Knowledge Layer That Refuses to Guess⭐9
This article explores moving beyond basic RAG systems by designing a persistent knowledge layer that values factual accuracy and refuses to make guesses.
RAG Workflow and Loop Engineering: The Dispatcher That Decides⭐9
A dispatcher pattern for RAG pipelines that decides when to loop and stop, coordinating retrieval, aggregation, and synthesis for enterprise reliability.
Building Document Structure with Loop Engineering: Recovering a⭐9
How to rebuild a PDF's missing table of contents from body typography for RAG systems, using loop engineering on heading styles to recover document structure.
Prompt, Context, Loop: The Three Engineering Layers Every RAG⭐10
Explore the three engineering layers of RAG systems: prompt, context, and loop. Learn how each layer works and why their evolution isn't a simple sequence.
How I Reproduced BM25, Dense Retrieval, and SPLADE on a 16GB MacBook⭐9
I reproduced BM25, dense retrieval & SPLADE on a 16GB MacBook, matching RAG baselines; includes crash fixes & score interpretation.
Most RAG Hallucinations Are Extraction Errors: Seven Patterns⭐9
RAG failures are often extraction mistakes, not true hallucinations. Use typed generation contracts with seven patterns to enforce correct answer shapes and red...