BUG: fix ImportError when optional dependency FlagEmbedding is not installed #2649
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
qinxuye
reviewed
Dec 10, 2024
|
Tests seem failed. |
…onal dependency FlagEmbedding is not installed.
3 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
#2540 introduces
FlagEmbeddingpackage to support sparse vector for bge-m3. However,FlagEmbeddingis an optional dependency for embedding model (but required for rerank):inference/setup.cfg
Lines 184 to 187 in 70a0081
In the case
FlagEmbeddingis not installed, anImportErrorwill be raised even if embedding models only based onsentence-transformersare used, due to the logic related toBGEM3FlagModel. This PR fixes this problem.By the way, maybe adding
FlagEmbeddingto required dependency for embedding is not suitable now until upstream solve the dependency, since it requirestransformers==4.44.2(https://github.com/FlagOpen/FlagEmbedding/blob/master/setup.py#L18) and will make models like Qwen2-VL unusable (https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct/discussions/5).