# What is BM25? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Information Retrieval  
> **Canonical Citation:** [https://spidits.com/ai-glossary/bm25](https://spidits.com/ai-glossary/bm25)

## Definition
Okapi BM25 is a ranking function used by search engines to estimate the relevance of documents to a given search query. It is based on the probabilistic retrieval framework and improves upon TF-IDF by adding term frequency saturation and document length normalization.

## Architectural Mechanics & Deep Dive
Okapi BM25 is a classic, highly effective ranking algorithm used by search engines to estimate the relevance of a document to a given search query. Based on probabilistic information retrieval, BM25 improves upon simple TF-IDF by incorporating term frequency saturation (limiting the impact of a term appearing repeatedly in one document) and document length normalization (penalizing long documents that contain terms by chance).

## Industry Applications & Real-World Use Cases
Keyword search engines, hybrid search systems, and initial candidate retrieval in RAG.

## Frequently Asked Questions

### What is term frequency saturation in BM25?
It limits the impact of multiple term occurrences. If a keyword appears 20 times in a document, BM25 doesn't score it 20 times higher than if it appeared twice.

### Why is BM25 still popular in the era of vector search?
Because keyword search is highly precise for exact matches (like serial numbers or names) where semantic embeddings might fail due to lack of keyword specificity.

## Related Terminology
- [semantic-search](https://spidits.com/ai-glossary/semantic-search)
- [rag](https://spidits.com/ai-glossary/rag)

---
*From the SPIDITS AI Knowledge Base (336+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*