Easy Hybrid search Question 67 of 223

What is BM25?

GenAI / LLM · Speak this in 60–90 seconds · Faridabad & Delhi NCR

PICTURE THIS: AN LLM TURN

Text inTokens

TransformerAttention

Text outNext token

Simple meaning

BM25 is a ranking function for keyword search that scores term frequency with document-length normalization.

WHY — Tokens instead of words?

LLMs use tokens (not full words) because it helps them:

Hybrid search questions separate

people who only read docs from people who shipped.

Keep it short, concrete,

and tied to GenAI / LLM work.

Stable token IDs

Each piece maps to a number the network can learn.

Fits the model

Fixed pieces are what transformers expect as input.

STEPS — What happens with tokens?

Before the model can read a sentence, it goes through these steps:

1
BM25 is a ranking
function for keyword search that scores term frequency with document-length normalization.
2
It is strong on
exact product names, error codes, and legal phrases.
3
RAG systems often run
BM25 beside embeddings.
4
Context mix
Attention looks at nearby tokens together.
5
Next token
The model scores what should come next.
6
Decode
IDs turn back into readable text.

EXAMPLE — See it in action

Let's see how a real sentence is tokenized (tokens may vary by model):

Input text

“It is strong on exact product names, error codes, and legal phrases.”

Tokenized output

Itisstrongonexactproduct

Token IDs (example)

2987408337471632900

Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).

Key takeaway

BM25 is a ranking function for keyword search that scores term frequency with document-length normalization. It is strong on exact product names, error codes, and legal phrases.