Skip to content

fix: load bm25 offline by listing only files present in its hf repo #728

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
joein merged 1 commit into from
Sep 24, 2026
Merged

fix: load bm25 offline by listing only files present in its hf repo #728

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions fastembed/sparse/bm25.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,9 +51,13 @@
license="apache-2.0",
size_in_GB=0.01,
sources=ModelSource(hf="Qdrant/bm25"),
additional_files=[f"{lang}.txt" for lang in supported_languages],
# The repo has no tamil.txt, and Tamil works without stopwords. Listing a missing file
# would make download_model reject every cached snapshot.
additional_files=[f"{lang}.txt" for lang in supported_languages if lang != "tamil"],
requires_idf=True,
model_file="mock.file",
# BM25 has no weights, but download_model requires model_file in a cached snapshot, so
# point it at the repo's (empty) config.json.
model_file="config.json",
),
]

Expand Down
Loading