Skip to content

[BUG]: retriever query should default to HuggingFace for embedding #2185

@randerzander

Description

@randerzander

Version

26.5.0

Which installation method(s) does this occur on?

No response

Describe the bug.

retriever query currently uses vLLM for doing query embedding, which is much higher latency than HuggingFace

Minimum reproducible example

Relevant log output

Other/Misc.

No response

Metadata

Metadata

Assignees

No one assigned

    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