Skip to content

Add the normalize and truncate parameters to feature_extraction to be compatible with Text Embeddings Inference (TEI) #1877

@datavistics

Description

@datavistics

Is your feature request related to a problem? Please describe.
I would like to be able to use feature_extraction with full compatibility with Text Embeddings Inference: https://huggingface.github.io/text-embeddings-inference/#/Text%20Embeddings%20Inference/embed

Describe the solution you'd like
We should add the ability to put truncate and normalize in the post call

Describe alternatives you've considered
Ive tried workarounds, which involve overwriting the methods, but my friends made fun of my ugly code.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions