---
title: "Blog | Ceisium"
description: "Technical articles about crawling, indexing, retrieval, and website search."
canonical: https://ceisium.com/blog/
---

> For the complete documentation and public content index, see [llms.txt](/llms.txt). This page is the Markdown alternative to the canonical HTML page.

# Blog | Ceisium

Current public articles:

## Ceisium technical articles

- [BM25 in RAG: Why Exact Keywords Still Matter](https://ceisium.com/blog/bm25-in-rag/index.md): Dense retrieval can miss error codes, identifiers, and exact phrases. BM25 gives RAG systems another path to the source evidence they need.
- [Boolean Retrieval: AND, OR, and NOT in Search](https://ceisium.com/blog/boolean-retrieval/index.md): Learn how Boolean search uses AND, OR, and NOT to combine result sets, where exact control helps, and why website search still needs ranking.
- [Document Length Normalization: Why Long Pages Need Context](https://ceisium.com/blog/document-length-normalization/index.md): Learn why long pages get more chances to match a search query, how BM25 adjusts for relative document length, and why shorter is not automatically better.
- [How Website Crawling Shapes Search Quality](https://ceisium.com/blog/how-website-crawling-shapes-search-quality/index.md): Learn how crawl scope, sitemaps, rendering, URL identity, and recrawl freshness shape the pages a site-search ranker can choose from.
- [Semantic Search vs Keyword Search: How to Choose and When to Combine Them](https://ceisium.com/blog/semantic-search-vs-keyword-search/index.md): Keyword search uses literal evidence. Embedding-based semantic search bridges vocabulary gaps. Learn where each fails and when hybrid retrieval earns its added complexity.
- [TF-IDF: The Search Ranking Idea Behind BM25](https://ceisium.com/blog/what-is-tf-idf/index.md): TF-IDF is a classic lexical ranking method that scores documents using repeated query words and rare query words. Learn how it works, where it helps, and how BM25 addresses some of its limits.
- [What Is an Inverted Index?](https://ceisium.com/blog/what-is-an-inverted-index/index.md): An inverted index maps terms to the documents that contain them, helping search engines find text matches without scanning every page.
- [What is BM25? A Plain English Guide](https://ceisium.com/blog/what-is-bm25/index.md): BM25 is a keyword search ranking function that scores documents using term frequency, term rarity, and document length. Learn how it works, where it helps, and how it differs from TF-IDF.
- [What Is Hybrid Search?](https://ceisium.com/blog/what-is-hybrid-search/index.md): Hybrid search combines keyword and vector retrieval. Learn how fusion, candidate windows, filters, and reranking turn two result lists into one.
- [What is Inverse Document Frequency?](https://ceisium.com/blog/what-is-inverse-document-frequency/index.md): Inverse document frequency helps search rank rare query words above words that appear everywhere. Learn the idea with a simple docs-search example.
- [What Is Tokenization in Search?](https://ceisium.com/blog/what-is-tokenization-in-search/index.md): Learn how search engines split and normalize page text and queries into searchable terms, and why those choices can decide which pages reach ranking.
- [What Is Vector Search?](https://ceisium.com/blog/what-is-vector-search/index.md): Vector search finds related content by comparing embeddings. Learn how vectors, similarity, approximate nearest-neighbor search, and hybrid retrieval work together.