Skip to content

[BUG] OpenAI Compatible Embedder validation fails against llama.cpp #593

@General-Disorder

Description

@General-Disorder

Problem (one or two sentences)

OpenAI Compatible Embedder validation fails against llama.cpp
when configured with a base URL.

Using the exact embeddings endpoint URL
(http://host:port/v1/embeddings)
forces the direct-request code path and succeeds.

Context (who is affected and when)

Anyone using llama.cpp through OpenAI Compatible Provider configuring a base url

Reproduction steps

Set up llama.cpp with embed model (eg Nomic)
Point Zoo code indexing to it using base url

Expected result

Should work with base url

Actual result

error is shown : embeddings:validation.invalidResponse

Variations tried (optional)

No response

App Version

3.58.1

API Provider (optional)

OpenAI Compatible

Model Used (optional)

omic-embed-text-v2-moe.Q4_K_M.gguf

Zoo Code Task Links (optional)

No response

Relevant logs or errors (optional)

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    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