#Search

5 articles tagged with Search.

AI•#Rag#Embeddings•last month

Debugging RAG Retrieval — Why It Returns Garbage

When RAG answers go sideways, the model usually isn't the problem. Here's the top-to-bottom checklist we run to find where retrieval actually breaks.

KU

Kiril Urbonas·20

Read article

AI•#Rag#Search•last month

Reranking in RAG: When a Cross-Encoder Earns Its Latency

Our RAG answers kept citing the wrong paragraph even when the right one was retrieved. A cross-encoder reranker fixed relevance but added 180ms. Here's when that trade pays off.

KU

Kiril Urbonas·17

Read article

AI•#Rag#LLM•2 months ago

RAG Chunking Strategies: Fixed, Semantic, and Recursive Compared

Our support bot kept citing half a sentence and missing the answer that sat two lines below. The culprit wasn't the model, it was how we split the docs.

KU

Kiril Urbonas·9

Read article

AI•#Rag#Eval•2 months ago

RAG Retrieval Evaluation — Building an Offline Eval Harness Before You Ship

You can't improve retrieval you don't measure. The offline eval harness that lets us change embeddings, chunking, and rerankers with confidence instead of vibes — with the metrics that actually predict production quality.

KU

Kiril Urbonas·15

Read article

AI•#Ai#Rag•3 months ago

Hybrid Search — Combining BM25 and Embeddings for Better RAG

Pure vector search misses exact-keyword queries. Pure BM25 misses semantic ones. Combining them with reciprocal rank fusion is the simplest large win in RAG retrieval.

KU

Kiril Urbonas·23

Read article