Model reference · open weights
bm25 is an open-weight embedding model from Qdrant.
Summary of the Qdrant/bm25 model card, 2026-10-01
What it is
| Released by | Qdrant |
|---|---|
| Released | 2024-06-13 |
From the model card
Repository with files to perform BM25 searches with FastEmbed.
BM25 (Best Matching 25) is a ranking function used by search engines to estimate the relevance of documents to a given search query.
Note: This model is supposed to be used with Qdrant. Vectors have to be configured with Modifier.IDF.
Here's an example of BM25 with FastEmbed.
from fastembed import SparseTextEmbedding
documents = [
"You should stay, study and sprint.",
"History can only prepare us to be surprised yet again.",
]
model = SparseTextEmbedding(model_name="Qdrant/bm25")
embeddings = list(model.embed(documents))
# [
# SparseEmbedding(
# values=array([1.67419738, 1.67419738, 1.67419738, 1.67419738]),
# indices=array([171321964, 1881538586, 150760872, 1932363795])),
# SparseEmbedding(values=array(
# [1.66973021, 1.66973021, 1.66973021, 1.66973021, 1.66973021]),
# indices=array([
# 578407224, 1849833631, 1008800696, 2090661150,
# 1117393019
# ]))
# ]
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
How it works