Embedding does not work for Ollama, Mistral and LM Studio

[entrptaher]

Bug Description

This is my mistral embedding flow, which works outside of langflow.

Mistral embedding component throws error.

This is LM Studio and Ollama embedding flow,

Both of them throws error,

Embedding model client not properly initialized

I know they works outside of langflow, and even langflow can access it, otherwise it wouldn't be able to read the model names.

I thought okay, maybe all embeddings are broken on my version somehow, but then I tested with cohere and it definitely worked as per this screenshot.

Which means those components have issues.

This is the error trace,

warnings.warn(
[2025-01-13 01:09:54,589][ERROR] Error generating embeddings
Traceback (most recent call last):
File "", line 58, in generate_embeddings
AttributeError: 'URL' object has no attribute 'startswith'
[2025-01-13 01:12:12,447][ERROR] Error generating embeddings
Traceback (most recent call last):
File "", line 53, in generate_embeddings
ValueError: Embedding model client not properly initialized

Reproduction

Create a embedding with mistral, ollama or lm studio api.

Expected behavior

Embedding models works without throwing errors like it did with cohere embeddings.

Who can help?

No response

Operating System

Darwin Developers-Mini.lan 24.2.0 Darwin Kernel Version 24.2.0: Fri Dec 6 19:04:03 PST 2024; root:xnu-11215.61.5~2/RELEASE_ARM64_T8132 arm64

Langflow Version

Version 1.1.1.dev28 from langflowai/langflow-nightly:latest image

Python Version

None

Screenshot

No response

Flow File

No response

[entrptaher]

Not sure what I am missing here, even cloudflare embeddings does not work. So far only cohere worked.

[entrptaher]

I removed these check for client and it started working.

            # Check if the embedding model has the required attributes
            if not hasattr(embedding_model, "client") or not embedding_model.client:
                msg = "Embedding model client not properly initialized"
                raise ValueError(msg)

            # Ensure the base URL has proper protocol
            if hasattr(embedding_model.client, "base_url"):
                base_url = embedding_model.client.base_url
                if not base_url.startswith(("http://", "https://")):
                    embedding_model.client.base_url = f"https://{base_url}"

Result: