Graph Expansion 기반 Recall 1.0 달성 및 Reranking 통한 정밀도 최적화
Building KernelMind Part 3: Evaluation, Retrieval Ablations, RAGAS, and Turning The Project Into Something Measurable
Building KernelMind Part 3: Evaluation, Retrieval Ablations, RAGAS, and Turning The Project Into Something Measurable
Building KernelMind Part 2: Hybrid Retrieval, Reranking, and Actually Retrieving Useful Code
Why production RAG fails — and the boring metrics that fix it
I evaluated my self-trained LLM what 31% accuracy actually means
Why your local LLM knowledge base gives bad answers (and how to fix it)
Two Retrieval Methods Are Better Than One: Evidence from 500 Clinical Queries
Beyond Vector Search: Mastering Contextual Retrieval for LLMs
Stop Wasting Tokens: High-Performance Local Re-ranking with Spring AI and JEP 489
이중 의미론적 Chunking 및 BGE-zh-v1.5 기반 RAG 최적화로 First-hit Rate 23% 향상
My First RAG System Had No Evals. 40% of Answers Were Wrong.
Context Pruning Unlocks Superior RAG Accuracy Metrics
Training and Finetuning Reranker Models with Sentence Transformers v4