Skip to content
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.

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

Dependency bug from chroma 0.5.23 at SentenceTransformerEmbeddingFunction #3271

Open
kirankotari opened this issue Dec 9, 2024 · 1 comment

Comments

@kirankotari
Copy link

kirankotari commented Dec 9, 2024

Transformer library updated to use "tokenizers>=0.21,<0.22" (released 4 days ago)
Where in chroma we are still point to 'tokenizers >= 0.13.2, <= 0.20.3',

Which creating dependency conflict, can you please update tokenizers to latest package.

Here is the I am trying to run

sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(
    model_name="all-MiniLM-L6-v2"
)

Links:
https://github.com/huggingface/transformers/blob/34f4080ff59b1668d919a1ba9f8bc4a3a2a3f478/setup.py#L183C5-L183C30
https://github.com/chroma-core/chroma/blob/1110d07f17c75e44c372361fd2684f5b08edec0d/pyproject.toml#L31C3-L31C37

I tried to use lower version, which started creating more issues, related to torch 2.5.1 compatible not found.

Platform:
MacOS
Python 3.12.4

@kirankotari kirankotari changed the title Dependency bug from chroma 0.5.23 Dependency bug from chroma 0.5.23 at SentenceTransformerEmbeddingFunction Dec 9, 2024
@kokhoor
Copy link

kokhoor commented Dec 17, 2024

is it safe to use tokenizers version 0.21.0 with chromadb?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants