Qdrant/bm25 refetches from the Hub when fully cached (offline probe ignores the mock model_file)
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.2k
- Forks
- 248
- Avg merge
- 4d 8h
- Merged PRs (30d)
- 4
Description
What happened: On fastembed >=0.7.4, loading Qdrant/bm25 with a fully populated cache (HF_HUB_OFFLINE=1 or local_files_only=True) still triggers a live Hugging Face Hub fetch instead of resolving offline.
Why: bm25 is a mock model with model_file "mock.file" (no real weight file). The offline cache probe in ModelManagement.download_model requires the model_file to exist on disk; "mock.file" is never downloaded, so the check is always False and bm25 falls through to the network even when every real additional_files stop-word list is cached. #577 fixed the general cached case but not this mock-model path.
Repro: cache Qdrant/bm25, set HF_HUB_OFFLINE=1, load it. A Hub request is still attempted.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start in ModelManagement.download_model and reproduce the Qdrant/bm25 load with a populated cache and HF_HUB_OFFLINE=1. Trace how the mock model_file and cached additional_files affect the offline probe; done means loading bm25 offline does not attempt a Hugging Face Hub request.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 68/100