Topic Archive

AI

LLMs, AI tools, automation flows, and product updates.

3 published posts belong to this topic.

AI9/12/2026

When Search Keeps Pulling the Wrong Documents, What to Suspect Before Embeddings

When RAG retrieval quality won't improve, it's easy to blame the embedding model or the vector DB first, but the real culprit is often chunk splitting that mechanically cuts documents and fragments their context. This piece walks through examples of how common mistakes—fixed-length splitting, cutting sentences in half, separating tables from headings—wreck recall, then covers how to tune chunk size and overlap to match document structure, along with practical metrics for measuring retrieval quality.

#RAG#청크 분할#검색 품질#임베딩

AI8/20/2026

Why Finer Chunking Takes the Answer Further Away

Chunk size and the splitting criterion alone determine the quality of the embedding vectors. Cut wrong and similarity search returns only half-finished fragments with broken context, shattering the correct answer — but splitting larger doesn't fix it either. This article examines the mechanics behind common splitting mistakes and lays out practical evaluation metrics that look at search recall and response completeness together. It's structured so candidate chunk validation, context retrieval strategies, and per-criterion experiment methods can be applied directly to your pipeline.

#RAG#청크 분할#임베딩#벡터 검색

AI8/15/2026

Why the Screen Shatters While Tokens Flow

When an LLM response streams token by token over SSE and is painted to the screen, markdown syntax breaks midway, abort requests don't propagate properly, and rendering stutters on every token. This article walks through the real failures you hit in streaming UI—markdown parsing collapse, abort handling and error recovery, and rendering performance problems—in the order they break, then lays out proven fixes like partial rendering and a backpressure approach that minimizes buffer accumulation.

#SSE#스트리밍#LLM#마크다운 파싱